GraphEcho：LLM图智能体中的结构冗余与证据溯源
GraphEcho: Structural Redundancy and Evidence Provenance in LLM Graph Agents
浏览论文内容
中文总结 AI 辅助
GraphEcho基准通过控制路径与证据来源，揭示LLM图智能体易将重复路径误判为佐证，并提出溯源感知后训练以减少重复，但可能牺牲证据覆盖与准确性。
中文摘要 AI 辅助
大型语言模型（LLM）智能体可以在不获取更多独立证据的情况下遵循更多图路径。GraphEcho测试智能体是否将这些重复遭遇误认为是额外的佐证。该基准在保持证据内容固定的同时，改变路径数量和证据来源，并评估判断和主动探索。受控的合成实验揭示了依赖于模型的判断偏移，但在所有评估的冻结智能体中，冗余的支持路径增加了重复行走的比例。溯源感知的后训练（PAPT）减少了重复访问并提高了合成准确性，但覆盖的不同来源更少。在科学主张上，它继续减少重复，而准确性下降。这些发现暴露了高效探索与有效证据使用之间的差距：智能体可以学会停止重复自身，同时忽略所需的信息。GraphEcho提供了一种受控方式来评估图智能体得出结论的内容及其探索是否达到不同的证据来源。
英文摘要
A large language model (LLM) agent can follow more graph paths without acquiring more independent evidence. GraphEcho tests whether agents mistake these repeated encounters for additional corroboration. The benchmark varies path counts and evidential origins while holding evidence content fixed, and evaluates both judgments and active exploration. Controlled synthetic experiments reveal model-dependent judgment shifts, but redundant supporting paths increase the share of repeated walks across all evaluated frozen agents. Provenance-aware post-training (PAPT) reduces revisits and improves synthetic accuracy, yet covers fewer distinct sources. On scientific claims, it continues to reduce repetition while accuracy declines. These findings expose a gap between efficient exploration and effective evidence use: an agent can learn to stop repeating itself while overlooking information it needs. GraphEcho provides a controlled way to evaluate both what graph agents conclude and whether their exploration reaches distinct evidential sources.
发表机构
- Tokyo University of Science（东京理科大学）
- Hong Kong Baptist University（香港浸会大学）
- University of Michigan（密歇根大学）
- The University of Tokyo（东京大学）
机构由 AI 辅助整理，请以论文原文为准。
