减少对话提升多智能体大模型准确率，避免错误传播。
DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs
- 先让智能体独立推理，再结构化整合结果
- 比最强基线准确率提升30.7%，耗能降6.5倍
- 适合需要高效低错推理的系统设计
多智能体大模型通过整合多个智能体输出来提升推理能力，但交互密集的方法易导致错误传播和高通信开销。当智能体交换原始响应或推理过程时，错误中间结果可能被采纳并放大，形成看似可信却错误的共识；多轮通信也增加了令牌消耗、延迟和推理成本。本文提出一种受控通信的协调框架DarkForest：首先保持智能体独立，各自生成答案而不查看其他输出；随后将原始响应解析为结构化候选记录，将语义相似的候选聚类，并基于智能体可靠性、置信度、解析质量、支持模式可靠性和独立性修正，估计校准后的信念分布；协调器仅接收策略允许的证据，实现受控通信。在六个推理基准上的实验表明，DarkForest达到领先的整体质量，相比最强基线提升最多30.7%的基准指标，并将令牌消耗降低最多6.5倍。
原文摘要 · Abstract (English)
Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead. When agents exchange raw responses or reasoning traces, incorrect intermediate reasoning may be adopted and amplified, leading to confident but wrong consensus; multi-round communication also increases token consumption, latency, and inference cost. In this paper, we propose a controlled-communication coordination framework named DarkForest. DarkForest first keeps agents independent, so each agent produces an answer without seeing the others' outputs. It then parses the raw responses into structured candidate records, groups semantically equivalent candidates into clusters, and estimates a calibrated belief distribution over these clusters using agent reliability, confidence, parse quality, support-pattern reliability, and independence corrections. A coordinator receives only policy-permitted evidence from this belief state with controlled communication. Experiments on six reasoning benchmarks show that DarkForest achieves leading overall quality, improves the strongest baseline by up to 30.7\% on benchmark metrics, and reduces token consumption by up to $6.5\times$ compared with communication-heavy baselines.
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。