cs.AINov 13, 2026

Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination

Authors: Mohamed Aghzal, Mor Geva, Gregory J. Stein, Ziyu Yao

Organizations: George Mason University · Tel Aviv University

Abstract

Mechanistic Interpretability (MI) has made significant progress in explaining the internal computations of Large Language Models (LLMs); however, these advances have yet to demonstrate comparable success in explaining the decision-making processes of LLM-based agents. This paper examines the challenges MI tools face when applied to realistic agentic failures. We focus on one such failure: web agents hallucinating actions that are not available on a website. We apply a series of mechanistic analyzes to Qwen2.5-7B-Instruct as it interacts with live websites. We find that a linear probe trained on the last prompt token can predict hallucinations before generation begins (0.80 AUC) and steering along a probe direction corrects 85% of hallucinations, but disrupts 7% of valid actions. However, these results only provide a partial explanation of why the agent hallucinates. The probe direction is sensitive to prompt formatting, losing much of its steering effect after a minor change to how actions are represented. Additionally, circuit identification can be difficult as the computation is distributed across multiple components and positions, and the information the agent relies on varies across examples. We discuss how these observations challenge the assumptions underlying standard MI methods for circuit discovery and feature identification, and outline future directions for making these methods better suited to explain failures in LLM-based agents.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?

    Jun 23, 2026Ayan Antik Khan, Harsh Kohli, Yuekun Yao +2LLM Agent EvaluationMechanistic Interpretability

  2. Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective

    Mar 15, 2026Mohamed Aghzal, Gregory J. Stein, Ziyu YaoWeb AgentsLLM Agent Reliability

  3. Can Agents Infer Environment from Interaction? Evidence from Agentic Automata Learning

    Jun 15, 2026Reef Menaged, Gili Lior, Shauli Ravfogel +2LLM Agent EvaluationActive Learning