为论文添加结构化元数据，让AI代理高效精准读取研究内容。
Knows: Agent-Native Structured Research Representations
- 给论文配轻量YAML侧边文件，包含可验证的结论与证据链。
- 小模型读侧边文件准确率提升至67%，耗能降86%。
- 适合需要批量处理文献的AI研究者或自动化工具开发者。
研究资料主要以面向读者的PDF文档形式存在，这成为日益依赖智能体的研究工作流瓶颈——大语言模型需从长文档中提取细粒度、任务相关的资讯，过程昂贵、重复且不稳定。本文提出Knows，一种轻量级配套规范，将结构化的论点、证据、来源和可验证关系绑定到现有研究资料上，使大模型代理可直接消费。Knows通过与原始PDF共存的轻量YAML侧边文件（KnowsRecord）实现，无需修改出版物本身，并由确定性模式校验器验证。在20篇跨14个学科的论文上评估140个理解问题，对比仅读PDF、仅读侧边文件及混合条件，六种不同规模的大模型表现：弱模型（0.8B–2B参数）准确率从19%–25%提升至47%–67%（+29至+42个百分点），输入令牌消耗减少29%–86%；通过大模型评分重检，弱模型侧边文件准确率（75%–77%）接近强模型读PDF的表现（78%–83%）。此外，社区侧边文件枢纽https://knows.academy/已收录超万篇论文，持续每日增长，表明该格式具备规模化应用潜力。
原文摘要 · Abstract (English)
Research artifacts are distributed primarily as reader-oriented documents like PDFs. This creates a bottleneck for increasingly agent-assisted and agent-native research workflows, in which LLM agents need to infer fine-grained, task-relevant information from lengthy full documents, a process that is expensive, repetitive, and unstable at scale. We introduce Knows, a lightweight companion specification that binds structured claims, evidence, provenance, and verifiable relations to existing research artifacts in a form LLM agents can consume directly. Knows addresses the gap with a thin YAML sidecar (KnowsRecord) that coexists with the original PDF, requiring no changes to the publication itself, and validated by a deterministic schema linter. We evaluate Knows on 140 comprehension questions across 20 papers spanning 14 academic disciplines, comparing PDF-only, sidecar-only, and hybrid conditions across six LLM agents of varying capacity. Weak models (0.8B--2B parameters) improve from 19--25\% to 47--67\% accuracy (+29 to +42 percentage points) when reading sidecar instead of PDF, while consuming 29--86\% fewer input tokens; an LLM-as-judge re-scoring confirms that weak-model sidecar accuracy (75--77\%) approaches stronger-model PDF accuracy (78--83\%). Beyond this controlled evaluation, a community sidecar hub at https://knows.academy/ has already indexed over ten thousand publications and continues to grow daily, providing independent evidence that the format is adoption-ready at scale.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。