Structured paper representation helps agents find and connect ai research faster

Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for Agents

Artificial IntelligenceComputation and Language

Summary

Scientific papers often contain important ideas, experiments, and results scattered in long text. The authors created SPRA, a way to break down papers into clear parts like problems, methods, and findings. This organized format helps computer agents quickly find and check scientific information. They tested SPRA on millions of AI papers and showed it improves how agents answer questions and draw conclusions compared to traditional methods. Their work supports better tools to explore and reuse scientific knowledge efficiently.

What this means in practice

  • For academic library teams: Enable library search systems to provide detailed, reliable answers by linking paper components instead of searching full texts only.
  • For ai application developers: Build AI tools that generate concise summaries and cross-paper syntheses from large collections of research using structured content from SPRA.

Authors

Yutong Leng, Haojiong Chen, Fukai Shang, Xiaoyang Wang, Mindong Liu, Runyuan Ma, Jiantao Qiu

Abstract

Scientific agents must connect research problems, methods, and findings dispersed through narrative articles. We introduce SPRA (Structured Paper Representation for Agents), a paper-level representation of persistent research objects and typed relations. Its empirical-AI profile organizes Problems, Contributions, Components, ExperimentSetups, Measures, and Findings for querying, traversal, and reuse. Selected paper-level citation relations record dependencies, component use, and comparisons with prior work; source locations support verification. We instantiate SPRA across more than one million AI papers, with 19.95 million research units and 24.07 million internal relations. Evaluations access SPRA through Schema-RAG with task evidence fixed before inference. Across seven subfields, SPRA improves source-conditioned scientific QA by 0.381/5 over passage retrieval while remaining close to Full Compact (0.078/5 lower on average). In directed cross-paper reasoning, qualification improves by 0.184/5 over passage retrieval; Top-5 synthesis shows mixed quality effects. Across all paired RQ2 tasks, including Top-5, input+output tokens decrease by 28.5% relative to passage retrieval and 95.3% relative to Full Compact. In idea generation, a 0.067-point lower Overall score than Full Compact accompanies 93.7% fewer input+output tokens. Together, these results support SPRA as a usable representation of scientific content and a foundation for research workflows that connect, inspect, and reuse paper-level research objects. The SPRA resource is accessible through the SciVerse scholarly-data platform.