RE-Searcher：具有目标导向规划与自我反思的鲁棒智能体搜索
RE-Searcher: Robust Agentic Search with Goal-oriented Planning and Self-reflection
AI总结：
针对LLM在复杂搜索环境中因查询微小变动导致推理脆弱的问题，提出RE-Searcher，通过目标导向规划与自我反思结合，提升搜索鲁棒性并取得最先进结果。
摘要：
大型语言模型（LLM）在知识密集型问答和推理方面表现出色，但其实际部署仍受限于知识截止日期、幻觉以及有限的交互方式。通过外部搜索工具增强LLM有助于缓解这些问题，但也使智能体暴露于复杂的搜索环境中，在该环境中，查询表述的微小、看似合理的变动可能将推理引向低效的轨迹并放大错误。我们提出了一项系统性分析，量化了环境复杂性如何诱发脆弱的搜索行为，并进而降低整体性能。为应对这一挑战，我们提出了一种简单而有效的方法来实例化一个搜索智能体——RE-Searcher。在搜索过程中，RE-Searcher明确阐述一个具体的搜索目标，随后反思检索到的证据是否满足该目标。这种目标导向规划与自我反思的结合使RE-Searcher能够在复杂搜索环境中抵御虚假线索并执行鲁棒搜索。大量实验表明，我们的方法提高了搜索准确性并取得了最先进的结果。扰动研究进一步证明了其对噪声或误导性外部信号的显著鲁棒性，减轻了搜索过程的脆弱性。我们相信这些发现为将基于LLM的智能体集成到更复杂的交互环境中并实现更自主的决策提供了实用指导。
英文摘要：
Large language models (LLMs) excel at knowledge-intensive question answering and reasoning, yet their real-world deployment remains constrained by knowledge cutoff, hallucination, and limited interaction modalities. Augmenting LLMs with external search tools helps alleviate these issues, but it also exposes agents to a complex search environment in which small, plausible variations in query formulation can steer reasoning into unproductive trajectories and amplify errors. We present a systematic analysis that quantifies how environmental complexity induces fragile search behaviors and, in turn, degrades overall performance. To address this challenge, we propose a simple yet effective approach to instantiate a search agent, RE-Searcher. During search, RE-Searcher explicitly articulates a concrete search goal and subsequently reflects on whether the retrieved evidence satisfies that goal. This combination of goal-oriented planning and self-reflection enables RE-Searcher to resist spurious cues in complex search environments and perform robust search. Extensive experiments show that our method improves search accuracy and achieves state-of-the-art results. Perturbation studies further demonstrate substantial resilience to noisy or misleading external signals, mitigating the fragility of the search process. We believe these findings offer practical guidance for integrating LLM-powered agents into more complex interactive environments and enabling more autonomous decision-making.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
