{
  "id": 10846338,
  "title": "UserProxyBench: Evaluating LLM User Simulators for Agent Benchmarks and Training",
  "url": "https://urgent.news/2026/09/29/userproxybench-evaluating-llm-user-simulators-for-agent-benchmarks",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-29T17:17:24.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.38043v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Interactive agent benchmarks and multi-turn reinforcement learning increasingly place a second language model in the role of the user. This simulated user controls what information the agent receives and when, yet current benchmarks score only the agent and do not directly measure whether the user correctly executed its assigned role. We introduce UserProxyBench, an evaluation layer over the…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}