{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/flowreasoner-reinforcing-query-level-meta","title":"FlowReasoner: Reinforcing Query-Level Meta-Agents","arxiv_id":"2504.15257","date":"2025-04-21","proceeding":null,"authors":["Hongcheng Gao","Yue Liu","Yufei He","Longxu Dou","Chao Du","Zhijie Deng","Bryan Hooi","Min Lin","Tianyu Pang"],"abstract":"This paper proposes a query-level meta-agent named FlowReasoner to automate the design of query-level multi-agent systems, i.e., one system per user query. Our core idea is to incentivize a reasoning-based meta-agent via external execution feedback. Concretely, by distilling DeepSeek R1, we first endow the basic reasoning ability regarding the generation of multi-agent systems to FlowReasoner. Then, we further enhance it via reinforcement learning (RL) with external execution feedback. A multi-purpose reward is designed to guide the RL training from aspects of performance, complexity, and efficiency. In this manner, FlowReasoner is enabled to generate a personalized multi-agent system for each user query via deliberative reasoning. Experiments on both engineering and competition code benchmarks demonstrate the superiority of FlowReasoner. Remarkably, it surpasses o1-mini by 10.52% accuracy across three benchmarks. The code is available at https://github.com/sail-sg/FlowReasoner.","url_abs":"https://arxiv.org/abs/2504.15257v1","url_pdf":"https://arxiv.org/pdf/2504.15257v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"flowreasoner-reinforcing-query-level-meta","repo_url":"https://github.com/sail-sg/flowreasoner","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.15257","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}