從序列到結構：LLM代理的關係不確定性傳播

摘要

可靠的不確定性量化（UQ）對於在複雜互動環境中部署大型語言模型（LLM）代理至關重要。現有的不確定性量化方法主要依賴局部信號，例如詞元機率、預測熵或逐步置信度，因而忽略了錯誤在執行軌跡中累積所需的長程依賴關係。因此，這些方法可能無法識別那些成因發生於最終答案之前數個推理或互動步驟的代理失敗。我們提出RUPA（Relational Uncertainty Propagation for Agents），一個針對LLM代理的軌跡層級不確定性量化框架。RUPA將執行歷史表示為一個有向軌跡圖，其中推理狀態、工具互動與環境回饋作為節點，並透過時間與語義依賴邊相互連接。隨後，它在此圖上傳播不確定性，以捕捉執行風險如何在互動步驟間累積與轉移。傳播後的信號與軌跡層級的行為特徵及目標對齊資訊相結合，以產生對完整代理軌跡的置信度估計。我們在具代表性的代理基準測試上評估RUPA，包括τ-2、Terminal-Bench-2與GAIA，並使用橫跨多個模型家族的6個開源LLM。實驗結果顯示，RUPA透過提供更準確的不確定性估計、實現更早的失敗偵測，以及在多樣化代理任務中改善不確定性引導的代理執行，持續優於現有的不確定性量化方法。這些結果表明，明確建模關係依賴對於長時程LLM代理的可靠不確定性量化至關重要，為可信賴的代理執行提供了實用的基礎。

English

Reliable uncertainty quantification (UQ) is essential for deploying large language model (LLM) agents in complex interactive environments. Existing UQ methods largely rely on local signals, such as token probabilities, predictive entropy, or per-step confidence, and therefore overlook the long-range dependencies through which errors accumulate across an execution trajectory. As a result, they may fail to identify agent failures whose causes originate several reasoning or interaction steps before the final answer. We propose RUPA (Relational Uncertainty Propagation for Agents), a trajectory-level UQ framework for LLM agents. RUPA represents an execution history as a directed trajectory graph in which reasoning states, tool interactions, and environment feedback are nodes connected by temporal and semantic dependency edges. It then propagates uncertainty over this graph to capture how execution risk accumulates and transfers across interaction steps. The propagated signal is combined with trajectory-level behavioral features and goal-alignment information to produce a confidence estimate for the full agent trajectory. We evaluate RUPA on representative agent benchmarks, including τ-2, Terminal-Bench-2, and GAIA, using 6 open-source LLMs spanning multiple model families. Experimental results show that RUPA consistently outperforms existing UQ methods by providing more accurate uncertainty estimates, enabling earlier failure detection, and improving uncertainty-guided agent execution across diverse agent tasks. These results demonstrate that explicitly modeling relational dependency is crucial to reliable UQ for long-horizon LLM agents, providing a practical foundation for trustworthy agent execution.