CODESKILL: Learning Self-Evolving Skills for Coding Agents

arXiv:2605.25430 · cs.AI · Submitted 2026-05-25 · Read on arXiv

cs.AI

Submitted: 2026-05-25

Updated: 2026-09-25

Terminology

• Benchmark — 20× in this paper · explained in 2 episodes
• Reinforcement Learning — 15× in this paper · explained in 4 episodes
• Alignment — 13× in this paper · explained in 1 episode
• Agent Skills — 7× in this paper · explained in 1 episode
• GRPO — 5× in this paper · explained in 6 episodes
• Procedural Knowledge — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Verifier — 4× in this paper · explained in 2 episodes
• Action Space — 3× in this paper · explained in 1 episode
• Generalization — 3× in this paper · explained in 13 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Provenance — 2× in this paper · explained in 4 episodes
• Self-Evolving Agents — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Actionability — 1× in this paper · explained in 3 episodes
• Agentic Problem — 1× in this paper · explained in 1 episode
• Agentic Workflows — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• EvoSkill: Automated Skill Discovery for Multi-Agent Systems
• SWE-Exp: Experience-Driven Software Issue Resolution
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• Memp: Exploring Agent Procedural Memory
• SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
• ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning
• SkillNet: Create, Evaluate, and Connect AI Skills
• Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
• SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
• Qwen3 Technical Report
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Structurally Aligned Subtask-Level Memory for Software Engineering Agents
• EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
• SWE-smith: Scaling Data for Software Engineering Agents
• AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
• CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
• Dynamic Dual-Granularity Skill Bank for Agentic RL
• Reinforcement Learning for Self-Improving Agent with Skill Library

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