method · first seen 24 Oct 2026
self-improving research agents
LLM agent systems that iteratively improve their own research process and tools from feedback.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top PlayersPapers · 24 Oct 2026 · Changlian Ma, Limin Wang
Latest sources
- Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top PlayersPapers · 24 Oct 2026 · Changlian Ma, Limin Wang