MARS通过角色分工提升大模型协作推理效率，节省一半计算开销。
MARS: toward more efficient multi-agent collaboration for LLM reasoning
- 作者-评审-元评审三角色分工，避免冗余沟通
- 在多基准测试中准确率媲美MAD，但耗时和令牌减半
- 适合追求高效推理的部署场景，尤其资源受限时
大语言模型在自然语言理解上表现优异，但在单智能体模式下推理能力有限。多智能体辩论（MAD）通过轮桌式协作提升推理质量，但带来高昂的计算开销。本文提出基于评审流程的MARS框架：作者生成初始解，评审者独立给出判断与意见，元评审整合反馈并决定最终结果与修改方向。该设计避免了评审者间的频繁交互，显著降低令牌消耗与推理时间。在多个基准测试中，使用不同LLM进行的实验表明，MARS在保持与MAD相当准确率的同时，将令牌使用量和推理时间均减少约50%。代码已开源于https://github.com/xwang97/MARS。
原文摘要 · Abstract (English)
Large language models (LLMs) have achieved impressive results in natural language understanding, yet their reasoning capabilities remain limited when operating as single agents. Multi-Agent Debate (MAD) has been proposed to address this limitation by enabling collaborative reasoning among multiple models in a round-table debate manner. While effective, MAD introduces substantial computational overhead due to the number of agents involved and the frequent communication required. In this paper, we propose MARS (Multi-Agent Review System), a role-based collaboration framework inspired by the review process. In MARS, an author agent generates an initial solution, reviewer agents provide decisions and comments independently, and a meta-reviewer integrates the feedback to make the final decision and guide further revision. This design enhances reasoning quality while avoiding costly reviewer-to-reviewer interactions, thereby controlling token consumption and inference time. We compared MARS with both MAD and other state-of-the-art reasoning strategies across multiple benchmarks. Extensive experiments with different LLMs show that MARS matches the accuracy of MAD while reducing both token usage and inference time by approximately 50\%. Code is available at https://github.com/xwang97/MARS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。