recursive-self-improvement

awesome-rsi

+201

A curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.

Raven

+134

The Harness of Harnesses • built for RSI: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

ScienceBuddy

+42

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

rsi-gear/gear

+17

Gear (General Evolution Architecture) is RSI infrastructure for AI agents. Use Gear to refine agent harnesses.

RSI-Jev

+8

Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.

RSI-Exam

+9

RSI-Exam: Measuring Recursive Self-Improvement on Long-Horizon, Executable Research Tasks · Discord https://discord.gg/FBzhepyE

aibuildai-llm-posttrain-agent

+3

AIBuildAI LLM-Post-Train Agent: a recursive self-improving (RSI) agent for autonomous LLM post-training

Hyra-results

+3

Research artifacts from Hyra (/ˈhaɪ.rɑː/)

Awesome-AI4AI

+2

AI4AI Survey: can AI reliably improve AI? 223 papers on long-horizon agents, benchmarks, harness design, and recursive self-improvement · updated weekly