Agent Recursive Self-Improvement Experiment
markjeffrey · x · 2026-07-15
The Weco team reports its first recursive self-improvement (RSI) experiment on "auto-research auto-research agent": letting an agent work for 8 consecutive days to automatically research and rewrite another agent's harness (the execution/inference layer around the model).
They claim the auto-optimized harness outperforms the team's two-year manual tuning on held-out benchmarks. The core takeaway: AI progress may be entering a phase of acceleration through self-improvement.
Related event: AIDE² Self-Improvement Run Beats 2 Years of Manual Tuning(12 posts)→
More from coding & agent
- Design Is Becoming Game Dev: Build Your Own Tools With AI as the Executor — hewarsaber · 2026-10-27
- Dev turns DJI Mavic into local AI security drone built with Opus 5.5 — alexcovo_eth · 2026-10-27
- Microsoft Research: ForkPilot cuts long-horizon agent compute by up to 59% — EliasEskin · 2026-10-27
- Cursor launches Agent SDK: agents as code with Markdown prompts and TypeScript tools — soleio · 2026-10-27
- Vibecheck, the 'usable formal methods' hackathon, sells out two floors in SF — spikedoanz · 2026-10-27
- How do you verify AI agent outputs beyond unit tests and LLM-as-judge? — Practical_Green5775 · 2026-10-27