Skill-Contracted Agents for Evidence-Aware Materials Literature Analysis

基于技能契约的材料文献证据感知分析智能体

Abstract: Materials science literature analysis requires simultaneous attention to composition, processing, characterization, and property relationships, yet conventional retrieval-augmented generation pipelines struggle to reconcile heterogeneous tasks within a single retrieve-then-generate architecture.

摘要： 材料科学文献分析需要同时关注成分、加工、表征和性能之间的关系，然而传统的检索增强生成（RAG）流程难以在单一的“先检索后生成”架构中协调各种异构任务。

Here we present AlphaAgent, a skill-driven agent framework that decouples retrieval-based question answering from paper-level report generation through explicit skill contracts.

我们在此提出 AlphaAgent，这是一个由技能驱动的智能体框架，通过明确的技能契约，将基于检索的问答与论文层面的报告生成解耦。

A dedicated retrieval skill rewrites user requests into material-specific search intents, queries a curated index of more than 300,000 papers from the Journal Citation Reports Metallurgy and Metallurgical Engineering category, and reformulates queries when initial evidence is insufficient.

一个专门的检索技能会将用户请求重写为材料特定的搜索意图，查询一个包含来自《期刊引证报告》（JCR）冶金与冶金工程类别中超过 30 万篇论文的精选索引，并在初始证据不足时重新构建查询。

A separate report-generation skill parses full-text PDFs to produce structured per-paper analytical reports and cross-paper summaries.

另一个独立的报告生成技能则负责解析全文 PDF，以生成结构化的单篇论文分析报告和跨论文综述。

In a blind evaluation on 40 materials-science questions, half of which required deep analytical reasoning, AlphaAgent substantially outperformed a baseline system matched for underlying model, document index, and retrieval scale, with the largest gains in mechanistic explanation and awareness of credibility boundaries.

在针对 40 个材料科学问题的盲测评估中（其中一半问题需要深度分析推理），AlphaAgent 的表现显著优于在底层模型、文档索引和检索规模上均匹配的基准系统，尤其在机制解释和可信度边界感知方面提升最为显著。

These results indicate that explicit task separation, refined retrieval intent, and evidence-aware generation improve large-language-model-based literature analysis for materials research.

这些结果表明，明确的任务分离、精细化的检索意图以及证据感知生成，能够提升基于大语言模型的材料研究文献分析能力。