DarkForest:智能体少交流,准确率更高
阅读原文· arxiv.org多智能体大语言模型系统通过组合多个智能体的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。本文提出一个名为DarkForest的可控通信协调框架。该框架首先让每个智能体独立生成答案,随后将原始响应解析为结构化候选记录,并依据代理可靠性等因素对语义等价的候选进行分组与校准,协调器仅从该信念分布中接收策略允许的证据。在六个推理基准测试上,DarkForest取得了领先的综合质量,其基准指标比最强基线提升高达30.7%,同时将token消耗降低至通信密集型基线的1/6.5。
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 6.5times compared with communication-heavy baselines.