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

• URL: http://arxiv.org/abs/2604.20043v1
• Date: Tue, 21 Apr 2026 22:55:57 GMT
• Title: TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs
• Abstract summary: TriEx is a tri-view explainability framework that instruments sequential decision making with aligned artifacts.<n>We show that TriEx enables scalable analysis of explanation faithfulness, belief dynamics, and evaluator reliability.
• Score: 16.622300148265275
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement? [66.17176838165994]
  Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience.<n>It remains unclear whether an agent can actively test its behavior, judge the resulting experience, and use that experience to improve future decisions.<n>We introduce textbfStextsuperscript3Gym, an interactive benchmark for evaluating LLM self-improvement.
  arXiv  Detail & Related papers  (2026-08-31T17:05:41Z)
• MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents [74.83535434786145]
  MNIST-PRO is a benchmark that isolates agentic perception by converting MNIST digit recognition into a sequential, glimpse-based search task with lookback constraints.<n>We evaluate ten multimodal models across four memory representations, including raw visual history, textual states, structured metric grid maps, and a consolidated visual canvas.
  arXiv  Detail & Related papers  (2026-08-31T16:05:39Z)
• QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents [38.13248430205106]
  QUACK is an evaluation framework for auditing the grounding of agent language in multimodal social reasoning.<n>It reconstructs each agent's ground-truth trajectory from engine logs and checks every discussion claim against it.<n>We find that even the strongest agent hallucinates 15.1% of its verifiable spatial claims and makes over half of its accusations without grounded evidence.
  arXiv  Detail & Related papers  (2026-05-26T14:19:08Z)
• EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs [23.973683864983272]
  EgoT-Bench is a fine-grained egocentric benchmark for grounded and verifiable operation-centric reasoning.<n>EgoT-Bench comprises 3,172 QA pairs over 351 egocentric retrospect videos.
  arXiv  Detail & Related papers  (2026-05-19T09:02:20Z)
• Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation [0.299647994399672]
  Belief Engine (BE) is an auditable belief-update layer that treats "belief" as an evidential state over a proposition.<n>BE extracts arguments into structured memory and updates stance with a log-odds rule controlled by evidence uptake u and prior anchoring a.<n>On DEBATE, a human deliberation dataset with pre/post opinions, BE best reconstructs participants whose final stance follows extracted evidence.
  arXiv  Detail & Related papers  (2026-05-14T19:13:12Z)
• Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models [154.39583176906893]
  Large language models (MLs) have advanced understanding, they remain highly prone to hallucinations in scenes.<n>We argue this stems from a failure intemporal monitoring, the ability to persistently track object dynamic identities, states, and relations over time.<n>Existing benchmarks obscure this deficit relying on single final-answer queries that can often be resolved via local visual cues or statistical priors.
  arXiv  Detail & Related papers  (2026-05-09T14:32:36Z)
• AgentV-RL: Scaling Reward Modeling with Agentic Verifier [63.55502685076245]
  Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS)<n>We propose Agentic Verifier, a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.<n>We show that Agentic Verifier yields consistent performance gains under both parallel and sequential TTS.
  arXiv  Detail & Related papers  (2026-04-17T12:27:36Z)
• Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts [58.86896791968143]
  Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks.<n>We identify a puzzling phenomenon termed Seeing but Not Thinking: models accurately perceive image content yet fail in subsequent reasoning.<n>We propose the Routing Distraction hypothesis: when processing visual inputs, the routing mechanism fails to adequately activate task-relevant reasoning experts.
  arXiv  Detail & Related papers  (2026-04-09T17:59:44Z)
• Can Unified Generation and Understanding Models Maintain Semantic Equivalence Across Different Output Modalities? [61.533560295383786]
  Unified Multimodal Large Language Models (U-MLLMs) integrate understanding and generation within a single architecture.<n>We observe that U-MLLMs fail to maintain semantic equivalence when required to render the same results in the image modality.<n>We introduce VGUBench, a framework to decouple reasoning logic from generation fidelity.
  arXiv  Detail & Related papers  (2026-02-27T06:23:56Z)
• OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows [9.617220633655716]
  We present textbfunderlineOmni-textbfunderlineModality textbfunderlineGeneration Agent (textbfOMG-Agent)
  arXiv  Detail & Related papers  (2026-02-04T02:25:40Z)
• CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs [53.199517625701475]
  CoG is a training-free framework inspired by Dual-Process Theory that mimics the interplay between intuition and deliberation.<n>CoG significantly outperforms state-of-the-art approaches in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-01-16T07:27:40Z)
• Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents [52.14392337070763]
  We introduce CFG-Bench, a new benchmark designed to systematically evaluate fine-grained action intelligence.<n>CFG-Bench consists of 1,368 curated videos paired with 19,562 three-modalities question-answer pairs targeting four cognitive abilities.<n>Our comprehensive evaluation on CFG-Bench reveals that leading MLLMs struggle to produce detailed instructions for physical interactions.
  arXiv  Detail & Related papers  (2025-11-24T02:02:29Z)
• Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval [49.85856484781787]
  We introduce Interact-RAG, a new paradigm that elevates the LLM agent into an active manipulator of the retrieval process.<n>We develop a reasoning-enhanced workflow, which enables both zero-shot execution and the synthesis of interaction trajectories.<n>Experiments across six benchmarks demonstrate that Interact-RAG significantly outperforms other advanced methods.
  arXiv  Detail & Related papers  (2025-10-31T15:48:43Z)
• COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context [17.575806280348797]
  Small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence.<n>We propose a lightweight hierarchical framework that separates tactical execution, strategic oversight, and context organization into three specialized components.
  arXiv  Detail & Related papers  (2025-10-09T20:14:26Z)
• Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection [16.154903877808795]
  Audit-LLM is a multi-agent log-based insider threat detection framework comprising three collaborative agents. We propose a pair-wise Evidence-based Multi-agent Debate (EMAD) mechanism, where two independent Executors iteratively refine their conclusions through reasoning exchange to reach a consensus.
  arXiv  Detail & Related papers  (2024-08-12T11:33:45Z)
• Evaluating the Reliability of Self-Explanations in Large Language Models [2.8894038270224867]
  We evaluate two kinds of such self-explanations - extractive and counterfactual.<n>Our findings reveal, that, while these self-explanations can correlate with human judgement, they do not fully and accurately follow the model's decision process.<n>We show that this gap can be bridged because prompting LLMs for counterfactual explanations can produce faithful, informative, and easy-to-verify results.
  arXiv  Detail & Related papers  (2024-07-19T17:41:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.