Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents

Computer Science > Artificial Intelligence [Submitted on 30 May 2026] Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents Yufeng Wang Do LLM agents act on the reasoning they state? This question of process fidelity is central to using LLMs in social simulation, yet it is hard to measure where no reference for correct behavior exists. We study it in acontrolled setting, a Texas Poker simulator with a verifiable reference action for every decision by decomposing the faithfulness gap into two steps: reasoning-conclusion and conclusion-action. The two steps behave oppositely. Comments: submitted to COLM social simulation with LLM workshop Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.00476 [cs.AI]   (or arXiv:2606.00476v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.00476 Focus to learn more Submission history From: Yufeng Wang [view email] [v1] Sat, 30 May 2026 02:02:21 UTC (178 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs 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?)