让智能体在探索中自我修正信念，提升对环境的准确理解。
Align While Search: Belief-Guided Exploratory Inference for World-Grounded Embodied Agents
- 用信念迭代更新机制替代梯度优化，实现无训练自适应推理。
- 信息增益最大化策略使智能体在部分观测下更接近真实世界状态。
- 适合需要低开销、高对齐的现实场景智能体部署。
本文提出一种测试时自适应智能体，在部分可观测环境下通过后验引导的信念精炼进行探索性推理，无需基于梯度的更新或额外训练。该智能体维护外部结构化信念，通过动作条件观测逐步更新，并以最大化预测信息增益为目标选择行动。信息增益由轻量级LLM代理模型估计，世界对齐性则通过新设计的奖励函数评估，该函数量化后验信念与真实环境配置的一致性。实验表明，该方法在对齐潜在世界状态方面优于提示增强或检索增强的LLM基线，且集成开销显著更低。
原文摘要 · Abstract (English)
In this paper, we propose a test-time adaptive agent that performs exploratory inference through posterior-guided belief refinement without relying on gradient-based updates or additional training for LLM agent operating under partial observability. Our agent maintains an external structured belief over the environment state, iteratively updates it via action-conditioned observations, and selects actions by maximizing predicted information gain over the belief space. We estimate information gain using a lightweight LLM-based surrogate and assess world alignment through a novel reward that quantifies the consistency between posterior belief and ground-truth environment configuration. Experiments show that our method outperforms inference-time scaling baselines such as prompt-augmented or retrieval-enhanced LLMs, in aligning with latent world states with significantly lower integration overhead.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。