mlsanityData to 7 Oct 2026

Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning

arXiv 2511.16043 ↗First posted 20 Nov 2025cs.LGcited by 68

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

also in 2 more
Abstract (arXiv)

Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an alternative but are typically restricted by the model's inherent capabilities and single-round interactions, hindering the development of complex curricula involving tool use or dynamic reasoning. We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data through multi-step co-evolution and seamless tool integration. Agent0 establishes a symbiotic competition between two agents initialized from the same base LLM: a curriculum agent that proposes increasingly challenging frontier tasks, and an executor agent that learns to solve them. We integrate external tools to enhance the executor's problem-solving capacity; this improvement, in turn, pressures the curriculum agent to construct more complex, tool-aware tasks. Through this iterative process, Agent0 establishes a self-reinforcing cycle that continuously produces high-quality curricula. Empirically, Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks. Code is available at https://github.com/aiming-lab/Agent0.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 73 of its 83 references that are in the map. First posted on arXiv 20 Nov 2025.

Builds on

73 of 83 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolution29 Sep
  2. 2025VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use1 Sep
  3. 2025Understanding Tool-Integrated Reasoning26 Aug
  4. 2025R-Zero: Self-Evolving Reasoning LLM from Zero Data7 Aug
  5. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent3 Jul
  6. 2025SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning30 Jun
  7. 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution26 May
  8. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMs15 Apr
  9. 2024Self-playing Adversarial Language Game Enhances LLM Reasoning16 Apr

Other references · 64

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  6. 2025Qwen3 Technical Reportcited by 8,195
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  9. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  10. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  11. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  12. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
38 more
  1. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  2. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  3. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  4. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  5. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  6. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,099
  7. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  8. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 948
  9. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 323
  10. 2025TTRL: Test-Time Reinforcement Learningcited by 253
  11. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 220
  12. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 193
  13. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 190
  14. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  15. 2025ToRL: Scaling Tool-Integrated RLcited by 166
  16. 2025SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoningcited by 145
  17. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 144
  18. 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecyclecited by 129
  19. 2025BIG-Bench Extra Hardcited by 123
  20. 2025WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agentcited by 114
  21. 2025Online Difficulty Filtering for Reasoning Oriented Reinforcement Learningcited by 100
  22. 2025Maximizing Confidence Alone Improves Reasoningcited by 97
  23. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 90
  24. 2025Efficient Reinforcement Finetuning via Adaptive Curriculum Learningcited by 88
  25. 2024A Survey on Self-Evolution of Large Language Modelscited by 86
  26. 2025SPICE: Self-Play In Corpus Environments Improves Reasoningcited by 78
  27. 2025AgentEvolver: Towards Efficient Self-Evolving Agent Systemcited by 77
  28. 2024Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Modelscited by 73
  29. 2025MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understandingcited by 66
  30. 2025Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Modelscited by 61
  31. 2025Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Modelscited by 58
  32. 2024FullStack Bench: Evaluating LLMs as Full Stack Coderscited by 56
  33. 2025Self-Challenging Language Model Agentscited by 56
  34. 2025Co-Evolving LLM Coder and Unit Tester via Reinforcement Learningcited by 51
  35. 2025SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Datacited by 50
  36. 2025Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variationcited by 44
  37. 2025Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoningcited by 43
  38. 2025EvolveSearch: An Iterative Self-Evolving Search Agentcited by 42

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 66.

68 papers.

Sort:

By area:

  1. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 252
  2. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 140
  3. 2026Dr. Zero: Self-Evolving Search Agents without Training Datacited by 39
  4. 2026Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Datacited by 31
  5. 2025Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoningcited by 28
  6. 2026Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loopscited by 25
  7. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanismscited by 19
  8. 2026Exploring Reasoning Reward Model for Agentscited by 13
  9. 2026Position: Agentic Evolution is the Path to Evolving LLMscited by 13
  10. 2026A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compressioncited by 12
  11. 2026ClawArena: Benchmarking AI Agents in Evolving Information Environmentscited by 10
  12. 2026CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolutioncited by 9
38 more
  1. 2026Scaling Self-Play with Self-Guidancecited by 9
  2. 2026Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learningcited by 8
  3. 2026Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Tracescited by 8
  4. 2026Recursive Synthesis for Long-Horizon Terminal Taskscited by 8
  5. 2026One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligencecited by 7
  6. 2026Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remembercited by 7
  7. 2026EnvHarness: Awakening Static Worlds for Agent Learningcited by 7
  8. 2026SEAD: Self-Evolving Agent for Multi-Turn Service Dialoguecited by 6
  9. 2026Principle-Evolvable Scientific Discovery via Uncertainty Minimizationcited by 6
  10. 2026SAGE: Multi-Agent Self-Evolution for LLM Reasoningcited by 6
  11. 2026Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Librariescited by 6
  12. 2026RewardHarness: Self-Evolving Agentic Post-Trainingcited by 5
  13. 2026Self-Evolving World Models for LLM Agent Planningcited by 5
  14. 2026PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agentscited by 5
  15. 2026RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environmentscited by 5
  16. 2026Rethinking Continual Experience Internalization for Self-Evolving LLM Agentscited by 4
  17. 2025CogDoc: Towards Unified thinking in Documentscited by 3
  18. 2026SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agentscited by 3
  19. 2026Self-evolving Embodied AIcited by 2
  20. 2026Agentic Tool Use in Large Language Modelscited by 2
  21. 2026El Agente Forjador: Task-Driven Agent Generation for Quantum Simulationcited by 2
  22. 2026Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoningcited by 2
  23. 2026MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphscited by 2
  24. 2026PREPING: Building Agent Memory without Taskscited by 2
  25. 2026Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probescited by 2
  26. 2026Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?cited by 2
  27. 2026MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoningcited by 2
  28. 2026SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Readcited by 1
  29. 2026Internalizing Agency from Reflective Experiencecited by 1
  30. 2026MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learningcited by 1
  31. 2026EXG: Self-Evolving Agents with Experience Graphscited by 1
  32. 2026RISE: Reliable Improvement in Self-Evolving Vision-Language Modelscited by 1
  33. 2026Rethinking Memory as Continuously Evolving Connectivitycited by 1
  34. 2026Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systemscited by 1
  35. 2026MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agentscited by 1
  36. 2026Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Designcited by 1
  37. 2026Learning What to Practice: Diagnosis-Guided Self-Evolution for Language Modelscited by 1
  38. 2026BiomechAgent: AI-Assisted Biomechanical Analysis Through Code-Generating Agentscited by 0

50 most cited of 68 All 68 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Towards AGI A Pragmatic Approach Towards Self Evolving Agent
  2. 2025Multi-Agent Evolve: LLM Self-Improve through Co-evolution
  3. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
  4. 2025CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution
  5. 2026Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
  6. 2025AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
  7. 2025Evolving in Tasks: Empowering the Multi-modality Large Language Model as the Computer Use Agent
  8. 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents