PathAnchor improves scientific evidence retrieval and citation accuracy
PathAnchor: Path-Structured Evidence for Scientific Agents
Artificial Intelligence
Summary
Sometimes, when AI systems try to answer science questions, they mix up facts or make claims not fully supported by sources. The authors developed PathAnchor, which organizes information as linked steps keeping the order and connections clear. This helps the system find better evidence, correctly trace it back, and give answers with solid proof. Tests show PathAnchor retrieves and cites relevant sources more accurately than previous methods.
What this means in practice
- •For knowledge base engineers: Enhance scientific QA systems by integrating path-structured evidence to improve source tracing and verify citation accuracy across multiple documents.
- •For medical informatics teams: Improve clinical decision support tools to provide claims backed by clearly traced scientific evidence from multiple publications.
Authors
Qiuhui Chen, Jiafan Lu, Shuaimin Tang, Tao Dai, Suyuan Wang, Chenrui Ji, Zhenglei Zhou, Weimin Zhong
Abstract
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.