Certified Long-Horizon Code Agent Evolution via Validation-Gated Skill Optimization

arXiv:2609.32990 · cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/SWE-agent/mini-swe-agent

Terminology

• Ablation — 17× in this paper · explained in 1 episode
• Adaptation — 15× in this paper · explained in 1 episode
• Agent Skills — 5× in this paper · explained in 1 episode
• Consistency — 5× in this paper · explained in 3 episodes
• GRPO — 3× in this paper · explained in 6 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 2× in this paper
• International Conference on Machine Learning — 2× in this paper
• Theoretical Guarantees — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• EvoSkill: Automated Skill Discovery for Multi-Agent Systems
• Evolving Excellence: Automated Optimization of LLM-based Agents
• Training-Free Group Relative Policy Optimization
• SWE-Exp: Experience-Driven Software Issue Resolution
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Memp: Exploring Agent Procedural Memory
• EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
• Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement
• SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support
• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
• ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
• Automatic Prompt Optimization with "Gradient Descent" and Beam Search
• A Self-Improving Coding Agent
• SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
• Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
• Voyager: An Open-Ended Embodied Agent with 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
• 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