Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913175032561664 |
|---|---|
| author | Wang, Yufeng |
| author_facet | Wang, Yufeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00476 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents Wang, Yufeng Artificial Intelligence 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. |
| title | Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2606.00476 |