超越单一通道代理基准测试
Beyond single-channel agentic benchmarking
AI总结：
本文提出通过人类-人工智能双元组的可靠性评估代理安全性，强调不相关错误模式对风险降低的重要性，以改进AI安全性评估方法。
摘要：
当代用于代理人工智能（AI）的基准测试经常通过孤立的任务级准确性阈值来评估安全性，隐含地将自主系统视为单一故障点。这种单一通道范式与安全关键工程中已确立的原则相悖，其中通过冗余、错误模式的多样性以及联合系统可靠性来实现风险缓解。本文认为，当代理在有人参与的环境中部署时，孤立地评估AI代理会系统性地错误表征其操作安全性。使用最近的一个实验室安全基准测试作为案例研究表明，即使不完美的AI系统也能通过作为冗余审计层来提供显著的安全性，以对抗已记录的人类失败源，包括注意力下降、无意识盲视以及偏差的正常化。这种观点将代理安全性评估重新定位到人类-人工智能双元组的可靠性，而非绝对的代理准确性，特别强调不相关错误模式作为风险降低的主要决定因素。这种转变使AI基准测试与其它安全关键领域已确立的做法相一致，并为更生态有效的安全性评估提供了一条路径。
英文摘要：
Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm diverges from established principles in safety-critical engineering, where risk mitigation is achieved through redundancy, diversity of error modes, and joint system reliability. This paper argues that evaluating AI agents in isolation systematically mischaracterizes their operational safety when deployed within human-in-the-loop environments. Using a recent laboratory safety benchmark as a case study demonstrates that even imperfect AI systems can nonetheless provide substantial safety utility by functioning as redundant audit layers against well-documented sources of human failure, including vigilance decrement, inattentional blindness, and normalization of deviance. This perspective reframes agentic safety evaluation around the reliability of the human-AI dyad rather than absolute agent accuracy, with a particular emphasis on uncorrelated error modes as the primary determinant of risk reduction. Such a shift aligns AI benchmarking with established practices in other safety-critical domains and offers a path toward more ecologically valid safety assessments.
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。
