Poison Valleys: Diagnosing Path-Dependent Failure in LLM Code Repair

cs.SE, cs.AI

Submitted: 2026-10-15

Updated: 2026-10-15

Comments: Accepted to Interpreting Agent Behavior (IAB): The First Workshop on Human-Centered Interpretation for Understanding Agents, Humans, and Interaction (NeurIPS 2026 workshop); 22 pages; code, data, and demo: https://poisonvalleys.org

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

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