让AI论文报告可审计，追踪每句话的证据来源。
From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents
- 构建可验证的证据链，追踪每个结论的出处。
- 提出四维审计标准，量化报告可信度。
- 适合科研人员、期刊审稿人和模型评估者使用。
深度研究代理可在几分钟内生成流畅的科学报告，但读者验证核心主张时发现成本不在阅读，而在溯源：哪句话由哪段文本支持、哪些信息被忽略、证据是否存在矛盾。随着研究生成成本降低，可审计性成为瓶颈，主要风险从孤立事实错误转向证据链薄弱或误导性的科学化输出。本文提出将声明级可审计性作为深度研究代理的设计与评估核心目标，归纳出长期失败模式（客观性漂移、临时约束、不可验证推理），并引入可审计自主研究（AAR）标准——一个紧凑的测量框架，通过溯源覆盖率、溯源严谨性、矛盾透明度和审计成本四项指标实现可测试性。进一步主张采用协议化验证的语义溯源：持久可查询的溯源图，编码主张-证据关系（含冲突），在生成过程中而非发布后持续验证，并提供实用的部署集成模式。
原文摘要 · Abstract (English)
A deep research agent produces a fluent scientific report in minutes; a careful reader then tries to verify the main claims and discovers the real cost is not reading, but tracing: which sentence is supported by which passage, what was ignored, and where evidence conflicts. We argue that as research generation becomes cheap, auditability becomes the bottleneck, and the dominant risk shifts from isolated factual errors to scientifically styled outputs whose claim-evidence links are weak, missing, or misleading. This perspective proposes claim-level auditability as a first-class design and evaluation target for deep research agents, distills recurring long-horizon failure modes (objective drift, transient constraints, and unverifiable inference), and introduces the Auditable Autonomous Research (AAR) standard, a compact measurement framework that makes auditability testable via provenance coverage, provenance soundness, contradiction transparency, and audit effort. We then argue for semantic provenance with protocolized validation: persistent, queryable provenance graphs that encode claim--evidence relations (including conflicts) and integrate continuous validation during synthesis rather than after publication, with practical instrumentation patterns to support deployment 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。