[论文解读] Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagation

Saurabh Jha, Rohan Arora+8 more|arXiv (Cornell University)|Jan 25, 2026

Semantic Web and Ontologies被引用 0

一句话总结

论文提出 EoG，一种分解架构，使用本地演绎推理结合大语言模型与确定性图遍历与信念传播来实现图引导的调查，在 ITBench 场景中取得显著提升。

ABSTRACT

LLM agents excel when environments are mostly static and the needed information fits in a model's context window, but they often fail in open-ended investigations where explanations must be constructed by iteratively mining evidence from massive, heterogeneous operational data. These investigations exhibit hidden dependency structure: entities interact, signals co-vary, and the importance of a fact may only become clear after other evidence is discovered. Because the context window is bounded, agents must summarize intermediate findings before their significance is known, increasing the risk of discarding key evidence. ReAct-style agents are especially brittle in this regime. Their retrieve-summarize-reason loop makes conclusions sensitive to exploration order and introduces run-to-run non-determinism, producing a reliability gap where Pass-at-k may be high but Majority-at-k remains low. Simply sampling more rollouts or generating longer reasoning traces does not reliably stabilize results, since hypotheses cannot be autonomously checked as new evidence arrives and there is no explicit mechanism for belief bookkeeping and revision. In addition, ReAct entangles semantic reasoning with controller duties such as tool orchestration and state tracking, so execution errors and plan drift degrade reasoning while consuming scarce context. We address these issues by formulating investigation as abductive reasoning over a dependency graph and proposing EoG (Explanations over Graphs), a disaggregated framework in which an LLM performs bounded local evidence mining and labeling (cause vs symptom) while a deterministic controller manages traversal, state, and belief propagation to compute a minimal explanatory frontier. On a representative ITBench diagnostics task, EoG improves both accuracy and run-to-run consistency over ReAct baselines, including a 7x average gain in Majority-at-k entity F1.

研究动机与目标

• 在大型、异构数据且存在隐藏依赖的情况下，证明对可靠诊断调查的需求。
• 引入一个分解的架构（EoG），将本地演绎推理与确定性图遍历分离。
• 证明在具有图结构的环境中，该方法可实现更高的正确性。

提出的方法

• 提出将本地演绎推理（通过 LLM）与基于图的信念传播分离的 EoG 架构。
• 利用图遍历与信念传播实现对解释的确定性传播。
• 演示如何将局部推理结果整合到全局解释中以提高可靠性。

实验结果

研究问题

• RQ1 如何在不牺牲正确性的前提下，使用 LLM 在图结构环境中对故障进行可靠诊断？
• RQ2 将局部演绎推理与确定性图推理分离是否能提升解释质量和鲁棒性？
• RQ3 在 ITBench 类场景中，使用图引导的 LLM 调查能实现哪些性能提升？

主要发现

• EoG 在 ITBench 场景下的 Majority@k F1 比基线高出 7 倍。
• 将局部推理与图遍历分离可在具有图结构的领域提升解释准确性。
• 图引导的调查可推广至具有固有图结构的领域。