Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation
This addresses a critical limitation in multi-agent LLM frameworks for complex reasoning, though it is incremental as it builds on existing multi-agent paradigms.
The paper tackled the problem of lazy agent behavior in multi-agent LLM reasoning systems, where one agent dominates and undermines collaboration, and introduced a method with a verifiable reward mechanism to mitigate this, achieving improved performance on complex reasoning tasks.
Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks. Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent proposes plans and monitors progress while a reasoning agent executes subtasks through sequential conversational turns. Despite promising performance, we identify a critical limitation: lazy agent behavior, in which one agent dominates while the other contributes little, undermining collaboration and collapsing the setup to an ineffective single agent. In this paper, we first provide a theoretical analysis showing why lazy behavior naturally arises in multi-agent reasoning. We then introduce a stable and efficient method for measuring causal influence, helping mitigate this issue. Finally, as collaboration intensifies, the reasoning agent risks getting lost in multi-turn interactions and trapped by previous noisy responses. To counter this, we propose a verifiable reward mechanism that encourages deliberation by allowing the reasoning agent to discard noisy outputs, consolidate instructions, and restart its reasoning process when necessary. Extensive experiments demonstrate that our framework alleviates lazy agent behavior and unlocks the full potential of multi-agent framework for complex reasoning tasks.