CoCoA：用于参数化检索知识协同的协作式智能体链
CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy
AI总结：
本文提出CoCoA框架，通过多智能体协作与长链训练策略，增强大模型在RAG中参数化知识与检索知识的显式协同，提升开放域和多跳问答性能。
摘要：
检索增强生成（RAG）增强了大型语言模型（LLM），特别是在知识密集型任务中。尽管有其优势，当前的RAG方法在生成过程中往往难以充分利用知识。特别是，模型内部的参数化知识与外部检索知识之间的协同作用仍然有限。检索到的内容有时可能会误导生成，而某些生成的内容可以引导模型产生更准确的输出。在这项工作中，我们提出了协作式智能体链（Collaborative Chain-of-Agents），这是一个旨在增强参数化知识和检索知识显式协同的框架。具体来说，我们首先引入了CoCoA-zero，一个多智能体RAG框架，它首先执行条件知识归纳，然后推理答案。在此基础上，我们开发了CoCoA，一种长链训练策略，该策略从CoCoA-zero合成扩展的多智能体推理轨迹，以对LLM进行微调。该策略增强了模型显式整合和联合利用参数化知识与检索知识的能力。实验结果表明，CoCoA在开放域问答和多跳问答中具有优越性。
英文摘要：
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs), especially for knowledge-intensive tasks. Despite its advantages, current RAG methods often struggle to fully exploit knowledge during generation. In particular, the synergy between the model's internal parametric knowledge and external retrieved knowledge remains limited. Retrieved contents may sometimes mislead generation, while certain generated content can guide the model toward more accurate outputs. In this work, we propose Collaborative Chain-of-Agents, a framework designed to enhance explicitly synergy over both parametric and retrieved knowledge. Specifically, we first introduce CoCoA-zero, a multi-agent RAG framework that first performs conditional knowledge induction and then reasons answers. Building on this, we develop CoCoA, a long-chain training strategy that synthesizes extended multi-agent reasoning trajectories from CoCoA-zero to fine-tune the LLM. This strategy enhances the model's capability to explicitly integrate and jointly leverage parametric and retrieved knowledge. Experimental results demonstrate the superiority of CoCoA in open-domain QA and multi-hop QA.
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。
