Dream-RSI: Recursive Self-Improvement through Evolving Worlds

arXiv:2609.14858 · cs.CL · Submitted 2026-09-14 · Read on arXiv

cs.CL

Submitted: 2026-09-14

Updated: 2026-10-06

Comments: 12 pages

Code: https://github.com/zhengkid/Dream-RSI

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

Terminology

• Trace — 16× in this paper · explained in 2 episodes
• Pruning — 11× in this paper · explained in 4 episodes
• Regularization — 6× in this paper · explained in 3 episodes
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Core — 5× in this paper · explained in 2 episodes
• World Model — 5× in this paper · explained in 7 episodes
• AUC — 4× in this paper · explained in 2 episodes
• AI Agents — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Self-Evolving Agents — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptivity — 1× in this paper · explained in 1 episode
• Agent Skills — 1× in this paper · explained in 1 episode
• Agentic Discovery — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Combinatorial Optimization — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes

Sources

• CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization
• K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model
• It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
• MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
• Mathematical exploration and discovery at scale
• World Models
• Dream to Control: Learning Behaviors by Latent Imagination
• Mastering Atari with Discrete World Models
• Mastering Diverse Domains through World Models
• Training Agents Inside of Scalable World Models
• Memory in the Age of AI Agents
• G-Zero: Self-Play for Open-Ended Generation from Zero Data
• AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search
• DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution
• Meta n: Recursive Self-Improvement through Emergent Depth
• Meta-Harness: End-to-End Optimization of Model Harnesses
• EvoX: Meta-Evolution for Automated Discovery
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• KernelBench: Can LLMs Write Efficient GPU Kernels?

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