When Reasoning Models Hurt Behavioral Simulation: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation

Computer Science > Machine Learning [Submitted on 12 Apr 2026] When Reasoning Models Hurt Behavioral Simulation: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Sandro Andric Large language models are increasingly used as agents in social, economic, and policy simulations. A common assumption is that stronger reasoning should improve simulation fidelity. We argue that this assumption can fail when the objective is not to solve a strategic problem, but to sample plausible boundedly rational behavior. In such settings, reasoning-enhanced models can become better solvers and worse simulators: they can over-optimize for strategically dominant actions, collapse compromise-oriented terminal behavior, and sometimes exhibit a diversity-without-fidelity pattern in which local variation survives without outcome-level fidelity. We study this solver-sampler mismatch in three multi-agent negotiation environments adapted from earlier simulation work: an ambiguous fragmented-authority trading-limits scenario, an ambiguous unified-opposition trading-limits scenario, and a new-domain grid-curtailment case in emergency electricity management. We compare three reflection conditions, no reflection, bounded reflection, and native reasoning, across two primary model families and then extend the same protocol to direct OpenAI runs with GPT-4.1 and GPT-5.2. Across all three experiments, bounded reflection produces substantially more diverse and compromise-oriented trajectories than either no reflection or native reasoning. In the direct OpenAI extension, GPT-5.2 native ends in authority decisions in 45 of 45 runs across the three experiments, while GPT-5.2 bounded recovers compromise outcomes in every environment. The contribution is not a claim that reasoning is generally harmful. It is a methodological warning: model capability and simulation fidelity are different objectives, and behavioral simulation should qualify models as samplers, not only as solvers. Comments: 12 pages, 5 figures, supplementary material included as ancillary file Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Multiagent Systems (cs.MA) Cite as: arXiv:2604.11840 [cs.LG]   (or arXiv:2604.11840v1 [cs.LG] for this version)   https://doi.org/10.48550/arXiv.2604.11840 Focus to learn more Submission history From: Sandro Andric [view email] [v1] Sun, 12 Apr 2026 13:36:10 UTC (437 KB) Access Paper: HTML (experimental) view license Current browse context: cs.LG < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.AI cs.CY cs.MA References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)