arxiv.orgpaperScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
ScienceBuddy is an interactive scientific research workspace with continually improving agents that turn researcher requests, feedback, and execution evidence into training tasks and evaluation rubrics. Its core contribution is "recursive-in-recursive self-improvement," where an inner recursion evolves the agent harness with the model fixed, and an outer recursion trains the model via RL under the improved harness, with each shaping the other over time. The paper presents case studies across four scientific task families and releases the system as a research product.
TL;DR A scientific research agent that recursively co-evolves its harness and its model via RL, released as an interactive research product.
Technologies named here
- ScienceBuddy
Techniques named here
- Recursive-in-recursive self-improvement
Related in agents