SkillZip Pro: Execution-Aware Dynamic Compression of Progressively Loaded Skills for Self-Evolving Agents

arXiv:2608.30785 · cs.AI · Submitted 2026-08-31 · Read on arXiv

cs.AI

Submitted: 2026-08-31

Updated: 2026-08-31

Code: https://github.com/yutou520131/SkillZip-Pro

Terminology

• Benchmark — 34× in this paper · explained in 2 episodes
• Redundancy — 19× in this paper · explained in 2 episodes
• Accuracy — 14× in this paper · explained in 1 episode
• Verification — 14× in this paper · explained in 2 episodes
• Fidelity — 10× in this paper · explained in 2 episodes
• Provenance — 10× in this paper · explained in 3 episodes
• Trace — 10× in this paper · explained in 2 episodes
• Agent Skills — 7× in this paper · explained in 1 episode
• Ablation — 5× in this paper · explained in 1 episode
• Regret — 5× in this paper · explained in 3 episodes
• Self-Evolving Agents — 4× in this paper · explained in 2 episodes
• Scaffolding — 3× in this paper · explained in 3 episodes
• Agent Harness — 2× in this paper · explained in 2 episodes
• Agentic Coding — 2× in this paper · explained in 1 episode
• Adaptability — 1× in this paper · explained in 1 episode
• Agentic Evaluation — 1× in this paper · explained in 1 episode
• Commentary — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Progressive Disclosure — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• SkillGrad: Optimizing Agent Skills Like Gradient Descent
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills
• Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
• Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents
• SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
• LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
• Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
• A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
• LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
• SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
• SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
• SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

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