AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems
cs.SE, cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/AiHubCN/Awesome-Chinese-LLM
Terminology
Sources
- Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reports
- From Question Answering to Task Completion: A Survey on Agent System and Harness Design
- SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
- R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Large Language Model-Based Agents for Software Engineering: A Survey
- Code as Agent Harness
- Training Software Engineering Agents and Verifiers with SWE-Gym
- Are LLMs Correctly Integrated into Software Systems?
- Agent Workflow Memory
- Agentless: Demystifying LLM-based Software Engineering Agents
- FairMedQA: Benchmarking Bias in Large Language Models for Medical Question Answering
- Large Language Models for Robotics: A Survey
- Understanding Bugs in Modern Agentic Frameworks: A Study of Symptoms, Root Causes, and Triggering Conditions
- Where LLM Agents Fail and How They can Learn From Failures
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