TestGRAD: Evolving Test Suites via Failure Pattern Momentum for SWE-Agent Ensemble
cs.SE, cs.AI
Submitted: 2026-10-07
Updated: 2026-10-07
Sources
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling
- AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Lost in the Middle: How Language Models Use Long Contexts
- SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
- DiffSpec: Differential Testing with LLMs using Natural Language Specifications and Code Artifacts
- Large Language Models are not Fair Evaluators
- OpenHands: An Open Platform for AI Software Developers as Generalist 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