TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingSimilar Papers 제목 키워드 기반
A Measure of Explanatory Effectiveness
In most conversations about explanation and AI, the recipient of the explanation (the explainee) is suspiciously absent, despite the problem being ultimately communicative in nature. We pose the problem `explaining AI sy…
Learning by Self-Explaining
Much of explainable AI research treats explanations as a means for model inspection. Yet, this neglects findings from human psychology that describe the benefit of self-explanations in an agent's learning process. Motiva…
image-classificationImage ClassificationExplaining Reinforcement Learning with Shapley Values
For reinforcement learning systems to be widely adopted, their users must understand and trust them. We present a theoretical analysis of explaining reinforcement learning using Shapley values, following a principled app…
reinforcement-learningReinforcement LearningExplaining Image Classification with Visual Debates
An effective way to obtain different perspectives on any given topic is by conducting a debate, where participants argue for and against the topic. Here, we propose a novel debate framework for understanding and explaini…
Classificationimage-classificationImage ClassificationAttributions All the Way Down? The Metagame of Interpretability
We introduce the metagame, a conceptual framework for quantifying second-order interaction effects of model explanations. For any first-order attribution $φ(f)$ explaining a model $f$, we measure the directional influenc…