@inproceedings{wang-etal-2026-seeing,
    title = "Seeing Isn{'}t Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents",
    author = "Wang, Hanlin  and
      Leong, Chak Tou  and
      Wang, Jian  and
      Li, Wenjie",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1884/",
    pages = "37796--37815",
    ISBN = "979-8-89176-395-1",
    abstract = "Recent advancements in large language models (LLMs) have enabled agents to tackle complex embodied tasks through environmental interaction. However, these agents still make suboptimal decisions and perform ineffective actions, as they often overlook critical environmental feedback that differs from their internal beliefs. Through a formal probing analysis, we characterize this as $\textit{belief inertia}$, a phenomenon where agents stubbornly adhere to prior beliefs despite explicit observations. To address this, we advocate active belief intervention, moving from passive understanding to active management. We introduce the Estimate-Verify-Update ($\texttt{EVU}$) mechanism, which empowers agents to predict expected outcomes, verify them against observations through explicit reasoning, and actively update prior beliefs based on the verification evidence. $\texttt{EVU}$ is designed as a unified intervention mechanism that generates textual belief states explicitly, and can be integrated into both prompting-based and training-based agent reasoning methods. Extensive experiments across three embodied benchmarks demonstrate that $\texttt{EVU}$ consistently yields substantial gains in task success rates. Further analyses validate that our approach effectively mitigates belief inertia, advancing the development of more robust embodied agents. Our code is available at https://github.com/WangHanLinHenry/EVU."
}