Model Releases
ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences
arXiv:2610.08691v1 Announce Type: new Abstract: Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent program-level improvements, and exi
arXiv:2610.08691v1 Announce Type: new Abstract: Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent program-level improvements, and existing evaluations do not examine this process across sequential tasks in both the natural and social sciences. We formalize ScienceClaw as fixed-parameter program self-evolution that unifies task solving, scientific verification, and program updates. ScienceClaw-Eval spans 23 disciplines and measures scientific correctness, evolutionary gain, retention, cross-dataset transfer, and evolution cost through sequential streams and independent reset evaluation. Our framework repairs executable workflows through multi-turn interaction, converts re-execution-verified failure--success trajectories into linked Skill and Operator candidates, and retains an update only when source-task replay reproduces the repair and independent scientific tasks improve. Code is available at https://github.com/beita6969/ScienceClaw.
Related
- Semantic Projection for Continual Self-Evolution of Language Agents
- Agentic self-driving microscopy benchmarks support qualification but do not necessarily generalize to unseen tasks
- SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition
- SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
Source: arXiv cs.AI | 2026-10-07