mlsanityData to 7 Oct 2026

Autogenesis: A Self-Evolving Agent Protocol

arXiv 2604.15034 ↗First posted 16 Apr 2026cs.AIcited by 12

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

also in 1 more
Abstract (arXiv)

LLM-based agent systems can adapt by revising prompts, constructing tools, and changing other runtime resources. Managing these heterogeneous updates requires a shared lifecycle for identifying targets, assessing candidates, and retaining accepted versions, complementing communication protocols such as A2A and MCP. We introduce AUTOGENESIS PROTOCOL (AGP), which decouples what evolves from how updates are proposed. Its Resource Substrate Protocol Layer (RSPL) represents prompts, agents, tools, environments, and memory as protocol-registered resources with explicit state and versioned interfaces. Its Self-Evolution Protocol Layer (SEPL) specifies candidate proposal, assessment, and commit, with auditable histories and support for restoring retained resource states. We instantiate AGP in AUTOGENESIS SYSTEM (AGS), a self-evolving multi-agent system that retrieves, instantiates, and refines resources during execution. Across reasoning, tool-use, and coding benchmarks, AGS improves over its non-evolving configuration, and repeated reasoning runs report the accompanying output-token cost. Execution cases show a shared update lifecycle across all five resource types.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 33 of its 50 references that are in the map. First posted on arXiv 16 Apr 2026.

Builds on

33 of 50 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts24 Oct
  2. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence28 Jul
  3. 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution26 May
  4. 2025HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems17 May
  5. 2025From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agent4 May
  6. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
  7. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug

Other references · 26

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  6. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  8. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  10. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  11. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  12. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
14 more
  1. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  2. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  5. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  6. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  7. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  8. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  9. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
  10. 2025ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimizationcited by 50
  11. 2025ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestrationcited by 44
  12. 2025EvoAgentX: An Automated Framework for Evolving Agentic Workflowscited by 43
  13. 2025AWorld: Orchestrating the Training Recipe for Agentic AIcited by 16
  14. 2025JoyAgent-JDGenie: Technical Report on the GAIAcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 12.

12 papers.

  1. 2026From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flawscited by 21
  2. 2026SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolutioncited by 18
  3. 2026Code Is the Body: Agent-Owned Software Bodies for Recursive Evolution and Descentcited by 3
  4. 2026Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolutioncited by 3
  5. 2026Runtime-Independent Persistent Agents: Preserving Identity, Memory, and Code Across Models, Harnesses, and Serverscited by 2
  6. 2026Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systemscited by 1
  7. 2026MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselvescited by 1
  8. 2026ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memorycited by 0
  9. 2026Beyond Component Testing: Validating Agentic AI Systemscited by 0
  10. 2026Continual Learning in Transitioncited by 0
  11. 2026The Empire, Long Divided, Must Unite: Architectural Convergence in Three LLM Agent Harnessescited by 0
  12. 2026Authorization for Self-Modifying AI Agent Populations: Conserving Authority across Replacement, Forking, and Rollbackcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration
  2. 2026Software Self-Extension with SelfEvolve: an Agentic Architecture for Runtime Code Generation
  3. 2026MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
  4. 2026SEAGym: An Evaluation Environment for Self-Evolving LLM Agents
  5. 2026From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents
  6. 2026AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse
  7. 2026Towards AGI A Pragmatic Approach Towards Self Evolving Agent
  8. 2026Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems