AgentDropoutV2：透過測試時校正或拒絕剪枝機制優化多智能體系統中的資訊流

AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning

February 26, 2026

作者: Yutong Wang, Siyuan Xiong, Xuebo Liu, Wenkang Zhou, Liang Ding, Miao Zhang, Min Zhang

cs.AI

摘要

儘管多智能體系統在複雜推理任務中表現卓越，但個體參與者產生的錯誤信息會引發級聯負面影響。現有解決方案往往依賴僵化的結構工程或昂貴的微調過程，限制了系統的可部署性與適應能力。我們提出AgentDropoutV2——一種測試時糾錯或剔除的剪枝框架，旨在無需重新訓練即可動態優化多智能體系統的信息流。該框架如同主動防火牆，可攔截智能體輸出並採用檢索增強型校正器，基於故障驅動的指示器池進行迭代式錯誤修正。此機制通過將蒸餾後的故障模式作為先驗知識，實現對潛在錯誤的精準識別。對於無法修復的輸出則執行剪枝以阻斷錯誤傳播，同時通過後備策略保障系統完整性。在大量數學基準測試上的實證結果表明，AgentDropoutV2能顯著提升多智能體系統的任務表現，在數學基準上平均準確率提升達6.3個百分點。此外，系統展現出強大的泛化與自適應能力：根據任務難度動態調節校正強度，並利用情境感知指示器解決多類錯誤模式。我們的代碼與數據集已開源於：https://github.com/TonySY2/AgentDropoutV2。

English

While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information generated by individual participants. Current solutions often resort to rigid structural engineering or expensive fine-tuning, limiting their deployability and adaptability. We propose AgentDropoutV2, a test-time rectify-or-reject pruning framework designed to dynamically optimize MAS information flow without retraining. Our approach acts as an active firewall, intercepting agent outputs and employing a retrieval-augmented rectifier to iteratively correct errors based on a failure-driven indicator pool. This mechanism allows for the precise identification of potential errors using distilled failure patterns as prior knowledge. Irreparable outputs are subsequently pruned to prevent error propagation, while a fallback strategy preserves system integrity. Empirical results on extensive math benchmarks show that AgentDropoutV2 significantly boosts the MAS's task performance, achieving an average accuracy gain of 6.3 percentage points on math benchmarks. Furthermore, the system exhibits robust generalization and adaptivity, dynamically modulating rectification efforts based on task difficulty while leveraging context-aware indicators to resolve a wide spectrum of error patterns. Our code and dataset are released at https://github.com/TonySY2/AgentDropoutV2.