{"total":56,"rows":[{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2307.14936","title":"PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback","created":"2023-07-27","cited_by_count":69,"area":null},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62,"area":null},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53,"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":"2410.17621","title":"Process Supervision-Guided Policy Optimization for Code Generation","created":"2024-10-23","cited_by_count":26,"area":null},{"id":"2403.03894","title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","created":"2024-03-06","cited_by_count":23,"area":null},{"id":"2502.01715","title":"Process-Supervised Reinforcement Learning for Code Generation","created":"2025-02-03","cited_by_count":22,"area":null},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2411.11504","title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","created":"2024-11-18","cited_by_count":16,"area":null},{"id":"2407.18271","title":"Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning","created":"2024-07-21","cited_by_count":15,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","cited_by_count":11,"area":null},{"id":"2605.07442","title":"GameGen-Verifier: Parallel Keypoint-Based Verification for LLM-Generated Games via Runtime State Injection","created":"2026-05-08","cited_by_count":11,"area":null},{"id":"2410.23074","title":"Multi-Programming Language Sandbox for LLMs","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2502.13921","title":"Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis","created":"2025-02-19","cited_by_count":10,"area":null},{"id":"2407.12022","title":"ITERTL: An Iterative Framework for Fine-tuning LLMs for RTL Code Generation","created":"2024-06-28","cited_by_count":9,"area":null},{"id":"2603.15611","title":"Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning","created":"2026-03-16","cited_by_count":8,"area":null},{"id":"2508.05242","title":"CodeBoost: Boosting Code LLMs by Squeezing Knowledge from Code Snippets with RL","created":"2025-08-07","cited_by_count":7,"area":null},{"id":"2410.21236","title":"Flaming-hot Initiation with Regular Execution Sampling for Large Language Models","created":"2024-10-28","cited_by_count":6,"area":null},{"id":"2505.11480","title":"SuperCoder: Assembly Program Superoptimization with Large Language Models","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2504.07527","title":"Supervised Optimism Correction: Be Confident When LLMs Are Sure","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2601.08734","title":"TerraFormer: Automated Infrastructure-as-Code with LLMs Fine-Tuned via Policy-Guided Verifier Feedback","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2412.13464","title":"GenX: Mastering Code and Test Generation with Execution Feedback","created":"2024-12-18","cited_by_count":4,"area":null},{"id":"2503.18460","title":"ModiGen: A Large Language Model-Based Workflow for Multi-Task Modelica Code Generation","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2504.00019","title":"ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2510.19296","title":"QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2605.02944","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2510.04097","title":"WebRenderBench: Enhancing Web Interface Generation through Layout-Style Consistency and Reinforcement Learning","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2601.13097","title":"RM -RF: Reward Model for Run-Free Unit Test Evaluation","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2602.23407","title":"Learning to Generate Secure Code via Token-Level Rewards","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2605.25252","title":"Quantifying Empirical Compute-Supervision Tradeoffs in RLVR","created":"2026-05-24","cited_by_count":2,"area":null},{"id":"2608.30005","title":"Small Language Models as Judges for Rubric-Based Reinforcement Learning","created":"2026-08-30","cited_by_count":2,"area":null},{"id":"2406.04710","title":"Morescient GAI for Software Engineering (Extended Version)","created":"2024-06-07","cited_by_count":1,"area":null},{"id":"2406.10305","title":"Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2508.03487","title":"BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.25243","title":"Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2601.00575","title":"InfoSynth: Information-Guided Benchmark Synthesis for LLMs","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2602.12049","title":"Improving HPC Code Generation Capability of LLMs via Online Reinforcement Learning with Real-Machine Benchmark Rewards","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2504.12365","title":"Themisto: Jupyter-Based Runtime Benchmark","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2602.20333","title":"DMCD: Semantic-Statistical Framework for Causal Discovery","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2605.11680","title":"ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.04577","title":"Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.21069","title":"From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.26457","title":"DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2607.27271","title":"RLPF: Reinforcement Learning from Performance Feedback for Code Generation","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.01422","title":"From Rollouts to Recipes: Self-Contained Post-Training for LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.03894","title":"CROCODIL: Cross-Model Code Editing with LLMs","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.33796","title":"RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34717","title":"ReMCTS: Reflection-Enhanced Monte Carlo Tree Search for Code Generation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39383","title":"From Search to Signal: Online Post-Training in Automatic Heuristic Design","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.05966","title":"HuatuoGPT-3: RL-Only Domain Adaptation from Base Models","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.14573","title":"Learning after Execution with Action-Specific Credit","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}