Automated Code Efficiency Optimization via Agent Skill Mining
cs.SE, cs.CL
Submitted: 2026-03-29
Updated: 2026-11-16
Terminology
Sources
- Test vs Mutant: Adversarial LLM Agents for Robust Unit Test Generation
- Evaluating Large Language Models Trained on Code
- SWE-Exp: Experience-Driven Software Issue Resolution
- Supersonic: Learning to Generate Source Code Optimizations in C/C++
- Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
- Search-Based LLMs for Code Optimization
- In Line with Context: Repository-Level Code Generation via Context Inlining
- Zero-Shot Vulnerability Detection in Low-Resource Smart Contracts Through Solidity-Only Training
- Controlled Self-Evolution for Algorithmic Code Optimization
- EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
- ECO: Enhanced Code Optimization via Performance-Aware Prompting for Code-LLMs
- CADET: Debugging and Fixing Misconfigurations using Counterfactual Reasoning
- SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- Evaluating Language Models for Efficient Code Generation
- SWE-QA: Can Language Models Answer Repository-level Code Questions?
- EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
- Toolformer: Language Models Can Teach Themselves to Use Tools
- From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
- CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
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