SkillFocus: Evolving Agent Skills via Capability Decomposition
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
- SkillCommit: Evolving Agent Skills through Behaviorally Validated Scope Expansion
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support
- Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
- SkillGrad: Optimizing Agent Skills Like Gradient Descent
- EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- Meta Context Engineering via Agentic Skill Evolution
- Instruction-Following Evaluation for Large Language Models
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