{"total":22,"rows":[{"id":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107,"area":null},{"id":"2406.01422","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","created":"2024-06-03","cited_by_count":58,"area":null},{"id":"2405.17503","title":"Code Repair with LLMs gives an Exploration-Exploitation Tradeoff","created":"2024-05-26","cited_by_count":51,"area":null},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46,"area":null},{"id":"2405.18649","title":"LeDex: Training LLMs to Better Self-Debug and Explain Code","created":"2024-05-28","cited_by_count":40,"area":null},{"id":"2507.05687","title":"AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs","created":"2025-07-08","cited_by_count":40,"area":null},{"id":"2408.08343","title":"API-guided Dataset Synthesis to Finetune Large Code Models","created":"2024-08-15","cited_by_count":11,"area":null},{"id":"2504.14640","title":"Risk Assessment Framework for Code LLMs via Leveraging Internal States","created":"2025-04-20","cited_by_count":9,"area":null},{"id":"2504.18050","title":"Validating Network Protocol Parsers with Traceable RFC Document Interpretation","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2510.26101","title":"QCoder Benchmark: Bridging Language Generation and Quantum Hardware through Simulator-Based Feedback","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2504.13515","title":"Large Language Models for Validating Network Protocol Parsers","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2604.10508","title":"How Many Tries Does It Take? Iterative Self-Repair in LLM Code Generation Across Model Scales and Benchmarks","created":"2026-04-12","cited_by_count":5,"area":null},{"id":"2410.11096","title":"SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2606.31511","title":"Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models","created":"2026-06-30","cited_by_count":4,"area":null},{"id":"2604.00491","title":"Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2606.04847","title":"MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2607.12962","title":"Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2409.05177","title":"Insights from Benchmarking Frontier Language Models on Web App Code Generation","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2604.21950","title":"Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.03852","title":"FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2406.14867","title":"Investigating the Transferability of Code Repair for Low-Resource Programming Languages","created":"2024-06-21","cited_by_count":0,"area":null},{"id":"2608.04439","title":"ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}