迈向AI代理可靠性的科学
Towards a Science of AI Agent Reliability
AI总结：
本文提出十二个具体指标，从一致性、鲁棒性、可预测性和安全性四个维度分解AI代理的可靠性，并通过实验揭示能力提升仅带来可靠性小幅改进。
摘要：
AI代理越来越多地被部署来执行重要任务。虽然标准基准测试上的准确率分数不断提高表明进展迅速，但许多代理在实践中仍然持续失败。这种差异凸显了当前评估的一个根本局限性：将代理行为压缩为单一成功指标会掩盖关键的操作缺陷。值得注意的是，它忽略了代理是否在不同运行中表现一致、能否承受扰动、是否可预测地失败，或者错误严重性是否有界。基于安全关键工程，我们通过提出十二个具体指标来提供全面的性能概况，这些指标将代理可靠性分解为四个关键维度：一致性、鲁棒性、可预测性和安全性。在两个互补基准测试上评估15个模型，我们发现最近的能力提升仅带来了可靠性的小幅改进。通过暴露这些持续的局限性，我们的指标补充了传统评估，同时提供了推理代理如何表现、退化和失败的工具。
英文摘要：
AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many agents still continue to fail in practice. This discrepancy highlights a fundamental limitation of current evaluations: compressing agent behavior into a single success metric obscures critical operational flaws. Notably, it ignores whether agents behave consistently across runs, withstand perturbations, fail predictably, or have bounded error severity. Grounded in safety-critical engineering, we provide a holistic performance profile by proposing twelve concrete metrics that decompose agent reliability along four key dimensions: consistency, robustness, predictability, and safety. Evaluating 15 models across two complementary benchmarks, we find that recent capability gains have only yielded small improvements in reliability. By exposing these persistent limitations, our metrics complement traditional evaluations while offering tools for reasoning about how agents perform, degrade, and fail.
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。
