Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities
cs.SE
Submitted: 2025-09-30
Updated: 2026-10-29
Comments: This paper is accepted to COLM 2026
Code: https://github.com/SWE-agent/mini-swe-agent
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Detecting Language Model Attacks with Perplexity
- RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
- Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks
- Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling
- Challenges and Paths Towards AI for Software Engineering
- LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead
- MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistants
- Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code
- From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future
- AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development Automation
- Certifying LLM Safety against Adversarial Prompting
- Large Language Model-Based Agents for Software Engineering: A Survey
- MarsCode Agent: AI-native Automated Bug Fixing
- An Empirical Study on LLM-based Agents for Automated Bug Fixing
- Adversarial Bug Reports as a Security Risk in Language Model-Based Automated Program Repair
- AutoCodeRover: Autonomous Program Improvement
- Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
- Agentless: Demystifying LLM-based Software Engineering Agents
- SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
- OrcaLoca: An LLM Agent Framework for Software Issue Localization
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