SkillsBench
Emerging15papers using it
2026first seen
Papers using SkillsBench (15)
- MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and EvaluationGraph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent SkillsDomain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-TeamingSkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill RevisionSkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at ScaleAIP: A Graph Representation for Learning and Governing Agent SkillsWhat Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model AgentsSkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-RefinementSkillJuror: Measuring How Agent Skill Organization Changes Runtime BehaviorSkillsInjector: Dynamic Skill Context Construction for LLM AgentsSkillMOO: Multi-Objective Optimization of Agent Skills for Software EngineeringSkillSmith: Compiling Agent Skills into Boundary-Guided Runtime InterfacesCoevoskills: Self-evolving Agent Skills Via Co-evolutionary VerificationSkCC: Portable and Secure Skill Compilation for Cross-Framework LLM AgentsClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation