Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents
- GitSkills: A Dataset of Agent Skills on GitHub
- SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale
- SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
- Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution
- SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
- Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents
- Skill Retrieval Augmentation for Agentic AI
- WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
- Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
- SkillGrad: Optimizing Agent Skills Like Gradient Descent
- GraSP: Graph-Structured Skill Compositions for LLM Agents
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems