Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents

• URL: http://arxiv.org/abs/2604.17252v1
• Date: Sun, 19 Apr 2026 04:36:33 GMT
• Title: Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents
• Abstract summary: Estimate-Verify-Update (EVU) is a unified intervention mechanism that generates textual belief states explicitly.<n>EVU consistently yields substantial gains in task success rates.<n>Our approach effectively mitigates belief inertia, advancing the development of more robust embodied agents.
• Score: 20.463811944310475
• License: http://creativecommons.org/licenses/by/4.0/
• 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 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 (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. 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 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.

Related papers

• Operational Hallucination and Safety Drift in AI Agents [0.3823356975862005]
  Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.<n>This paper empirically characterizes two observed failure modes across multiple state-of-the-art LLMs: Safety Drift and Operational Hallucination.<n>We propose an Action-Aware Supervision Layer - a lightweight, plug-and-play architectural blueprint incorporating intent-action consistency checks, state tracking, and forced termination primitives.
  arXiv  Detail & Related papers  (2026-07-20T17:01:50Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• 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)
• ActFER: Agentic Facial Expression Recognition via Active Tool-Augmented Visual Reasoning [55.562958315741646]
  We propose ActFER, an agentic framework that reformulates FER as active visual evidence acquisition followed by multimodal reasoning.<n>We further develop Utility-Calibrated GRPO, a reinforcement learning algorithm tailored to agentic FER.
  arXiv  Detail & Related papers  (2026-04-10T05:53:19Z)
• Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing [5.497064111008921]
  We propose textbfSelf-textbfAudited textbfVerified textbfReasoning (textscSAVeR), a novel framework that enforces verification over internal belief states within the agent before action commitment.<n>Our approach consistently improves reasoning faithfulness while preserving competitive end-task performance.
  arXiv  Detail & Related papers  (2026-04-09T16:01:03Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• Learning to Seek Evidence: A Verifiable Reasoning Agent with Causal Faithfulness Analysis [10.749786847079163]
  Explanations for AI models in high-stakes domains like medicine often lack verifiability, which can hinder trust.<n>We propose an interactive agent that produces explanations through an auditable sequence of actions.<n>This policy is optimized using reinforcement learning, resulting in a model that is both efficient and generalizable.
  arXiv  Detail & Related papers  (2025-11-03T10:21:35Z)
• Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems [49.69773210844221]
  This paper challenges the prevailing hypothesis that persuasive efficacy is primarily a function of model scale.<n>Through a series of multi-agent persuasion experiments, we uncover a fundamental trade-off we term the Persuasion Duality.<n>Our findings reveal that the reasoning process in LRMs exhibits significantly greater resistance to persuasion, maintaining their initial beliefs more robustly.
  arXiv  Detail & Related papers  (2025-09-25T12:03:10Z)
• LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation [4.29885665563186]
  LATENTGUARD is a framework that combines behavioral alignment with supervised latent space control for interpretable and precise safety steering.<n>Our results show significant improvements in both safety controllability and response interpretability without compromising utility.
  arXiv  Detail & Related papers  (2025-09-24T07:31:54Z)
• Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows [41.97051158610974]
  We present a systematic analysis of agentic robustness under deceptive or misleading feedback.<n>We reveal that even strongest agents are vulnerable to persuasive yet flawed critiques.<n>Our findings highlight fundamental vulnerabilities in feedback-based robustness and offer guidance for building more robust agentic systems.
  arXiv  Detail & Related papers  (2025-06-03T19:26:23Z)
• Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations [58.96953392466609]
  We take an in-depth look at the causal awareness of modern representations of agent interactions.<n>We show that recent representations are already partially resilient to perturbations of non-causal agents.<n>We introduce a metric learning approach that regularizes latent representations with causal annotations.
  arXiv  Detail & Related papers  (2023-12-07T18:57:03Z)

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.