从流畅到可验证：深度研究代理的声明级可审计性
From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents
AI总结：
本文提出深度研究代理的声明级可审计性作为关键设计目标，通过溯源覆盖、正确性、矛盾透明度和审计努力来评估可审计性，强调在合成过程中持续验证以提升科学输出的可信度。
摘要：
深度研究代理可以在几分钟内生成一份流畅的科学报告；然后仔细的读者试图验证主要声明，并发现真正的成本不是阅读，而是追溯：哪句话由哪段落支持，什么被忽略了，证据之间哪里有冲突。我们认为，随着研究生成变得廉价，可审计性成为瓶颈，主导的风险从孤立的事实错误转移到了科学风格的输出，其声明-证据链接薄弱、缺失或误导。这种观点将声明级可审计性作为深度研究代理的第一设计和评估目标，提炼出长期存在的失败模式（目标漂移、短暂约束和不可验证的推理），并引入了可审计的自主研究（AAR）标准，一个紧凑的测量框架，使可审计性通过溯源覆盖、溯源正确性、矛盾透明度和审计努力来测试。我们随后主张语义溯源与协议化验证：持久、可查询的溯源图谱，编码声明-证据关系（包括冲突），并在合成过程中整合持续验证，而不是在发布后进行验证，同时提供实用的仪器模式以支持大规模部署。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
