Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules
cs.SE, cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/samugit83/cortex
Terminology
Sources
- SWE-Bench+: Enhanced Coding Benchmark for LLMs
- On Randomness in Agentic Evals
- Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding
- DemoEvolve: Demonstration-Guided Harness Evolution under Sparse Feedback
- HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
- Skill Following: Evaluating Actual Skill Use in Retrieval-Enabled LLM Agents
- LiteEvo: Automated, Cost-Efficient Harness Evolution for Generalization to Unseen Tasks
- DeltaSelect: Affordable A/B Testing for Coding Agents
- An Empirical Study of Harness Design for Coding Agents
- SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
- Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?
- Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses?
- Do Personalized Skills Help Coding Agents? An Empirical Study of Developer Interaction Histories
- Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows
- REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage
- EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?
- Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories
- Skill Issue: Lessons from Optimizing Repository SKILLs for Coding Agents
- What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills
- Beyond Endpoint Performance: Process-Level Evaluation of Self-Evolving Agents
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties