paper-with-me

홈 › Papers

TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs

2026-04-21 · Ziyi Wang, Chen Zhang, Wenjun Peng, Qi Wu, Xinyu Wang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.20043

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

A Measure of Explanatory Effectiveness

2023-05-20 · Dylan Cope, Peter McBurney

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

2023-09-15 · Wolfgang Stammer, Felix Friedrich, David Steinmann, Manuel Brack 외

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 Classification

Explaining Reinforcement Learning with Shapley Values

2023-06-09 · Daniel Beechey, Thomas M. S. Smith, Özgür Şimşek

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 Learning

Explaining Image Classification with Visual Debates

2022-10-17 · Avinash Kori, Ben Glocker, Francesca Toni

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 Classification

Attributions All the Way Down? The Metagame of Interpretability

2026-05-07 · Hubert Baniecki, Przemyslaw Biecek, Fabian Fumagalli arxiv

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…