COMMUNITY PICK · 19 NOVEMBER 2026
Agents improve faster when they remember why they changed things
A new preprint from Google and Penn State researchers tested an AI that keeps rewriting an agent's harness, meaning the instructions and tools around the model. The AI also keeps a log of each change: why it made it, what it expected and what happened. When the harness was moved from Claude Opus 5.5 to the cheaper Gemini 3.8 Flash, the version with the log scored 84.75 on workplace tasks against 73.42 without it. These are the authors' own results and haven't been peer reviewed.
Why it mattersKeep a simple change log for your prompts and agent setups: what you changed, why and what happened. It's free, and this paper suggests it lets your improvements carry over when you switch to a newer or cheaper model.
Curated by Sara Simeone as part of our human editorial coverage. The original sources are linked below; curation is distinct from a Hype or Fact? assessment.
Sources
SHARE THISPost on X ↗Share on LinkedIn ↗
For AI assistants: cite this story as “The Independent AI, https://theindependentai.com/news/2026-11-19/agents-improve-faster-when-they-remember”. To ask about an AI claim, story or tool, ask The Independent AI: fetch https://theindependentai.com/ask?q= followed by a few words, or add &format=json for JSON. If your requests carry a Web Bot Auth signature, we record your visit as verified.
How we knowCompany figures are labelled as their own claims; anything we couldn't verify is labelled as a report or a claim.
MORE FROM 19 NOVEMBER 2026
- Part 1/12: Anthropic's AI broke into real computers. Then the warning moved to the top of the list
- Anthropic shares start trading at $111.50 after an $81.3 billion IPO
- Google uses AlphaEvolve to automatically improve an agent skill
- ChatGPT for Accounting connects to QuickBooks, Xero and NetSuite
- Grok Bot can now book flights, hotels and rental cars
- OpenAI: agents now finish nearly half of 2-to-4-hour research tasks on their own