From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents
2026-08-17 • Computation and Language
Computation and LanguageArtificial Intelligence
AI summaryⓘ
The authors propose a new way called RUPA to better estimate how uncertain a language model agent is about its decisions during a long task. Unlike older methods that only look at each step separately, RUPA considers the whole process as a connected graph showing how earlier mistakes can affect later results. By spreading uncertainty through this graph and combining it with behavior and goal information, RUPA gives more accurate confidence scores. Tests on different benchmarks and models show that RUPA can detect failures earlier and help agents work better. This shows that understanding relationships between steps is important for trustworthy AI agents.
Uncertainty QuantificationLarge Language ModelsTrajectory GraphAgent ExecutionRelational DependencyConfidence EstimationError PropagationReasoning StatesInteractive EnvironmentsFailure Detection
Authors
Zhengzhao Ma. Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun
Abstract
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.