Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.01696 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909832848605184 |
|---|---|
| author | Jiang, Yi Zhao, Sendong Li, Jianbo Wang, Haochun Zhang, Lizhe Liu, Yan Qin, Bing |
| author_facet | Jiang, Yi Zhao, Sendong Li, Jianbo Wang, Haochun Zhang, Lizhe Liu, Yan Qin, Bing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01696 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy Jiang, Yi Zhao, Sendong Li, Jianbo Wang, Haochun Zhang, Lizhe Liu, Yan Qin, Bing Computation and Language Artificial Intelligence 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. |
| title | CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2508.01696 |