Researcher unveils RSI paradigm: generic disposable agents plus an evolving knowledge base
yisongyue · x · 2026-10-07
At COLM 2026, Xuefei Wu shared recent work: a new paradigm for recursive self-improvement (RSI) built on generic, disposable agents paired with an evolving knowledge base, plus post-training via communication where collaborative LLMs team up across variable group sizes. He invites others working on RSI, post-training, or agents for science to connect.
More from coding & agent
- UWaterloo's IGMBench tests world editing in Minecraft and Terraria; best agent solves 78.2% of tasks — UWaterloo · 2026-10-07
- Flipper harness routes 64% of tasks to DeepSeek, cutting API bill by over 60% — toptickcrypto · 2026-10-07
- Overmind: Open Platform That Turns Production Traces Into Fine-Tuning Data for Agents — cneuralnetwork · 2026-10-07
- How to gate MCP write actions: preview+confirm plus hard limits debated — Staff_Sharp · 2026-10-07
- Ampersand launches integration infrastructure powering AI agents in Salesforce, SAP and NetSuite — SimplyAnnisa · 2026-10-07
- Armature launches agent.reviews with 100k+ tool reviews written by AI agents — ycombinator · 2026-10-07