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

arXiv:2610.13912 · cs.CL · Submitted 2026-10-09 · Read on arXiv

cs.CL

Submitted: 2026-10-09

Updated: 2026-10-09

Comments: Code: https://github.com/Gen-Verse/RSI-Anything

Code: https://github.com/Gen-Verse/RSI-Anything

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• World Model — 1× in this paper · explained in 7 episodes

Sources

• Training Verifiers to Solve Math Word Problems
• Reflexion: Language Agents with Verbal Reinforcement Learning
• Reinforced Self-Training (ReST) for Language Modeling
• World Models
• JEPA-Anything: Learning Predictive Models across Different Worlds
• Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
• Revisiting Feature Prediction for Learning Visual Representations from Video
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• An immune world model for multiscale forecasting and therapeutic hypothesis generation
• Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
• Measuring Coding Challenge Competence With APPS
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration
• OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
• RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
• A Self-Improving Coding Agent
• Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
• Recursive self-improvement of AI research agents
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering