{"work":{"id":"1e4145d4-7462-4e43-a99d-e8f0b14cab76","openalex_id":null,"doi":null,"arxiv_id":"2504.15257","raw_key":null,"title":"FlowReasoner: Reinforcing Query-Level Meta-Agents","authors":null,"authors_text":"Hongcheng Gao, Yue Liu, Yufei He, Longxu Dou, Chao Du, Zhijie Deng, Bryan Hooi, Min Lin, and Tianyu Pang","year":2025,"venue":"cs.AI","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.","external_url":"https://arxiv.org/abs/2504.15257","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-10T14:17:10.147620+00:00","pith_arxiv_id":"2504.15257","created_at":"2026-05-10T05:25:54.985493+00:00","updated_at":"2026-07-10T14:17:10.147620+00:00","title_quality_ok":true,"display_title":"Flowreasoner: Reinforcing query-level meta-agents","render_title":"Flowreasoner: Reinforcing query-level meta-agents"},"hub":{"state":{"work_id":"1e4145d4-7462-4e43-a99d-e8f0b14cab76","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":14,"external_cited_by_count":null,"distinct_field_count":7,"first_pith_cited_at":"2025-07-28T17:59:05+00:00","last_pith_cited_at":"2026-07-08T23:33:49+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-04T05:10:53.489164+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}