Salesforce Research 发布 EvoHarnessBench 测试智能体应对工具环境持续演进
Salesforce Research 搞了个 EvoHarnessBench，17 条流 802 个任务，专门测智能体在工具库不断扩张时会不会顾此失彼，还提供在线 demo 可以接入自己的智能体跑分。
Salesforce Research 推出 EvoHarnessBench，覆盖 17 条任务流和 802 个任务，测试智能体在工具、技能和子智能体不断扩展时的表现。实验发现一个反复出现的模式：擅长保留既有能力的智能体往往难以利用新引入的工具，反之亦然。因此基准将能力保持（retention）与适应新能力（adaptation）分开计分，避免聚合分数掩盖问题。结果支持双层适应策略：用当前经验做内部更新，再在外层检验这些更新在环境再次变化后是否仍然有效，包括识别已过期的存储产物。
EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness? https://t.co/LQUhfKpAQB
Agents work through a harness of tools, skills, and specialist agents that keeps expanding as new capabilities arrive. EvoHarnessBench tests what happens as that harness grows, stage by stage, across 17 streams and 802 tasks.
A recurring pattern: the methods that best preserve earlier competence often struggle to use newly introduced capabilities, and vice versa. Aggregate scores can hide this, so we measure retention and adaptation separately.
Our results point to bi-level adaptation: inner updates from current experience, plus an outer check on whether those updates still hold once the harness moves again, including spotting when stored artifacts have gone stale.
Try the live demo or bring your own agent.
#AgenticAI #EnterpriseAI
