agent/papers/items/2025-2512-23611-close-the-loop-synthesizing-infinite-tool-use-data-via-multi-agent-role-playing.md

Paper: Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing

---

type: paper title: "Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing" authors: Yuwen Li, Wei Zhang, Zelong Huang, Mason Yang, Jiajun Wu, Shawn Guo, Huahao Hu, Lingyi Sun, et al. year: 2025 venue: arXiv url: https://arxiv.org/abs/2512.23611 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2025-12-29 updated_at: 2025-12-29 status: queued relevance: high topics:

• agent-evaluation
• multi-agent
• rag
• tool-use
• workflow-agent methods:

benchmarks:

models:

datasets:

• cs.CL related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 15 collection_queries: function-calling

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: function-calling
• inferred topics: agent-evaluation, multi-agent, rag, tool-use, workflow-agent
• arXiv categories: cs.CL
• collection score: 15

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2512.23611