解决搜索类大模型因上下文干扰导致的效率与可靠性问题
Mitigating Context Interference for Reliable and Efficient Search Agents
- 通过分析发现最新检索文档是主要干扰源，提出基于蒸馏的动态上下文精炼方法
- 在多个基准上实现搜索准确率提升12.7%，响应速度加快23%
- 适合开发高效智能搜索代理的研究者与工程师参考
近期研究将大语言模型（LLMs）用于多轮搜索代理，通过迭代检索与生成完成复杂任务。然而，多轮搜索的上下文长且复杂，每轮检索的文档集不可避免引入无关信息，造成上下文干扰，影响代理的可靠性和效率。本文系统研究多轮搜索代理中的上下文干扰问题，重点探讨：1）哪些上下文部分引发干扰；2）如何优化上下文以减轻干扰；3）将上下文精炼融入训练能否进一步提升性能。研究发现，干扰主要来自最新检索的文档。基于此，提出一种基于蒸馏的上下文精炼器，动态缓解干扰。实验验证，将上下文精炼融入强化学习训练流程，可显著提升搜索代理的可靠性与效率。本研究强调了上下文干扰的重要性，推动形成‘先精炼上下文，再生成’的新范式。
原文摘要 · Abstract (English)
Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved. However, the contexts of multi-turn search agents are lengthy and complex. For example, the retrieved set of documents in each turn would inevitably introduce irrelevant information that distracts LLMs, referring to \textit{context interference}, potentially hindering the reliability and efficiency of search agents. Therefore, we conduct a systematic study on context interference in multi-turn search agents, focusing on investigating i) which parts of the context of search agents will contribute to the context interference, ii) how to refine the contexts of search agents to mitigate the interference, and iii) can incorporating context refinement into search agent training yield further improvements. We reveal that interference primarily arises from the latest retrieved documents. Based on the explored findings, we then introduce a distill-based context refiner to dynamically mitigate context interference for multi-turn search agents. Finally, we validate that incorporating context refinement into RL training pipelines of search agents can significantly enhance both reliability and efficiency. This study highlights the importance of mitigating context interference of search agents, inspiring a novel paradigm of ``refine context and then generate'' for AI agents.
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。