← 研踪 PaperTrailarXiv:2611.14889 · v1
Can an AI Agent Be Epistemically Akratic? Higher-Order Evidence & the Limits of Self-Correction
首次提交 2026-11-11 09:27
版本更新 2026-11-11 09:27
雷达观测 2026-11-13 10:09
摘要
When we judge that our reasoning was defective, it seems plausible that we should abandon the conclusion it produced. This thought has special force for AI agents built to assess and correct their own work. Yet obeying such judgments can make an agent worse at distinguishing sound reasoning from defective reasoning. An AI agent may rely on information about its reasoning when deciding which conclusions to keep, while the part that judges whether those conclusions are justified cannot use that information. The agent can then exercise an epistemic competence by retaining conclusions it judges unjustified, even when its self-assessments are generally reliable. Nor is the difficulty resolved by training the agent to make its conclusions and assessments agree: agreement can be achieved by degrading either one. Crucially, I argue that a negative assessment can remain valuable by identifying conclusions requiring further scrutiny, without having authority to eliminate them. The result challenges a central assumption about AI self-correction: that bringing an agent's beliefs into agreement with its own self-assessment about their justification makes it better at correcting its mistakes.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-11 09:27 · 最新观测版本
Can an AI Agent Be Epistemically Akratic? Higher-Order Evidence & the Limits of Self-Correction
When we judge that our reasoning was defective, it seems plausible that we should abandon the conclusion it produced. This thought has special force for AI agents built to assess and correct their own work. Yet obeying such judgments can make an agent worse at distinguishing sound reasoning from defective reasoning. An AI agent may rely on information about its reasoning when deciding which conclusions to keep, while the part that judges whether those conclusions are justified cannot use that information. The agent can then exercise an epistemic competence by retaining conclusions it judges unjustified, even when its self-assessments are generally reliable. Nor is the difficulty resolved by training the agent to make its conclusions and assessments agree: agreement can be achieved by degrading either one. Crucially, I argue that a negative assessment can remain valuable by identifying conclusions requiring further scrutiny, without having authority to eliminate them. The result challenges a central assumption about AI self-correction: that bringing an agent's beliefs into agreement with its own self-assessment about their justification makes it better at correcting its mistakes.
查看此版本解读 →查看此版本原文 ↗