Recursive Self-Improvement

Overview

Recursive self-improvement asks how AI systems can use their own experience to make future versions more capable, efficient, or safe. Approaches include revising agent prompts, tools, memory, and code; evolving training data or models; and using search, world models, or learned evaluators to guide changes. Most demonstrated progress comes from bounded tasks with external or held-out checks, such as coding, reasoning, robotics, and scientific research benchmarks. A central challenge is ensuring that gains persist beyond the feedback used to produce them, without benchmark overfitting, unsafe regressions, or goal drift.

Latest papers

CardsList

107 papers29 papers in the last four weeks, down 29% on the four weeks before. 0.2% of all new papers.

  1. AREX: Towards a Recursively Self-Improving Agent for Deep Research

    Jul 23, 2026Shuqi Lu, Chaofan Li, Kun Luo +21Agentic RLDeep Research Agents

  2. Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops

    Jul 8, 2026Mingguang Chen, Licheng Wang, Bo QuLLM Self-RefinementHuman-in-the-Loop Evaluation

  3. MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution

    Jul 6, 2026Zefeng Wang, Minxi Yan, Jinhe Bi +3LLM Agent Self-ImprovementLLM Agent Skill Learning

  4. Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement

    Jul 5, 2026Jiang Zhang, Bing Yuan, Qian ZhangLanguage Model IntrospectionLanguage Model Self-Improvement

  5. Algorithmic Unverifiability of Safety for Fixed and Recursively Self-Improving Systems

    Jun 26, 2026Jose Pascual Gumbau MezquitaFormal VerificationSelf-Improving Agents

  6. The Red Queen Gödel Machine: Co-Evolving Agents and Their Evaluators

    Jun 24, 2026Alex Iacob, Andrej Jovanović, William F. Shen +12Evolutionary OptimizationAI Agent Evaluation

  7. Recursive Self-Evolving Agents via Held-Out Selection

    Jun 17, 2026Michael Nguyen, Quoc Nguyen, Paul VuongLLM Agent EvaluationLLM Agent Workflow Optimization

  8. From AGI to ASI

    Jun 10, 2026Tim Genewein, Matija Franklin, Alexander Lerchner +11Self-Improving AgentsRecursive Self-Improvement

  9. From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Design

    Jun 8, 2026Dun Li, Jiatao Li, Hongzhi LiLLM Agent Self-ImprovementSelf-Improving Agents

  10. What Does a System Modify When It Modifies Itself?

    Mar 29, 2026Florentin KochRecursive Self-Improvement

  11. A Theory of LLM Information Susceptibility

    Mar 24, 2026Zhuo-Yang Song, Hua Xing ZhuLarge Language Model-Guided OptimizationLanguage Model Scaling

  12. Hyperagents

    Mar 19, 2026Jenny Zhang, Bingchen Zhao, Wannan Yang +5Self-Improving AgentsRecursive Self-Improvement

  13. SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement

    Mar 6, 2026Subramanyam Sahoo, Aman Chadha, Vinija Jain +1LLM Safety AlignmentLLM Self-Refinement

  14. SGM: A Statistical Godel Machine for Risk-Controlled Recursive Self-Modification

    Oct 11, 2025Xuening Wu, Shenqin Yin, Yanlan Kang +4Automated Machine LearningSelf-Improving Agents