Group Deliberation Oriented Multi-Agent Conversational Model for Complex Reasoning
This provides an effective solution for AI systems handling complex reasoning tasks, though it is incremental over existing multi-agent approaches.
The paper tackled the limitations of single large language models in complex reasoning by proposing a multi-agent conversational model with role division and self-game mechanisms, resulting in accuracy improvements of 16.8% on HotpotQA, 14.3% on 2WikiMultihopQA, and 19.2% on MeetingBank, along with a 21.5% consistency gain.
This paper proposes a group deliberation oriented multi-agent conversational model to address the limitations of single large language models in complex reasoning tasks. The model adopts a three-level role division architecture consisting of generation, verification, and integration. An opinion generation agent produces diverse reasoning perspectives, an evidence verification agent retrieves external knowledge and quantifies factual support, and a consistency arbitration agent integrates logically coherent conclusions. A self-game mechanism is introduced to expand multi-path reasoning trajectories, while a retrieval enhancement module dynamically supplements external knowledge. A composite reward function combining factual consistency and logical coherence is designed, and an improved proximal policy optimization strategy is applied for collaborative training. Experimental results show that the proposed model improves multi-hop reasoning accuracy by 16.8 percent on HotpotQA, 14.3 percent on 2WikiMultihopQA, and 19.2 percent on MeetingBank, while improving consistency by 21.5 percent. The model achieves higher reasoning efficiency than mainstream multi-agent approaches, providing an effective and stable solution for complex reasoning tasks.