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
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11