How Much Skill Orchestration Can LLM Agents Compile Away? Execution-Grounded Specialization for Token-Efficient Skill Use
cs.SE, cs.AI, cs.CL, cs.LG
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
- SkillDroid: Compile Once, Reuse Forever
- SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
- SIGIL: Compiling Agent Skills into Typed Harnesses
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows
- SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
- Kimi K3: Open Frontier Intelligence
- Meta-Harness: End-to-End Optimization of Model Harnesses
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
- SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
- LLM-as-Code: Agentic Programming for Agent Harness
- WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- SkillEvolver: Skill Learning as a Meta-Skill
- CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
- SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters