Finding the Pivots to Repair Broken Source-Test Evolution Using LLMs
cs.SE
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/alibaba/spring-ai-alibaba
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning
- A Study on Thinking Patterns of Large Reasoning Models in Code Generation
- Exploring the Integration of Large Language Models in Industrial Test Maintenance Processes
- What Builds Effective In-Context Examples for Code Generation?
- Testora: Using Natural Language Intent to Detect Behavioral Regressions
- Breaking, Stale, or Missing? Benchmarking Coding Agents on Project-Level Test Evolution
- Unit Test Case Generation with Transformers and Focal Context
- TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution
- Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning
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