ScienceBuddy releases a self-improving scientific-agent workspace

ScienceBuddy turns researcher requests, feedback and execution evidence into new tasks and evaluation rubrics. Its inner loop edits the agent harness while holding the model fixed; an outer loop reinforces the model under the improved harness. The authors release the workspace and code with case studies across four scientific task families. The evidence remains a small author-run set rather than an independent productivity study.

For teams building research agents, this is a concrete design for learning from normal interactive use without mixing harness changes and model updates into one opaque loop. Trial the trace-to-rubric workflow before adopting recursive model training. Keep human review and held-out evaluations because user feedback can encode local preferences or mistakes.