mlsanityData to 14 Oct 2026

RSI-Anything: Unlocking Recursive Self-Improvement with World Models

arXiv 2610.13912 ↗First posted 9 Oct 2026cs.CLcited by 0

On the map: World models → World models for language agents also fits: Latent dynamics models and model-based RL

Abstract (arXiv)

Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve. We introduce RSI-Anything, a domain-general framework built on JEPA-Anything that uses predictive world models to guide action and learning-data selection. Observed feedback drives policy or workflow improvement and conditional world-model adaptation, while component and compatibility checks govern the retention of updated policy-model pairs. Across diverse computational and scientific domains, RSI-Anything demonstrates substantial gains. In code repair, with the coder fixed, success increases from 26.3% with a static verifier to 29.2% through predictive selection and 31.2% after world-model adaptation, at comparable test usage. Graphical user interface (GUI) evaluations showed higher task completion, while average actions decrease by 39.4%. Across five successive policy versions, laboratory-planning scores more than double from 21.80% to 46.01%. In reaction optimization, RSI-Anything achieves 96.15% mean best observed yield versus 82.16% for Bayesian optimization under the same 40-experiment budget. An end-to-end immune-science application further connects workflow evolution and predictive modeling with therapeutic hypothesis generation. These results demonstrate how predictive world models and retained system updates enable recursive improvement across diverse environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 34 of its 53 references that are in the map. First posted on arXiv 9 Oct 2026.

Builds on

34 of 53 references.

References · 34

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  7. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  8. 2018World Modelscited by 1,513
  9. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  10. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  11. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  12. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,195
22 more
  1. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
  2. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  3. 2021Measuring Coding Challenge Competence With APPScited by 902
  4. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  5. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 809
  6. 2024Genie: Generative Interactive Environmentscited by 747
  7. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  8. 2024Revisiting Feature Prediction for Learning Visual Representations from Videocited by 531
  9. 2023Reinforced Self-Training (ReST) for Language Modelingcited by 500
  10. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 356
  11. 2018Reinforcement Learning on Web Interfaces Using Workflow-Guided Explorationcited by 284
  12. 2026OpenClaw-RL: Train Any Agent Simply by Talkingcited by 90
  13. 2025A Self-Improving Coding Agentcited by 79
  14. 2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoningcited by 75
  15. 2025Co-Evolving LLM Coder and Unit Tester via Reinforcement Learningcited by 56
  16. 2025GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulatorscited by 42
  17. 2026RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL Systemcited by 24
  18. 2026Recursive self-improvement of AI research agentscited by 11
  19. 2026Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnessescited by 9
  20. 2026ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agentscited by 7
  21. 2026JEPA-Anything: Learning Predictive Models across Different Worldscited by 3
  22. 2026An immune world model for multiscale forecasting and therapeutic hypothesis generationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026RSIGym: A Flexible Environment for Recursive Self-Improvement
  2. 2026The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
  3. 2026ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
  4. 2026From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement
  5. 2026RSI-Forge: From Research Papers to Environments for Recursive Self-Improvement
  6. 2026COEVO: Co-Evolving Context and Parameters for Recursive Self-Improvement
  7. 2026R2 Flow: Recursive Self-Improvement via Recursive Skill Evolution
  8. 2026Harness^2: Recursive Agent Harnessing for an Open World