On the Limits of Execution Traces for Repairing Assertion Failures in LLM-Generated Code
cs.SE, cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/TheOpenSI/SYNKRASIS
Terminology
Sources
- Evaluating Large Language Models Trained on Code
- Large Language Model Guided Self-Debugging Code Generation
- Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
- Program Synthesis with Large Language Models
- TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code
- From Guessing to Seeing: Enhancing LLM-Based Program Repair via Trace-Guided Multi-strategy Debate
- DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information
- Solving math word problems with process- and outcome-based feedback
- Qwen2.5 Technical Report
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