Microsoft: clearing chat history boosts AI agent results up to 66% with Fork-and-Flush
The Decoder · rss · 2026-10-13
Microsoft researchers found autonomous AI agents get trapped in 'idea basins' — local solution regions they can't escape — caused by their ever-growing chat context. Their 'Fork-and-Flush' method clears the chat history while keeping the workspace, letting agents restart with accumulated results but without conversational baggage. On the same compute budget, this yields up to 66% better results. A zero-cost, immediately actionable insight for agent engineering: context isn't the longer the better.
More from coding & agent
- Daniel Jeffries: only ~2% can actually use AI agents, mass adoption is 10-20 years away — Dan_Jeffries1 · 2026-10-13
- Fully local AI short film mimics Wes Anderson style with a detailed open pipeline — Mist3r-Robot · 2026-10-13
- Controlling his Mac's terminal from a phone via t3 code beta while waiting at speech therapy — NERDDISCO · 2026-10-13
- LLM cache verifier drift: reject-only calibration tripled error rate; 5% audits fix it — Reasonable_Royal_621 · 2026-10-13
- A style guide for making Claude-like models write normally, and its linguistic traps — gleech · 2026-10-13
- Open-source desktop agent dodaios runs local Qwen models via ollama — and shows where 16GB models fail — InternationalGap3698 · 2026-10-13