用三视角框架让多智能体大模型的推理过程可解释、可验证。
TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs
- 构建第一人称自述、第二人称对手信念、第三人称审计三视图
- 发现智能体言行与信念存在系统性不一致
- 适合研究大模型决策透明性的研究人员
大语言模型智能体在交互式、部分可观测环境中的可解释性尤为困难，因决策依赖动态信念与其他智能体。本文提出 extbf{TriEx}，一种三视图可解释性框架，通过对齐的结构化产物实现序列决策解释：(i) 与动作绑定的第一人称自我推理，(ii) 随时间更新的第二人称对手信念状态，(iii) 基于环境参考信号的第三人称审计。该设计将解释转化为可跨时间、跨视角比较和验证的证据锚定对象。以不完全信息策略博弈为受控测试平台，我们证明了TriEx能实现解释可信度、信念动态和评估者可靠性的大规模分析，揭示了智能体所言、所信与所行之间的系统性差异。结果表明可解释性是依赖交互的属性，需采用多视图、证据驱动的评估方式。代码已开源。
原文摘要 · Abstract (English)
Explainability for Large Language Model (LLM) agents is especially challenging in interactive, partially observable settings, where decisions depend on evolving beliefs and other agents. We present \textbf{TriEx}, a tri-view explainability framework that instruments sequential decision making with aligned artifacts: (i) structured first-person self-reasoning bound to an action, (ii) explicit second-person belief states about opponents updated over time, and (iii) third-person oracle audits grounded in environment-derived reference signals. This design turns explanations from free-form narratives into evidence-anchored objects that can be compared and checked across time and perspectives. Using imperfect-information strategic games as a controlled testbed, we show that TriEx enables scalable analysis of explanation faithfulness, belief dynamics, and evaluator reliability, revealing systematic mismatches between what agents say, what they believe, and what they do. Our results highlight explainability as an interaction-dependent property and motivate multi-view, evidence-grounded evaluation for LLM agents. Code is available at https://github.com/Einsam1819/TriEx.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。