DrugHarness: An Evolvable Agent Harness for Computational Drug Discovery
[Sztuczna inteligencja] Autorzy: Yuxing Chen, Zhisheng Zhang, Cheng Tang i 20 więcej
Computational drug discovery requires agents to compose scientific operations and adapt to changing evidence and constraints. Here we introduce DrugHarness, an evolvable agent harness coupling composable scientific execution with conditional skill induction. Its environment integrates over 80 scientific operations, biomedical resources and task-specific code, preserving associations among candidates, results and artifacts. From execution trajectories and outcome feedback, DrugHarness induces action hypotheses with observable applicability conditions, recommended actions and supporting evidence. An independent review agent evaluates candidate skills derived from these hypotheses through source verification and, when needed, targeted execution trials. Admitted skills guide subsequent tasks and are revised through feedback. Evaluation on MolBench and SMDD-Bench demonstrates capabilities in…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja