QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization
cs.SE, cs.LG
Submitted: 2026-04-07
Updated: 2026-11-14
Code: https://github.com/steveicarus/iverilog
Terminology
Sources
- Evaluating Large Language Models Trained on Code
- SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning
- A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System
- VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool
- Qwen2.5-Coder Technical Report
- OctoPack: Instruction Tuning Code Large Language Models
- GPT-4 Technical Report
- Automatic Program Repair with OpenAI's Codex: Evaluating QuixBugs
- Towards LLM-based Root Cause Analysis of Hardware Design Failures
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- Gemini: A Family of Highly Capable Multimodal Models
- DebugBench: Evaluating Debugging Capability of Large Language Models
- RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models
- HLSDebugger: Identification and Correction of Logic Bugs in HLS Code with LLM Solutions
- Agentless: Demystifying LLM-based Software Engineering Agents
- Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation
- LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs
- Aligning the Objective of LLM-based Program Repair
- HDLdebugger: Streamlining HDL debugging with Large Language Models
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