When Does a Skill Add Value? Task-Conditional Gain Prediction for Selective Skill Use
cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- A Large Scale Benchmark for Individual Treatment Effect Prediction and Uplift Modeling
- SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
- CARROT: A Cost Aware Rate Optimal Router
- Skill Retrieval Augmentation for Agentic AI
- Skill Coverage: A Test Adequacy Metric for Agent Skills
- SkillTester: Benchmarking Utility and Security of Agent Skills
- Efficient Evaluation of LLM Performance with Statistical Guarantees
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- SkillRouter: Skill Routing for LLM Agents at Scale
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection