mlsanityData to 7 Oct 2026

Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

arXiv 2505.20286 ↗First posted 26 May 2025cs.AIcited by 114

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

also in 1 more
Abstract (arXiv)

Recent advances in large language models (LLMs) have enabled agents to autonomously perform complex, open-ended tasks. However, many existing frameworks depend heavily on manually predefined tools and workflows, which hinder their adaptability, scalability, and generalization across domains. In this work, we introduce Alita--a generalist agent designed with the principle of "Simplicity is the ultimate sophistication," enabling scalable agentic reasoning through minimal predefinition and maximal self-evolution. For minimal predefinition, Alita is equipped with only one component for direct problem-solving, making it much simpler and neater than previous approaches that relied heavily on hand-crafted, elaborate tools and workflows. This clean design enhances its potential to generalize to challenging questions, without being limited by tools. For Maximal self-evolution, we enable the creativity of Alita by providing a suite of general-purpose components to autonomously construct, refine, and reuse external capabilities by generating task-related model context protocols (MCPs) from open source, which contributes to scalable agentic reasoning. Notably, Alita achieves 75.15% pass@1 and 87.27% pass@3 accuracy, which is top-ranking among general-purpose agents, on the GAIA benchmark validation dataset, 74.00% and 52.00% pass@1, respectively, on Mathvista and PathVQA, outperforming many agent systems with far greater complexity. More details will be updated at hrefhttps://github.com/CharlesQ9/Alitahttps://github.com/CharlesQ9/Alita.

Key facts. Cited by 114 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 18 of its 24 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

18 of 24 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning16 Feb
  2. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools7 Feb
  3. 2024AFlow: Automating Agentic Workflow Generation14 Oct
  4. 2023CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models23 May

Other references · 14

  1. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,582
  2. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  3. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  4. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  5. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 467
  6. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
  7. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 211
  8. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 122
  9. 2024TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Taskscited by 70
  10. 2025AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agentscited by 49
  11. 2025Large Language Models are overconfident and amplify human biascited by 30
  12. 2024Long Term Memory: The Foundation of AI Self-Evolutioncited by 29
2 more
  1. 2025RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generationcited by 26
  2. 2024AppBench: Planning of Multiple APIs from Various APPs for Complex User Instructioncited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 65; 2026: 49.

114 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2025UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learningcited by 205
  3. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 140
  4. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 122
  5. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 119
  6. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 99
  7. 2025Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?cited by 91
  8. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 90
  9. 2025Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluationcited by 83
  10. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 81
  11. 2026Self-Harness: Harnesses That Improve Themselvescited by 79
  12. 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 75
38 more
  1. 2025PyVision: Agentic Vision with Dynamic Toolingcited by 71
  2. 2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoningcited by 68
  3. 2025WideSearch: Benchmarking Agentic Broad Info-Seekingcited by 66
  4. 2025WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learningcited by 59
  5. 2025Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agentscited by 52
  6. 2025FLEX: Continuous Agent Evolution via Forward Learning from Experiencecited by 51
  7. 2025SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarioscited by 49
  8. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  9. 2026SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Taskscited by 45
  10. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 45
  11. 2025Agentic Web: Weaving the Next Web with AI Agentscited by 43
  12. 2026EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discoverycited by 41
  13. 2025MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agentscited by 37
  14. 2025AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocolcited by 36
  15. 2025CoAct-1: Computer-using Multi-Agent System with Coding Actionscited by 33
  16. 2025CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolutioncited by 33
  17. 2025MCP-Zero: Active Tool Discovery for Autonomous LLM Agentscited by 32
  18. 2025VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Modelscited by 31
  19. 2025AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxescited by 28
  20. 2025OAgents: An Empirical Study of Building Effective Agentscited by 28
  21. 2025Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Executioncited by 27
  22. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarioscited by 25
  23. 2025PolySkill: Learning Generalizable Skills Through Polymorphic Abstractioncited by 25
  24. 2025Position: Agent Should Invoke External Tools ONLY When Epistemically Necessarycited by 22
  25. 2025MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Sciencecited by 22
  26. 2025Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Taskscited by 22
  27. 2026ReCreate: Reasoning and Creating Domain Agents Driven by Experiencecited by 22
  28. 2025Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolutioncited by 18
  29. 2025MGA: Memory-Driven GUI Agent for Observation-Centric Interactioncited by 18
  30. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 17
  31. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 17
  32. 2025PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literaturecited by 15
  33. 2025WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidancecited by 15
  34. 2025Open Data Synthesis For Deep Researchcited by 14
  35. 2025Physics Supernova: AI Agent Matches Elite Gold Medalists at IPhO 2025cited by 14
  36. 2025General Agentic Planning Through Simulative Reasoning with World Modelscited by 13
  37. 2026MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Taskscited by 13
  38. 2025SynthAgent: Adapting Web Agents with Synthetic Supervisioncited by 12

50 most cited of 114 All 114 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Generalizability of Large Language Model-Based Agents: A Comprehensive Survey
  2. 2025ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems
  3. 2025Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research
  4. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
  5. 2023Agents: An Open-source Framework for Autonomous Language Agents
  6. 2025Towards Efficient Agents: A Co-Design of Inference Architecture and System
  7. 2024Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation
  8. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges