@inproceedings{fu-etal-2026-beyond,
    title = "Beyond Blind Following: Evaluating Robustness of {LLM} Agents under Imperfect Guidance",
    author = "Fu, Yao  and
      Qiu, Ran  and
      Wang, Xinhe  and
      Sansom, Jacob  and
      Prabhu, Sathvika Ayyappa  and
      Tang, Huijie  and
      Kim, Jaekyeom  and
      Sohn, Sungryull  and
      Lee, Honglak",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.310/",
    pages = "6591--6618",
    ISBN = "979-8-89176-380-7",
    abstract = "Large language models (LLMs) have shown strong capabilities as task-solving agents across interactive domains. However, in complex environments, these agents may need to rely on auxiliary guidance to reduce the search space or make up for limited domain-specific knowledge. Such guidance includes human-provided manuals and demonstrations, retrieved examples from memory or external tools, high-level heuristics, and agent-acquired knowledge from prior interactions. However, this guidance may be imperfect. For example, due to changes in the environment, ambiguous or simplified language, or retrieval errors from external sources, guidance can be incomplete, outdated, or contextually mismatched, potentially causing errors or failures during task execution. To address this, we introduce MIRAGE, a benchmark for MeasurIng Robustness of LLM Agents under Imperfect GuidancE. MIRAGE includes procedurally generated environments in navigation, cooking, and gaming, where both the environment and the auxiliary guidance vary in fidelity and relevance. We further extend MIRAGE to realistic web tasks via WebArena, using noisy or underspecified instructions extracted from demonstrations. Our findings reveal critical failure modes in current LLM agents and motivate future work on improving their robustness under imperfect guidance."
}