Can AI with High Reasoning Ability Replicate Human-like Decision Making in Economic Experiments?

Ayato Kitadai, Sinndy Dayana Rico Lugo, Yudai Tsurusaki, Yusuke Fukasawa, Nariaki Nishino · Group Decision and Negotiation · 2025 · experimental-economics · 10.1007/s10726-025-09946-9 · record kitadai2025-can-ai-with-high-reasoning-ability
tag layer · index · concepts · authors · עברית

Where this record's text came from. faceted 2026-08 by reading the locally held text (pdftext); every evidence string verified as an exact substring of that text before merging. Claim type is null-result rather than method: the paper builds a simulation framework, but its headline finding is that the hypothesised improvement (more reasoning → more human-like behaviour) did not occur, and the authors conclude that LLM agents are currently unwarranted stand-ins for human groups. The paper also attempts to reproduce Lin et al. (2020)'s human ultimatum-game data in silico and fails to match it; that is a simulation of an experiment rather than an independent replication of this paper's own claim, so replication status stays 'untested' — the internal robustness checks (15 and 20 examples, re-drawn random seeds) are the authors' own, not external. A secondary positive claim about personas is present ('The results also suggest that setting the personas of the generative agents may be important for reproducing the results of real economic experiments.') but is hedged and not the paper's central result, so it is not the recorded claim_type. 2026-08-14 and 2026-08-15 schema-0.3 passes: every quote verified as an exact substring of the staged text and anchored at merge time; concept terms verified present; every edge endpoint an existing node.

How to read this page. The article itself is not reproduced here — this paper is not cleared for redistribution, so what follows is the tag layer alone. The evidence sentences are withheld with the article. The table at the foot lists every tag the record carries; each row names the facet it belongs to, and the whose words column says whether the tag records the paper's own wording or the tagger's sentence about the paper. Every tag links to each other paper in the corpus carrying it. The machine-readable edition of the same thing is the TEI file beside this one, where the tags live in standOff, and the article is at its publisher via the link below. When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.

Other fields define these differently the same word, defined another way in another discipline
interpretability 3 fields · LLMs 2 fields · confidence interval 2 fields · simulation 2 fields · bounded rationality 2 fields · social context 2 fields

Tags on this paper

Every tag the record carries, each linking to every other paper in the corpus that carries it. A tag appears here whether or not its words occur in the article — the spans below are only the ones a sentence in this paper licenses. Of the 121 concept tags on this paper, all 121 are grounded in a quoted sentence. 115 carry the tagger's gloss of what the term means in this paper, which is not something the article can license.

generative agent economic experiments behavioral realism reasoning ability theoretical solution persona one-shot ultimatum game history-dependent learning reputation effects subgame-perfect equilibrium theoretical benchmark human-AI performance gap stringent test bed artificial correlations weakly dominant strategy perceived unfairness LLM agents traditional economic experiments additional methodological tool opaque biases harmful stereotypes structural inequities ground-truth benchmarks LLM-based simulations boundary conditions outputs of generative agents simulation design choices Generative AI generative models discriminative models underlying data distribution recognition to generation methodological transformation LLMs key subclass Transformer architecture statistical knowledge base social norms strategic heuristics foundation models general-purpose substrates downstream tasks retraining hallucinations learned statistical associations grounded world models black boxes interpretability prompt design few-shot prompting chain-of-thought (CoT) prompting general mitigation techniques scaffolding methods prompting strategies reasoning quality coherence, inference depth, and contextual relevance contextually coherent, multi-step responses inferential structure observable behavioral property experimental variable pragmatist perspective human cognition behavioral patterns methodological tools well-defined simulation contexts empirical tools evaluation protocols methodological safeguards coarse-grained evaluation criteria aggregate distributions individual-level deviations finer-grained behavioral criteria game-theoretic environments failures of alignment behavioral Turing tests latent utility function perceived social harmony material self-interest Persona design behavioral tendencies causal effects reasoning-related prompting strategy confounding variables central research question normative benchmarks of rationality empirically grounded human behavior simulation framework three sequential steps output format 1000 independent decisions formal power analysis robustness check computational cost per generation statistical resolution feasibility in simulation-based research substitutes for human participants agent-based modeling natural language reasoning prompt engineering Monte Carlo methods experimental instructions human-subject experiments Anderson-Darling (AD) Kolmogorov-Smirnov (KS) overall distributional differences maximum cumulative distribution differences social context stand-ins for real human groups treating LLMs as direct substitutes for human subjects flawed approach methodological scaffolding Persona settings contextual variables human decision-making inequity aversion fairness equilibrium bounded rationality social preferences Variability in reasoning ability and persona configurations agent behavior simulation outcomes Persona settings act as a proxy that embeds social preferences and bounded rationality into the agents; without them the agents' improved reasoning drives them to the subgame-perfect solution instead of to human-like fairness behaviour Randomly generated persona attributes in earlier studies injected noise into agent behaviour, which masked the effect of reasoning ability and prevented it from being evaluated systematically Skew in how the agents' offers were distributed across offer values drives the fitted acceptance-rate lines to impossible values above 1.0 or below 0, producing the anomalies seen in the responder-side figures Platonic Representation Hypothesis temperature parameter GPT model acceptance rate Anderson-Darling test Kolmogorov-Smirnov test p-value regression piecewise linear regression confidence interval simulation

Legend

relation to other work	`claim_relations`	how this paper stands to another: agrees, contradicts, extends, qualifies
claim type	`claim_type`	the shape of the claim: existence, mechanism, method, critique, prediction, null
concept edge	`concept_edges`	an asserted relation between two concepts, with the sentence asserting it
concept	`concepts`	an idea the paper works with, quoted where the paper uses it
content tag	`content_tags`	a finding, definition, quantity, statistic or variable named in the paper
control	`controls`	an experiment run to eliminate a rival explanation
limitation	`limitations`	what the paper says its evidence cannot support
mechanism	`mechanisms`	how the reported effect is said to come about
method	`method`	how the paper produced its evidence
phenomenon	`phenomenon`	the effect or regularity under study
sense	`senses`	a distinct use of a term, quoted where the paper fixes it
transfer	`transfers`	a method or concept carried in from another field
unrecordable relation	`unhoused_relations`	a relation the paper asserts that this vocabulary cannot express, with the reason

The paper

The full text is not reproduced here. This article is not cleared for redistribution, so the page carries the tag layer only. Its evidence sentences are withheld; the grounding status remains with each tag, and the article itself is at https://doi.org/10.1007/s10726-025-09946-9. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 3 · claim_type 1 · concept_edges 10 · concepts 121 · content_tags 28 · controls 1 · limitations 7 · mechanisms 3 · method 1 · phenomenon 1 · senses 23 · transfers 1 · unhoused_relations 8

Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; 8 of 10 relations here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.

facet	tag	field	conf.	whose words
claim_type	null-result Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_type`		the paper's words
phenomenon	LLM generative agents in the ultimatum game Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`phenomenon`		the paper's words
method	simulation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: simulation	`method`		the paper's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Persona settings act as a proxy that embeds social preferences and bounded rationality into the agents; without them the agents' improved reasoning drives them to the subgame-perfect solution instead of to human-like fairness behaviour	`mechanisms[0]`		the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Randomly generated persona attributes in earlier studies injected noise into agent behaviour, which masked the effect of reasoning ability and prevented it from being evaluated systematically	`mechanisms[1]`		the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Skew in how the agents' offers were distributed across offer values drives the fitted acceptance-rate lines to impossible values above 1.0 or below 0, producing the anomalies seen in the responder-side figures	`mechanisms[2]`		the tagger's words
limitations	Excluding persona settings in order to isolate reasoning ability is itself a limitation, since personas are known to shape human-like behaviour. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the transfer to agents with personas: WHILE OUR METHODOLOGICAL CHOICE CLARIFIES THE ROLE OF REASONING ABILITY, IT ALSO REPRESENTS A LIMITATION OF THIS STUDY - the excluded factor is known to matter	`limitations[0]`		the tagger's words
limitations	The sample size of 1000 decisions per condition was chosen pragmatically rather than by a formal power analysis. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the precision of every estimate: WHILE THIS NUMBER IS NOT DERIVED FROM A FORMAL POWER ANALYSIS, IT WAS SELECTED BASED ON TWO MAIN CONSIDERATIONS	`limitations[1]`		the tagger's words
limitations	Scope is restricted to decision-making and negotiation tasks; market-level and institutional applications are left to future work. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the scope of the conclusions: BROADER APPLICATIONS TO MARKET-LEVEL MODELING OR INSTITUTIONAL DESIGN REMAIN IMPORTANT DIRECTIONS FOR FUTURE WORK	`limitations[2]`		the tagger's words
limitations	Earlier claims of success are attributed to the coarseness of the evaluation rather than to the agents: aggregate distributions and binary alignment, with no individual-level analysis. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: published findings that generative agents reproduce human behaviour in economic games: this paper states those successes may stem from coarse-grained criteria — aggregate distributions or binary alignment — without individual-level or reasoning-process analysis	`limitations[3]`	1.0	the tagger's words
limitations	The expectation the title asks about is not borne out: greater reasoning ability does not directly produce reproduction of the experiments. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the assumption that a more capable model will simulate an economic experiment better: this paper reports zero-shot prompting with an older model aligning closely with human behaviour, and states improving reasoning ability cannot lead directly to reproduction	`limitations[4]`	1.0	the tagger's words
limitations	The paper's own explanation of why earlier work succeeded is a claim about MEASUREMENT RESOLUTION, not about behaviour: prior studies assessed aggregate distributions or binary alignment 'without deeper analysis of underlying reasoning processes or individual-level deviations'. On that account the earlier results are not wrong, they are coarse - which is a harder thing to test. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[5]`	0.9	the tagger's words
limitations	Agent outputs are reported as highly sensitive to design choices - persona, prompt formulation, role instructions - so any single configuration's result is conditional on choices the paper had to make and could not vary at once. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[6]`	0.85	the tagger's words
transfers	Prompt-engineering techniques for eliciting language-model reasoning are imported into the agent-based-modelling tradition of experimental economics, with prompts standing in for experimental instructions to human subjects. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`transfers[0]`		the tagger's words
controls	the in-context examples RE-DRAWN AT RANDOM from the raw data and the whole simulation re-run several times, alongside runs at 15 and 20 examples Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: the particular examples chosen for the prompt as the source of the result - an LLM's behaviour is conditioned on its examples, so a finding from one draw is a fact about that draw · outcome (stated by the tagger, no quotation): held	`controls[0]`	0.9	the tagger's words
concepts	generative agent Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: generative agent	`concepts[0]`		the paper's words
concepts	economic experiments Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: economic experiments	`concepts[1]`		the paper's words
concepts	behavioral realism Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: behavioral realism	`concepts[2]`		the paper's words
concepts	reasoning ability Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: reasoning ability	`concepts[3]`	0.95	the paper's words
concepts	theoretical solution Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: theoretical solution	`concepts[4]`	0.95	the paper's words
concepts	persona Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: persona	`concepts[5]`	0.9	the paper's words
concepts	one-shot ultimatum game Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: one-shot ultimatum game	`concepts[6]`	0.95	the paper's words
concepts	history-dependent learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: history-dependent learning	`concepts[7]`	0.95	the paper's words
concepts	reputation effects Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: reputation effects	`concepts[8]`	0.95	the paper's words
concepts	subgame-perfect equilibrium Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: subgame-perfect equilibrium	`concepts[9]`	0.95	the paper's words
concepts	theoretical benchmark Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: theoretical benchmark	`concepts[10]`	0.95	the paper's words
concepts	human-AI performance gap Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: human-AI performance gap	`concepts[11]`	0.95	the paper's words
concepts	stringent test bed Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: stringent test bed	`concepts[12]`	0.95	the paper's words
concepts	artificial correlations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: artificial correlations	`concepts[13]`	0.95	the paper's words
concepts	weakly dominant strategy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: weakly dominant strategy	`concepts[14]`	0.95	the paper's words
concepts	perceived unfairness Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: perceived unfairness	`concepts[15]`	0.95	the paper's words
concepts	LLM agents Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: LLM agents	`concepts[16]`	0.95	the paper's words
concepts	traditional economic experiments Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: traditional economic experiments	`concepts[17]`	0.95	the paper's words
concepts	additional methodological tool Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: additional methodological tool	`concepts[18]`	0.95	the paper's words
concepts	opaque biases Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: opaque biases	`concepts[19]`	0.95	the paper's words
concepts	harmful stereotypes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: harmful stereotypes	`concepts[20]`	0.95	the paper's words
concepts	structural inequities Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: structural inequities	`concepts[21]`	0.95	the paper's words
concepts	ground-truth benchmarks Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: ground-truth benchmarks	`concepts[22]`	0.95	the paper's words
concepts	LLM-based simulations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: LLM-based simulations	`concepts[23]`	0.95	the paper's words
concepts	boundary conditions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: boundary conditions	`concepts[24]`	0.95	the paper's words
concepts	outputs of generative agents Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: outputs of generative agents	`concepts[25]`	0.95	the paper's words
concepts	simulation design choices Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: simulation design choices	`concepts[26]`	0.95	the paper's words
concepts	Generative AI Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Generative AI	`concepts[27]`	0.95	the paper's words
concepts	generative models Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: generative models	`concepts[28]`	0.95	the paper's words
concepts	discriminative models Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: discriminative models	`concepts[29]`	0.95	the paper's words
concepts	underlying data distribution Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: underlying data distribution	`concepts[30]`	0.95	the paper's words
concepts	recognition to generation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: recognition to generation	`concepts[31]`	0.95	the paper's words
concepts	methodological transformation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: methodological transformation	`concepts[32]`	0.95	the paper's words
concepts	LLMs Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: LLMs	`concepts[33]`	0.95	the paper's words
concepts	key subclass Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: key subclass	`concepts[34]`	0.95	the paper's words
concepts	Transformer architecture Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Transformer architecture	`concepts[35]`	0.95	the paper's words
concepts	statistical knowledge base Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: statistical knowledge base	`concepts[36]`	0.95	the paper's words
concepts	social norms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: social norms	`concepts[37]`	0.95	the paper's words
concepts	strategic heuristics Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: strategic heuristics	`concepts[38]`	0.95	the paper's words
concepts	foundation models Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: foundation models	`concepts[39]`	0.95	the paper's words
concepts	general-purpose substrates Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: general-purpose substrates	`concepts[40]`	0.95	the paper's words
concepts	downstream tasks Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: downstream tasks	`concepts[41]`	0.95	the paper's words
concepts	retraining Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: retraining	`concepts[42]`	0.95	the paper's words
concepts	hallucinations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: hallucinations	`concepts[43]`	0.95	the paper's words
concepts	learned statistical associations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: learned statistical associations	`concepts[44]`	0.95	the paper's words
concepts	grounded world models Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: grounded world models	`concepts[45]`	0.95	the paper's words
concepts	black boxes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: black boxes	`concepts[46]`	0.95	the paper's words
concepts	interpretability Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: interpretability	`concepts[47]`	0.95	the paper's words
concepts	prompt design Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: prompt design	`concepts[48]`	0.95	the paper's words
concepts	few-shot prompting Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: few-shot prompting	`concepts[49]`	0.95	the paper's words
concepts	chain-of-thought (CoT) prompting Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: chain-of-thought (CoT) prompting	`concepts[50]`	0.95	the paper's words
concepts	general mitigation techniques Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: general mitigation techniques	`concepts[51]`	0.95	the paper's words
concepts	scaffolding methods Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: scaffolding methods	`concepts[52]`	0.95	the paper's words
concepts	prompting strategies Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: prompting strategies	`concepts[53]`	0.95	the paper's words
concepts	reasoning quality Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: reasoning quality	`concepts[54]`	0.95	the paper's words
concepts	coherence, inference depth, and contextual relevance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: coherence, inference depth, and contextual relevance	`concepts[55]`	0.95	the paper's words
concepts	contextually coherent, multi-step responses Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: contextually coherent, multi-step responses	`concepts[56]`	0.95	the paper's words
concepts	inferential structure Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: inferential structure	`concepts[57]`	0.95	the paper's words
concepts	observable behavioral property Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: observable behavioral property	`concepts[58]`	0.95	the paper's words
concepts	experimental variable Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: experimental variable	`concepts[59]`	0.95	the paper's words
concepts	pragmatist perspective Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: pragmatist perspective	`concepts[60]`	0.95	the paper's words
concepts	human cognition Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: human cognition	`concepts[61]`	0.95	the paper's words
concepts	behavioral patterns Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: behavioral patterns	`concepts[62]`	0.95	the paper's words
concepts	methodological tools Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: methodological tools	`concepts[63]`	0.95	the paper's words
concepts	well-defined simulation contexts Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: well-defined simulation contexts	`concepts[64]`	0.95	the paper's words
concepts	empirical tools Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: empirical tools	`concepts[65]`	0.95	the paper's words
concepts	evaluation protocols Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: evaluation protocols	`concepts[66]`	0.95	the paper's words
concepts	methodological safeguards Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: methodological safeguards	`concepts[67]`	0.95	the paper's words
concepts	coarse-grained evaluation criteria Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: coarse-grained evaluation criteria	`concepts[68]`	0.95	the paper's words
concepts	aggregate distributions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: aggregate distributions	`concepts[69]`	0.95	the paper's words
concepts	individual-level deviations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: individual-level deviations	`concepts[70]`	0.95	the paper's words
concepts	finer-grained behavioral criteria Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: finer-grained behavioral criteria	`concepts[71]`	0.95	the paper's words
concepts	game-theoretic environments Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: game-theoretic environments	`concepts[72]`	0.95	the paper's words
concepts	failures of alignment Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: failures of alignment	`concepts[73]`	0.95	the paper's words
concepts	behavioral Turing tests Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: behavioral Turing tests	`concepts[74]`	0.95	the paper's words
concepts	latent utility function Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: latent utility function	`concepts[75]`	0.95	the paper's words
concepts	perceived social harmony Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: perceived social harmony	`concepts[76]`	0.95	the paper's words
concepts	material self-interest Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: material self-interest	`concepts[77]`	0.95	the paper's words
concepts	Persona design Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Persona design	`concepts[78]`	0.95	the paper's words
concepts	behavioral tendencies Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: behavioral tendencies	`concepts[79]`	0.95	the paper's words
concepts	causal effects Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: causal effects	`concepts[80]`	0.95	the paper's words
concepts	reasoning-related prompting strategy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: reasoning-related prompting strategy	`concepts[81]`	0.95	the paper's words
concepts	confounding variables Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: confounding variables	`concepts[82]`	0.95	the paper's words
concepts	central research question Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: central research question	`concepts[83]`	0.95	the paper's words
concepts	normative benchmarks of rationality Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: normative benchmarks of rationality	`concepts[84]`	0.95	the paper's words
concepts	empirically grounded human behavior Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: empirically grounded human behavior	`concepts[85]`	0.95	the paper's words
concepts	simulation framework Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: simulation framework	`concepts[86]`	0.95	the paper's words
concepts	three sequential steps Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: three sequential steps	`concepts[87]`	0.95	the paper's words
concepts	output format Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: output format	`concepts[88]`	0.95	the paper's words
concepts	1000 independent decisions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: 1000 independent decisions	`concepts[89]`	0.95	the paper's words
concepts	formal power analysis Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: formal power analysis	`concepts[90]`	0.95	the paper's words
concepts	robustness check Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: robustness check	`concepts[91]`	0.95	the paper's words
concepts	computational cost per generation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: computational cost per generation	`concepts[92]`	0.95	the paper's words
concepts	statistical resolution Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: statistical resolution	`concepts[93]`	0.95	the paper's words
concepts	feasibility in simulation-based research Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: feasibility in simulation-based research	`concepts[94]`	0.95	the paper's words
concepts	substitutes for human participants Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: substitutes for human participants	`concepts[95]`	0.95	the paper's words
concepts	agent-based modeling Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: agent-based modeling	`concepts[96]`	0.95	the paper's words
concepts	natural language reasoning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: natural language reasoning	`concepts[97]`	0.95	the paper's words
concepts	prompt engineering Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: prompt engineering	`concepts[98]`	0.95	the paper's words
concepts	Monte Carlo methods Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Monte Carlo methods	`concepts[99]`	0.95	the paper's words
concepts	experimental instructions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: experimental instructions	`concepts[100]`	0.95	the paper's words
concepts	human-subject experiments Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: human-subject experiments	`concepts[101]`	0.95	the paper's words
concepts	Anderson-Darling (AD) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Anderson-Darling (AD)	`concepts[102]`	0.95	the paper's words
concepts	Kolmogorov-Smirnov (KS) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Kolmogorov-Smirnov (KS)	`concepts[103]`	0.95	the paper's words
concepts	overall distributional differences Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: overall distributional differences	`concepts[104]`	0.95	the paper's words
concepts	maximum cumulative distribution differences Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: maximum cumulative distribution differences	`concepts[105]`	0.95	the paper's words
concepts	social context Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: social context	`concepts[106]`	0.95	the paper's words
concepts	stand-ins for real human groups Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: stand-ins for real human groups	`concepts[107]`	0.95	the paper's words
concepts	treating LLMs as direct substitutes for human subjects Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: treating LLMs as direct substitutes for human subjects	`concepts[108]`	0.95	the paper's words
concepts	flawed approach Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: flawed approach	`concepts[109]`	0.95	the paper's words
concepts	methodological scaffolding Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: methodological scaffolding	`concepts[110]`	0.95	the paper's words
concepts	Persona settings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Persona settings	`concepts[111]`	0.95	the paper's words
concepts	contextual variables Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: contextual variables	`concepts[112]`	0.95	the paper's words
concepts	human decision-making Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: human decision-making	`concepts[113]`	0.95	the paper's words
concepts	inequity aversion Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: inequity aversion	`concepts[114]`	0.95	the paper's words
concepts	fairness equilibrium Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: fairness equilibrium	`concepts[115]`	0.95	the paper's words
concepts	bounded rationality Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: bounded rationality	`concepts[116]`	0.95	the paper's words
concepts	social preferences Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: social preferences	`concepts[117]`	0.95	the paper's words
concepts	Variability in reasoning ability and persona configurations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Variability in reasoning ability and persona configurations	`concepts[118]`	0.95	the paper's words
concepts	agent behavior Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: agent behavior	`concepts[119]`	0.95	the paper's words
concepts	simulation outcomes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: simulation outcomes	`concepts[120]`	0.95	the paper's words
unhoused_relations	LLM agents → traditional economic experiments Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. LLM agents are proposed to augment rather than replace traditional economic experiments. Augments-but-does-not-replace is absent from the eight types; distinct-from would lose the methodological complement relation.	`unhoused_relations[0]`	0.95	the tagger's words
unhoused_relations	ground-truth benchmarks → LLM-based simulations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Human data remain indispensable benchmarks for calibrating LLM simulations and identifying their boundary conditions. Benchmark-for/calibrates is absent from the eight types and is not mere operationalisation.	`unhoused_relations[1]`	0.95	the tagger's words
unhoused_relations	outputs of generative agents → simulation design choices Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Generative-agent outputs are highly sensitive to simulation design choices. Depends-on/sensitive-to is absent; causation would overstate a design dependence with multiple interacting parameters.	`unhoused_relations[2]`	0.95	the tagger's words
unhoused_relations	foundation models → downstream tasks Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Foundation models are adaptable to downstream tasks without retraining. Adaptable-to is absent from the eight types; neither kindhood nor operationalisation captures transfer to a task.	`unhoused_relations[3]`	0.95	the tagger's words
unhoused_relations	prompt engineering → experimental instructions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Prompt engineering serves as an analog to instructions given to human participants. Analogous-to is absent; same-as would erase the distinction between machine prompts and human-study instructions.	`unhoused_relations[4]`	0.95	the tagger's words
unhoused_relations	social context → stand-ins for real human groups Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Prompts incorporating social context are a necessary condition for advanced LLMs to serve as human-like stand-ins. Prerequisite-for is absent from the eight relation types.	`unhoused_relations[5]`	0.95	the tagger's words
unhoused_relations	Persona settings → social preferences Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Persona inclusion may act as a proxy for embedding social preferences in the simulation. Proxy-for is absent; operationalised-as would claim a measurement definition the paper does not make.	`unhoused_relations[6]`	0.95	the tagger's words
unhoused_relations	Persona settings → bounded rationality Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Persona inclusion may proxy bounded rationality in LLM-driven simulations. Proxy-for is absent from the eight types and the paper presents this as a hypothesis.	`unhoused_relations[7]`	0.95	the tagger's words
senses	replication of human behaviour - AT AGGREGATE GRAIN: distributions of choices or binary alignment with typical outcomes, which is the criterion under which earlier work succeeded Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	1.0	the tagger's words
senses	replication of human behaviour - AT INDIVIDUAL GRAIN: underlying reasoning processes and individual-level deviations, which the earlier evaluations did not examine Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	1.0	the tagger's words
senses	agent quality - split into two properties that trade off against each other: behavioral realism and rationality Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	1.0	the tagger's words
senses	successful replication - in the prior literature a claim about AGGREGATE DISTRIBUTIONS or binary alignment with typical outcomes; this paper attributes those successes to the coarseness of the criterion rather than to the agents Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[3]`	0.95	the tagger's words
senses	One-shot ultimatum game - a demanding test that removes learning and reputation and supplies a unique equilibrium benchmark Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[4]`	0.95	the tagger's words
senses	Human low-offer rejection - payoff sacrifice explained as resistance to perceived unfairness Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[5]`	0.95	the tagger's words
senses	Generative AI - distribution-learning synthesis rather than classification within existing boundaries Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[6]`	0.95	the tagger's words
senses	GPT-4 as behavioral model - a statistical knowledge base reflecting norms, heuristics, and communication conventions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[7]`	0.95	the tagger's words
senses	Hallucination - plausible but wrong output arising from association-based rather than grounded modeling Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[8]`	0.95	the tagger's words
senses	Few-shot prompting - annotated examples guiding output style and logic Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[9]`	0.95	the tagger's words
senses	Chain-of-thought prompting - explicit instruction to articulate intermediate reasoning steps Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[10]`	0.95	the tagger's words
senses	Reasoning ability - observable coherent multi-step response structure, not a claim about mental models or logical soundness Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[11]`	0.95	the tagger's words
senses	LLMs as empirical tools - outputs analyzed, compared, and validated like participant data under safeguards Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[12]`	0.95	the tagger's words
senses	Replication success under coarse criteria - aggregate distributions or binary typical-outcome alignment without individual reasoning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[13]`	0.95	the tagger's words
senses	Latent utility hypothesis - agents may optimize perceived social harmony rather than material self-interest Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[14]`	0.9	the tagger's words
senses	Isolated reasoning manipulation - vary zero-shot, few-shot, and chain-of-thought while holding persona, framing, and temperature outside the focal contrast Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[15]`	0.95	the tagger's words
senses	Core validity question - convergence toward normative rationality versus divergence from observed human behavior Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[16]`	0.95	the tagger's words
senses	Simulation sample - 1000 independent decisions balancing statistical resolution against chain-of-thought cost Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[17]`	0.95	the tagger's words
senses	Prompt engineering - methodological analog of instructions delivered to human experimental participants Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[18]`	0.95	the tagger's words
senses	AD versus KS - overall distributional difference versus maximum cumulative distribution difference Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[19]`	0.95	the tagger's words
senses	LLMs as human stand-ins - currently unwarranted without explicit social context and methodological scaffolding Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[20]`	0.95	the tagger's words
senses	Persona settings - configured cultural, age, and gender context needed because current models do not inherently possess it Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[21]`	0.95	the tagger's words
senses	Persona as behavioral proxy - possible embedding of social preferences and bounded rationality Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[22]`	0.9	the tagger's words
claim_relations	extends → Kitadai et al. (2023) LLM-driven ultimatum-game simulation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[0]`		the tagger's words
claim_relations	contradicts → Horton (2023) and Aher et al. (2023) reports of successful behavioural replication by LLM agents Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[1]`		the tagger's words
claim_relations	builds-on → prior LLM-agent studies that confounded reasoning with persona, payoff framing and temperature Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[2]`		the tagger's words
concept_edges	reasoning ability —causes→ theoretical solution Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. differs in: WHICH TARGET THE AGENTS CONVERGE ON, and the two targets pull apart: raising reasoning ability moves the simulation TOWARDS the game-theoretic solution and AWAY from the human experimental result. Better reasoning makes the agent a worse model of people - the paper's title asks the question and its abstract answers no · strength of the relation: 0.9 Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but higher reasoning moved results closer to the theoretical solution; causes is loose. also in: reasoning ability · theoretical solution	`concept_edges[0]`	0.95	the tagger's words
concept_edges	reasoning ability —contrasted-with→ behavioral realism Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 0.8 · note: The record already carries a sense saying agent quality splits into two properties that TRADE OFF. This edge is that trade-off as the paper measured it. Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but higher reasoning moved results away from real experimental results; contrasted-with 'behavioral realism' is loose. also in: reasoning ability · behavioral realism	`concept_edges[2]`	0.9	the tagger's words
concept_edges	Generative AI —distinct-from→ discriminative models Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The paper explicitly contrasts distribution-learning generation with classification and prediction. also in: Generative AI · discriminative models	`concept_edges[5]`	0.95	the tagger's words
concept_edges	opaque biases —causes→ harmful stereotypes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 0.7 · note: The paper says biases can perpetuate or amplify harmful stereotypes. also in: opaque biases · harmful stereotypes	`concept_edges[6]`	0.95	the tagger's words
concept_edges	scaffolding methods —distinct-from→ general mitigation techniques Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The authors explicitly adopt the strategies not as general mitigation but as reasoning scaffolds. also in: scaffolding methods · general mitigation techniques	`concept_edges[7]`	0.95	the tagger's words
concept_edges	prompting strategies —causes→ coherence, inference depth, and contextual relevance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 0.9 · note: Prior work is reported to show these strategies enhance all three output properties. also in: prompting strategies · coherence, inference depth, and contextual relevance	`concept_edges[8]`	0.95	the tagger's words
concept_edges	perceived social harmony —contrasted-with→ material self-interest Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 0.7 · note: The proposed implicit objective is social harmony rather than material self-interest. Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the claim is what Mei et al. (2024) 'proposed'; attributed. also in: perceived social harmony · material self-interest	`concept_edges[9]`	0.95	the tagger's words
concept_edges	treating LLMs as direct substitutes for human subjects —is-a→ flawed approach Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The paper directly classifies treating LLMs as substitutes as a flawed approach. also in: treating LLMs as direct substitutes for human subjects · flawed approach	`concept_edges[10]`	0.95	the tagger's words
concept_edges	contextual variables —causes→ human decision-making Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: Culture, age, and gender are said to significantly influence human decision-making. also in: contextual variables · human decision-making	`concept_edges[11]`	0.95	the tagger's words
concept_edges	Variability in reasoning ability and persona configurations —causes→ agent behavior Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 0.7 · note: The paper states this variability can significantly influence agent behavior. also in: Variability in reasoning ability and persona configurations · agent behavior	`concept_edges[12]`	0.95	the tagger's words
content_tags	Anderson-Darling test Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Anderson-Darling test	`content_tags.statistics[0]`		the tagger's words
content_tags	Kolmogorov-Smirnov test Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Kolmogorov-Smirnov test	`content_tags.statistics[1]`		the tagger's words
content_tags	p-value Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: p-value	`content_tags.statistics[2]`		the tagger's words
content_tags	regression Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: regression	`content_tags.statistics[3]`		the tagger's words
content_tags	confidence interval Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: confidence interval	`content_tags.statistics[4]`		the tagger's words
content_tags	Raising the reasoning ability of LLM-driven agents pushed their ultimatum-game behaviour toward the game-theoretic solution and away from the real human experimental data. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[0]`		the tagger's words
content_tags	No prompting condition produced a distribution that statistically matched either the theoretical solution or the human experimental data. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[1]`		the tagger's words
content_tags	On the proposer side the older, weaker-reasoning model with zero-shot prompting was also relatively close to human behaviour, showing that better reasoning does not straightforwardly buy better reproduction of economic experiments. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[2]`		the tagger's words
content_tags	On the responder side, chain-of-thought prompting produced the closest match to the theoretical (rational) distribution of any condition. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[3]`		the tagger's words
content_tags	Against human responder data the ranking inverted: the weakest-reasoning condition, zero-shot gpt-3.5, matched human acceptance behaviour most closely. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[4]`		the tagger's words
content_tags	The authors conclude that LLM agents do not spontaneously behave like humans in economic games without prompts carrying social context, so using LLM-driven multi-agent simulations as substitutes for real human groups is currently unwarranted. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[5]`		the tagger's words
content_tags	At every temperature setting almost all agents offered a 50-50 split of coins. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[6]`		the tagger's words
content_tags	Because every other setting was identical to the earlier study, the authors attribute the difference in results to the presence or absence of persona settings, and conclude that personas are essential for applying LLM-driven simulation to economic experiments. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[7]`		the tagger's words
content_tags	Robustness checks with 15 and 20 in-prompt examples changed the synthesised distributions only slightly and left the comparative pattern across conditions unchanged. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[8]`		the tagger's words
content_tags	reasoning ability Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: reasoning ability	`content_tags.definitions[0]`		the tagger's words
content_tags	generative agent Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: generative agent	`content_tags.definitions[1]`		the tagger's words
content_tags	Platonic Representation Hypothesis Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Platonic Representation Hypothesis	`content_tags.definitions[2]`		the tagger's words
content_tags	reasoning-related prompting strategy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: reasoning-related prompting strategy	`content_tags.variables[0]`		the tagger's words
content_tags	temperature parameter Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: temperature parameter	`content_tags.variables[1]`		the tagger's words
content_tags	GPT model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: GPT model	`content_tags.variables[2]`		the tagger's words
content_tags	acceptance rate Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: acceptance rate	`content_tags.variables[3]`		the tagger's words
content_tags	persona settings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: persona settings	`content_tags.variables[4]`		the tagger's words
content_tags	1000 — independent agent decisions generated for every combination of role, prompt type and temperature Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[0]`		the tagger's words
content_tags	10 — real experimental data points used as in-prompt examples for few-shot and chain-of-thought prompting Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[1]`		the tagger's words
content_tags	KS = 0.479 and AD = 128 — smallest divergence from the human proposer distribution, obtained by the chain-of-thought condition Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[2]`		the tagger's words
content_tags	AD = 15.5 — chain-of-thought responder distribution's divergence from the theoretical distribution, the smallest of any condition Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[3]`		the tagger's words
content_tags	AD = 20.8 ... AD = 43.7 — divergence from human responder data for few-shot (third best) and for chain-of-thought (worst of the four conditions) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[4]`		the tagger's words
content_tags	approximately 0.7 / approximately 0.4 or less — human acceptance rate at an offer of 50 versus the simulated agents' acceptance rate at the same offer Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[5]`		the tagger's words

Interpretive choices

Tags that could not be placed in the text:

none — every tag was located in the text

What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.