只在必要时才辩论，让大模型推理更高效
Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
- 根据初始回答置信度决定是否启动辩论，避免无效交互
- 推理效率最高提升6倍，性能不降反升
- 适合需要低成本高可靠推理的场景
多智能体协作已成为提升大语言模型（LLM）推理能力的有前景框架。尽管推理性能有所提升，但迭代式智能体交互带来了显著计算开销。此外，不必要的辩论会增加错误响应的风险。为此，我们提出‘仅在必要时辩论’（DOWN）——一种自适应多智能体辩论框架，基于智能体初始回答的置信度分数选择性激活辩论。仅对需要进一步讨论的查询启动辩论，在此过程中，智能体通过参考同伴响应及其置信度分数来优化输出。在多个基准上的评估表明，DOWN可将效率提升高达六倍，同时保持或超越现有方法的性能。进一步分析显示，DOWN有效缓解了因非必要辩论导致的错误传播风险。这些结果证明，该方法可在更低计算成本下实现高性能的LLM解决方案。
原文摘要 · Abstract (English)
Multiagent collaboration has emerged as a promising framework for enhancing the reasoning capabilities of large language models (LLMs). Despite improvements in reasoning, the approach introduces substantial computational overhead resulting from iterative agent interactions. Furthermore, engaging in unnecessary debates increases the risk of generating erroneous responses. To address these challenges, we propose Debate Only When Necessary (DOWN), an adaptive multiagent debate framework that selectively activates debate based on the confidence score of the agent's initial response. Debate is activated only for queries requiring further deliberation, during which agents refine their outputs by referencing peer responses and associated confidence scores. Evaluations on benchmarks show that DOWN improves efficiency by up to six times while preserving or even outperforming the performance of existing methods. Further analysis indicates that DOWN effectively mitigates the risk of error propagation stemming from the unnecessary debate process. These findings demonstrate the effectiveness of our approach in delivering high-performance LLM solutions at a lower computational cost.
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。