{"total":77,"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":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247,"area":"lr"},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151,"area":"lr"},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2502.01718","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","created":"2025-02-03","cited_by_count":93,"area":"lr"},{"id":"2505.15201","title":"Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems","created":"2025-05-21","cited_by_count":87,"area":"deeprl"},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83,"area":null},{"id":"2505.20732","title":"SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution","created":"2025-05-27","cited_by_count":73,"area":"agents"},{"id":"2506.03136","title":"Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning","created":"2025-06-03","cited_by_count":56,"area":null},{"id":"2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","created":"2024-12-18","cited_by_count":50,"area":"lr"},{"id":"2404.00725","title":"The Larger the Better? Improved LLM Code-Generation via Budget Reallocation","created":"2024-03-31","cited_by_count":43,"area":null},{"id":"2508.03501","title":"Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning","created":"2025-08-05","cited_by_count":36,"area":"lr"},{"id":"2403.16443","title":"CodeS: Natural Language to Code Repository via Multi-Layer Sketch","created":"2024-03-25","cited_by_count":28,"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":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"area":null},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2502.01715","title":"Process-Supervised Reinforcement Learning for Code Generation","created":"2025-02-03","cited_by_count":22,"area":null},{"id":"2507.21990","title":"ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge","created":"2025-07-29","cited_by_count":20,"area":"lr"},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"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":"2405.16661","title":"RLSF: Fine-tuning LLMs via Symbolic Feedback","created":"2024-05-26","cited_by_count":14,"area":"alignment"},{"id":"2405.17057","title":"ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation","created":"2024-05-27","cited_by_count":14,"area":"lr"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2508.18106","title":"A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code","created":"2025-08-25","cited_by_count":14,"area":null},{"id":"2406.02470","title":"Meta-Designing Quantum Experiments with Language Models","created":"2024-06-04","cited_by_count":12,"area":null},{"id":"2505.22704","title":"Training Language Models to Generate Quality Code with Program Analysis Feedback","created":"2025-05-28","cited_by_count":12,"area":null},{"id":"2508.10118","title":"From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation","created":"2025-08-13","cited_by_count":12,"area":"lr"},{"id":"2410.23074","title":"Multi-Programming Language Sandbox for LLMs","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2411.13611","title":"DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs","created":"2024-11-20","cited_by_count":9,"area":"alignment"},{"id":"2410.21349","title":"FALCON: Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization system","created":"2024-10-28","cited_by_count":8,"area":"alignment"},{"id":"2506.02211","title":"Improving LLM-Generated Code Quality with GRPO","created":"2025-06-02","cited_by_count":8,"area":"lr"},{"id":"2505.11480","title":"SuperCoder: Assembly Program Superoptimization with Large Language Models","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2507.22853","title":"Repair-R1: Better Test Before Repair","created":"2025-07-30","cited_by_count":6,"area":null},{"id":"2601.15158","title":"Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data","created":"2026-01-21","cited_by_count":6,"area":"lr"},{"id":"2603.12109","title":"On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents","created":"2026-03-12","cited_by_count":6,"area":"lr"},{"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":"2602.17684","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","created":"2026-02-04","cited_by_count":5,"area":"alignment"},{"id":"2508.16771","title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2508.19532","title":"Alignment with Fill-In-the-Middle for Enhancing Code Generation","created":"2025-08-27","cited_by_count":4,"area":"alignment"},{"id":"2510.12264","title":"Reducing Belief Deviation in Reinforcement Learning for Active Reasoning","created":"2025-10-14","cited_by_count":4,"area":"lr"},{"id":"2510.19296","title":"QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2511.20468","title":"DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs","created":"2025-11-25","cited_by_count":4,"area":"lr"},{"id":"2502.11466","title":"GiFT: Gibbs Fine-Tuning for Code Generation","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2607.10169","title":"Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization","created":"2026-07-11","cited_by_count":3,"area":"lr"},{"id":"2609.02987","title":"Tail-Likelihood Reinforcement Learning","created":"2026-09-02","cited_by_count":3,"area":"deeprl"},{"id":"2412.20340","title":"Distilling Desired Comments for Enhanced Code Review with Large Language Models","created":"2024-12-29","cited_by_count":2,"area":null},{"id":"2504.15210","title":"Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMs","created":"2025-04-21","cited_by_count":2,"area":"alignment"},{"id":"2505.10594","title":"CRPE: Expanding The Reasoning Capability of Large Language Model for Code Generation","created":"2025-05-15","cited_by_count":2,"area":"lr"},{"id":"2603.15061","title":"Writer-R1: Enhancing Generative Writing in LLMs via Memory-augmented Replay Policy Optimization","created":"2026-03-16","cited_by_count":2,"area":"alignment"},{"id":"2604.20398","title":"WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning","created":"2026-04-22","cited_by_count":2,"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":"2508.21451","title":"MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2509.03537","title":"AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models","created":"2025-08-27","cited_by_count":1,"area":"lr"},{"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":"2510.18895","title":"CosmoCore Affective Dream-Replay Reinforcement Learning for Code Generation","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2511.20099","title":"QiMeng-CRUX: Narrowing the Gap Between Natural Language and Verilog via Core Refined Understanding eXpression for Circuit Design","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2601.22803","title":"CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"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":"2602.22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2604.11297","title":"The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.16804","title":"AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problems","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2605.30478","title":"Improving Small Language Models for Code Generation with Reinforcement Learning from Verification Feedback","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2412.17908","title":"Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning","created":"2024-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2504.12365","title":"Themisto: Jupyter-Based Runtime Benchmark","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2509.24207","title":"Humanline: Online Alignment as Perceptual Loss","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2512.21351","title":"CosmoCore-Evo: Evolutionary Dream-Replay Reinforcement Learning for Adaptive Code Generation","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2603.13019","title":"ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning","created":"2026-03-13","cited_by_count":0,"area":"agents"},{"id":"2604.27308","title":"BoostLoRA: Growing Effective Rank by Boosting Adapters","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.00433","title":"Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.17174","title":"Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation","created":"2026-05-16","cited_by_count":0,"area":"diffusion"},{"id":"2605.28409","title":"Efficient Post-training of LLMs for Code Generation With Offline Reinforcement Learning","created":"2026-05-27","cited_by_count":0,"area":"offlinerl"},{"id":"2606.20641","title":"MAGNIFIED: RL Fine-tuning of Multimodal Large Language Models for Motion Planning","created":"2026-06-02","cited_by_count":0,"area":"mllm"},{"id":"2610.13015","title":"Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.13020","title":"Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}