动态修正或剔除错误信息，提升多智能体系统推理准确性。
AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning
- 测试时通过检索增强修正错误输出，避免错误传播。
- 数学与代码任务上平均准确率分别提升6.39%和2.28%。
- 自动适应任务难度，适合复杂推理场景使用。
多智能体系统（MAS）在复杂推理中表现优异，但单个智能体的错误信息会引发连锁反应。现有方法多依赖固定结构设计或昂贵微调，适应性差。本文提出AgentDropoutV2（ADv2），一种测试时的修正或剔除剪枝框架，动态优化信息流。其作为主动防火墙，拦截智能体输出，利用检索增强的修正器迭代纠错，并基于离线构建的错误模式指示池进行引导。无法修复的输出将被剔除，防止错误扩散。实验表明，ADv2在固定与动态MAS框架下均显著提升性能，在数学与代码基准上平均准确率分别提高6.39%和2.28%。此外，其具备良好自适应性，可按任务难度动态调节修正强度，有效应对多种错误模式。代码已开源：https://github.com/TonySY2/AgentDropoutV2。
原文摘要 · Abstract (English)
While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information from individual agents. Current solutions often resort to rigid structural engineering or expensive fine-tuning, limiting their adaptability. We propose AgentDropoutV2 (ADv2), a test-time rectify-or-reject pruning framework that dynamically optimizes MAS information flow. Acting as an active firewall, ADv2 intercepts agent outputs and employs a retrieval-augmented rectifier to iteratively correct errors. This rectification is guided by an indicator pool, which is constructed offline by distilling error patterns from historical MAS failure trajectories. Irreparable outputs are subsequently pruned to prevent error propagation. Empirical results demonstrate that ADv2 significantly boosts performance on both fixed and dynamic MAS frameworks, achieving average accuracy gains of 6.39 and 2.28 percentage points on extensive math and code benchmarks, respectively. Furthermore, ADv2 exhibits remarkable adaptivity, dynamically modulating rectification efforts based on task difficulty to resolve a wide spectrum of error patterns. Our code is released at https://github.com/TonySY2/AgentDropoutV2.
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。