Megadose AI progress, ranked and analyzed.

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

· ArXiv · AI/CL/LG ·
ScienceBuddy turns researcher interactions into training tasks and rubrics for agents that keep improving inside the workflow.

The paper introduces an interactive scientific research workspace built around “recursive-in-recursive” self-improvement. Its inner loop refines the evaluation harness while the model stays fixed; its outer loop trains the model using that improved harness. The authors describe case studies covering researcher interaction, harness refinement, and model learning across four scientific task families. ArXiv · AI/CL/LG's note

score 6

Categories: Research, Products to Try