新闻
ARE-bench: Benchmarking Agents' Research Ability in Real-World Researcher Sessions and Workspaces
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- ARE-bench evaluates research agents on 75 real-world tasks from active researcher projects, measuring whether agents respect prior decisions and existing workspace state.
- 为何重要
- Matters for engineers building or deploying research agents who need realistic assessment beyond clean benchmark environments.
- 注意
- Top models pass only 66.2% of tasks; performance drops to 28-40% when workspace history and material requirements are checked, suggesting current benchmarks may overestimate capability.
- agent
- eval
- benchmark
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。