新闻
UserProxyBench: Evaluating LLM User Simulators for Agent Benchmarks and Training
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- UserProxyBench introduces a scoring system to measure whether simulated users in agent benchmarks follow their instructions correctly, independent of agent performance.
- 为何重要
- Matters when building multi-turn agent benchmarks or training agents with reinforcement learning using language models as simulated users.
- 注意
- User instruction violations like premature information disclosure don't always hurt task rewards but do change the interaction being evaluated, masking evaluation quality issues.
- agent
- llm
- language model
- 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。