mlsanityData to 14 Oct 2026

OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

arXiv 2505.23885 ↗First posted 29 May 2025cs.AI cs.CLcited by 131

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

Large Language Model (LLM)-based multi-agent systems show promise for automating real-world tasks but struggle to transfer across domains due to their domain-specific nature. Current approaches face two critical shortcomings: they require complete architectural redesign and full retraining of all components when applied to new domains. We introduce Workforce, a hierarchical multi-agent framework that decouples strategic planning from specialized execution through a modular architecture comprising: (i) a domain-agnostic Planner for task decomposition, (ii) a Coordinator for subtask management, and (iii) specialized Workers with domain-specific tool-calling capabilities. This decoupling enables cross-domain transferability during both inference and training phases: During inference, Workforce seamlessly adapts to new domains by adding or modifying worker agents; For training, we introduce Optimized Workforce Learning (OWL), which improves generalization across domains by optimizing a domain-agnostic planner with reinforcement learning from real-world feedback. To validate our approach, we evaluate Workforce on the GAIA benchmark, covering various realistic, multi-domain agentic tasks. Experimental results demonstrate Workforce achieves open-source state-of-the-art performance (69.70%), outperforming commercial systems like OpenAI's Deep Research by 2.34%. More notably, our OWL-trained 32B model achieves 52.73% accuracy (+16.37%) and demonstrates performance comparable to GPT-4o on challenging tasks. To summarize, by enabling scalable generalization and modular domain transfer, our work establishes a foundation for the next generation of general-purpose AI assistants.

Key facts. Cited by 131 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 35 of its 49 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

35 of 49 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMs15 Apr
  2. 2025SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks19 Mar
  3. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools7 Feb
  4. 2025Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains10 Jan
  5. 2024MALT: Improving Reasoning with Multi-Agent LLM Training2 Dec
  6. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation1 Aug

Other references · 29

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2024Qwen2.5 Technical Reportcited by 4,942
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  5. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  6. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  7. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  8. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  9. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  10. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  11. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  12. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
17 more
  1. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  2. 2024AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agentscited by 401
  3. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 338
  4. 2025SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolutioncited by 263
  5. 2023FireAct: Toward Language Agent Fine-tuningcited by 256
  6. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 256
  7. 2024Magentic-One: A Generalist Multi-Agent System for Solving Complex Taskscited by 232
  8. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 205
  9. 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 137
  10. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Modelscited by 100
  11. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systemscited by 90
  12. 2024Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Datacited by 67
  13. 2024HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scalecited by 61
  14. 2025AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agentscited by 52
  15. 2025MPO: Boosting LLM Agents with Meta Plan Optimizationcited by 36
  16. 2024Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learningcited by 33
  17. 2024TapeAgents: a Holistic Framework for Agent Development and Optimizationcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 62; 2026: 69.

131 papers.

Sort:

By area:

  1. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 254
  2. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  3. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 128
  4. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 127
  5. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  6. 2025WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agentcited by 119
  7. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 116
  8. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 95
  9. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 94
  10. 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 80
  11. 2025PyVision: Agentic Vision with Dynamic Toolingcited by 79
  12. 2025Latent Collaboration in Multi-Agent Systemscited by 73
38 more
  1. 2025In-the-Flow Agentic System Optimization for Effective Planning and Tool Usecited by 72
  2. 2025WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learningcited by 61
  3. 2025Cache-to-Cache: Direct Semantic Communication Between Large Language Modelscited by 61
  4. 2025Training-Free Group Relative Policy Optimizationcited by 55
  5. 2025ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestrationcited by 47
  6. 2025Agentic Web: Weaving the Next Web with AI Agentscited by 45
  7. 2025Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Trainingcited by 42
  8. 2025MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agentscited by 42
  9. 2026AOrchestra: Automating Sub-Agent Creation for Agentic Orchestrationcited by 35
  10. 2025Efficient Agents: Building Effective Agents While Reducing Costcited by 32
  11. 2025AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxescited by 30
  12. 2025OAgents: An Empirical Study of Building Effective Agentscited by 29
  13. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 29
  14. 2025Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Executioncited by 27
  15. 2025Coding Agents with Multimodal Browsing are Generalist Problem Solverscited by 25
  16. 2026Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verificationcited by 22
  17. 2025DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seekingcited by 21
  18. 2025AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learningcited by 20
  19. 2025Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agentscited by 17
  20. 2026TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Trainingcited by 17
  21. 2025MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Usecited by 16
  22. 2025Towards Personalized Deep Research: Benchmarks and Evaluationscited by 16
  23. 2026EvoRoute: Experience-Driven Self-Routing LLM Agent Systemscited by 16
  24. 2026AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agentscited by 16
  25. 2025ReCode: Unify Plan and Action for Universal Granularity Controlcited by 15
  26. 2026MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Taskscited by 15
  27. 2025Reinforcement Learning Foundations for Deep Research Systems: A Surveycited by 14
  28. 2026Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agentscited by 14
  29. 2026Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agentscited by 14
  30. 2025Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Modelscited by 13
  31. 2026StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Managementcited by 13
  32. 2025Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systemscited by 12
  33. 2026OffSeeker: Online Reinforcement Learning Is Not All You Need for Deep Research Agentscited by 12
  34. 2025GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learningcited by 11
  35. 2025How Far Are We from Genuinely Useful Deep Research Agents?cited by 11
  36. 2025VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seekingcited by 10
  37. 2025FlowSearch: Advancing deep research with dynamic structured knowledge flowcited by 10
  38. 2026Recursive Multi-Agent Systemscited by 10

50 most cited of 131 All 131 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning
  2. 2026Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems
  3. 2025Curriculum Guided Massive Multi Agent System Solving For Robust Long Horizon Tasks
  4. 2025WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning
  5. 2026Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning
  6. 2025Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task Planning
  7. 2025ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning
  8. 2026Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor