发表机构
East China University of Science and Technology; Fudan University; Tencent（华东理工大学; 复旦大学; 腾讯）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PathAnchor通过路径结构化证据工作区组织科学证据，提升智能体检索与引用完整性，在柔性传感器问题上领先六个系统。
AI 中文摘要
科学智能体能够检索相关段落，但仍会丢失功能顺序、混合不同来源的证据，或得出超出检索记录的结论。我们提出了PathAnchor，一个基于路径结构化证据工作区的有界科学推理系统。该系统不将段落或提取的概念视为独立单元，而是检索保留角色、方向及每个转换所支持证据的来源链接的材料-传感器-信号-系统轨迹。控制器使用三个只读工具来搜索特定论文的轨迹、跨候选来源追踪路径，并在生成带引用的答案和明确的证据边界之前打开精确证据。在120个单篇和跨论文的柔性传感器问题上，PathAnchor得分82.6%，领先于六个被评估的系统。在匹配的控制器、语料库和六次调用预算下，用路径结构化记录替换无序概念图将来源召回率从61.3%提高到82.9%，将答案中所有声明均引用已打开证据的比例从69.2%提高到90.0%，并减少了工具调用。这些结果表明，在固定智能体资源下，证据组织影响检索和引用完整性。
英文摘要
Scientific agents can retrieve relevant passages yet still lose functional order, mix evidence across sources, or state conclusions that exceed the retrieved record. We introduce PathAnchor, a bounded scientific reasoning system built on path-structured evidence workspaces. Instead of treating passages or extracted concepts as independent units, the system retrieves source-linked Material-Sensor-Signal-System trajectories that preserve role, direction, and the evidence supporting each transition. A controller uses three read-only tools to search paper-specific trajectories, trace paths across candidate sources, and open exact evidence before producing a claim-cited answer and an explicit evidence boundary. On 120 single- and cross-paper flexible-sensor questions, PathAnchor scores 82.6% and leads six evaluated systems. Under a matched controller, corpus, and six-call budget, replacing unordered concept graphs with path-structured records raises source recall from 61.3% to 82.9%, increases answers whose claims all cite opened evidence from 69.2% to 90.0%, and reduces tool calls. These results show that evidence organization affects retrieval and citation completeness under fixed agent resources.
