SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. ScienceBuddy supports researchers in carrying out scientific tasks while transforming their requests, feedback, and execution evidence into tasks and evaluation rubrics for continual learning. At its core is recursive-in-recursive self-improvement, a paradigm that couples harness evolution with model reinforcement learning: the inner recursion improves the harness with the model fixed, while the outer recursion trains the

Read original source ↗ Open in workspace

recordType

paper

region

Global