mlsanityData to 14 Oct 2026

FlowReasoner: Reinforcing Query-Level Meta-Agents

arXiv 2504.15257 ↗First posted 21 Apr 2025cs.AIcited by 63

Not on the map. Why?

Cited by 51 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). Builds on 51 of its 62 references that are in the map. First posted on arXiv 21 Apr 2025.

Builds on

51 of 62 references.

References · 51

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2024Qwen2.5 Technical Reportcited by 4,942
  7. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  8. 2021Program Synthesis with Large Language Modelscited by 3,637
  9. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  10. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  11. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  12. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
38 more
  1. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  2. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  4. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  5. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  6. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  7. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  8. 2023Large Language Models as Optimizerscited by 864
  9. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  10. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  11. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
  12. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 570
  13. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  14. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  15. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 551
  16. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
  17. 2024AFlow: Automating Agentic Workflow Generationcited by 432
  18. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 426
  19. 2024Automated Design of Agentic Systemscited by 407
  20. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
  21. 2024TextGrad: Automatic "Differentiation" via Textcited by 273
  22. 2023Think before you speak: Training Language Models With Pause Tokenscited by 264
  23. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 216
  24. 2025Multi-agent Architecture Search via Agentic Supernetcited by 179
  25. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 155
  26. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 119
  27. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithmscited by 113
  28. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structurescited by 110
  29. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 107
  30. 2024Symbolic Learning Enables Self-Evolving Agentscited by 106
  31. 2025GuardReasoner: Towards Reasoning-based LLM Safeguardscited by 100
  32. 2024AutoFlow: Automated Workflow Generation for Large Language Model Agentscited by 83
  33. 2024Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaborationcited by 67
  34. 2025Efficient Inference for Large Reasoning Models: A Surveycited by 61
  35. 2024Archon: An Architecture Search Framework for Inference-Time Techniquescited by 60
  36. 2025ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimizationcited by 56
  37. 2024Offline Training of Language Model Agents with Functions as Learnable Weightscited by 48
  38. 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systemscited by 23

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 23; 2026: 40.

63 papers.

Sort:

By area:

  1. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 356
  2. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  3. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  4. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 116
  5. 2026Code as Agent Harnesscited by 47
  6. 2025EvoAgentX: An Automated Framework for Evolving Agentic Workflowscited by 44
  7. 2025GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoningcited by 42
  8. 2025EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systemscited by 37
  9. 2025G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learningcited by 29
  10. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 29
  11. 2026ReCreate: Reasoning and Creating Domain Agents Driven by Experiencecited by 24
  12. 2026From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agentscited by 24
38 more
  1. 2026Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baselinecited by 22
  2. 2025RobustFlow: Towards Robust Agentic Workflow Generationcited by 20
  3. 2025MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programmingcited by 16
  4. 2026EvoRoute: Experience-Driven Self-Routing LLM Agent Systemscited by 16
  5. 2025Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidancecited by 14
  6. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  7. 2026AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generationcited by 13
  8. 2025Aime: Towards Fully-Autonomous Multi-Agent Frameworkcited by 9
  9. 2026SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topologycited by 9
  10. 2026EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learningcited by 8
  11. 2026Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow Constructioncited by 8
  12. 2026SEVerA: Verified Synthesis of Self-Evolving Agentscited by 8
  13. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  14. 2025VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learningcited by 6
  15. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 6
  16. 2026Self-Improvement of Large Language Models: A Technical Overview and Future Outlookcited by 5
  17. 2025Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directionscited by 4
  18. 2025Efficient Tree-Structured Deep Research with Adaptive Resource Allocationcited by 4
  19. 2026Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systemscited by 4
  20. 2025MAS2: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systemscited by 3
  21. 2025Experience-Guided Adaptation of Inference-Time Reasoning Strategiescited by 3
  22. 2026Learning to Compose for Cross-domain Agentic Workflow Generationcited by 3
  23. 2026MAS-on-the-Fly: In-Context Structural Adaptation of LLM-Based Multi-Agent Systemscited by 3
  24. 2026FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reusecited by 3
  25. 2025Grammar Search for Multi-Agent Systemscited by 2
  26. 2026Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systemscited by 2
  27. 2026MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learningcited by 2
  28. 2026Towards Direct Evaluation of Harness Optimizers via Priority Rankingcited by 2
  29. 2026Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systemscited by 2
  30. 2025Agentic-KGR: Co-evolutionary Knowledge Graph Construction through Multi-Agent Reinforcement Learningcited by 1
  31. 2025FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaborationcited by 1
  32. 2026LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learningcited by 1
  33. 2026SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestrationcited by 1
  34. 2026FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skillscited by 1
  35. 2026TROVE: Adaptive Agent Skill Orchestration via Trace-Grounded Route Validation and Editingcited by 1
  36. 2025ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systemscited by 0
  37. 2026HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoningcited by 0
  38. 2026AIPO: Learning to Reason from Active Interactioncited by 0

50 most cited of 63 All 63 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
  2. 2025In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
  3. 2026FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
  4. 2025Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows
  5. 2025DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
  6. 2026AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
  7. 2026Tools as Continuous Flow for Evolving Agentic Reasoning
  8. 2025Inefficiencies of Meta Agents for Agent Design