GBC：基於梯度的連接以優化多智能體系統

摘要

基於大型語言模型（LLM）建構的多智能體系統（MAS）提供了一個有前景的框架，透過角色專業化與結構化互動來解決複雜任務。然而，其表現常受限於協調失靈，更根本的問題在於缺乏跨智能體的細粒度信用分配。現有方法通常依賴粗粒度的回饋，導致難以辨識錯誤源自哪些智能體或互動步驟。我們提出基於梯度的連接（Gradient-Based Connections, GBC），這是一種針對多智能體系統的細粒度歸因與優化方法。GBC將MAS建模為計算圖，並引入基於梯度的連接權重，以量化各智能體輸出對下游智能體在詞元層級的影響力。透過構建歸因圖並將任務特定損失訊號反向傳播，我們的方法能精確識別錯誤來源並進行有針對性的提示優化。我們進一步開發了AgentChord，這是一種利用前綴式梯度計算的高效實現。在MultiWOZ與τ-bench上的實驗顯示，GBC能提升多智能體表現，並優於強大的單智能體與多智能體基準；此外，更高的歸因品質與更佳的優化效果相關聯。程式碼已公開於：https://github.com/yxc-cyber/AgentChord。

English

Multi-agent systems (MAS) built on large language models (LLMs) provide a promising framework for solving complex tasks through role specialization and structured interaction. However, their performance is often limited by miscoordination and, more fundamentally, the lack of fine-grained credit assignment across agents. Existing approaches typically rely on coarse-grained feedback, making it difficult to identify which agents or interaction steps are responsible for errors. We propose Gradient-Based Connections (GBC), an approach for fine-grained attribution and optimization of multi-agent systems. GBC models a MAS as a computational graph and introduces gradient-based connection weights to quantify the influence of each agent's output on downstream agents at the token level. By constructing an attribution graph and propagating task-specific loss signals backward, our method enables precise identification of error sources and targeted prompt optimization. We further develop AgentChord, an efficient implementation that leverages prefix-based gradient computation. Experiments on MultiWOZ and τ-bench show that GBC improves multi-agent performance and outperforms strong single-agent and multi-agent baselines, and higher attribution quality is associated with greater optimization effectiveness. Code is available at: https://github.com/yxc-cyber/AgentChord.