@inproceedings{jiang-etal-2026-collaborative,
    title = "Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy",
    author = "Jiang, Yi  and
      Zhao, Sendong  and
      Li, Jianbo  and
      Wang, Haochun  and
      Zhang, Lizhe  and
      Liu, Yan  and
      Qin, Bing",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.167/",
    pages = "3663--3680",
    ISBN = "979-8-89176-390-6",
    abstract = "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."
}