{"total":99,"rows":[{"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":"2404.18400","title":"LLM-SR: Scientific Equation Discovery via Programming with Large Language Models","created":"2024-04-29","cited_by_count":133,"area":null},{"id":"2307.04349","title":"RLTF: Reinforcement Learning from Unit Test Feedback","created":"2023-07-10","cited_by_count":114,"area":null},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"area":null},{"id":"2505.15201","title":"Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems","created":"2025-05-21","cited_by_count":87,"area":"deeprl"},{"id":"2303.06833","title":"Transformer-based Planning for Symbolic Regression","created":"2023-03-13","cited_by_count":79,"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":"2409.09030","title":"Agents in Software Engineering: Survey, Landscape, and Vision","created":"2024-09-13","cited_by_count":60,"area":"agents"},{"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":"2511.06449","title":"FLEX: Continuous Agent Evolution via Forward Learning from Experience","created":"2025-11-09","cited_by_count":52,"area":"lr"},{"id":"2506.05817","title":"CodeContests+: High-Quality Test Case Generation for Competitive Programming","created":"2025-06-06","cited_by_count":46,"area":"lr"},{"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":"2505.17621","title":"Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided Exploration","created":"2025-05-23","cited_by_count":34,"area":"lr"},{"id":"2401.03003","title":"AST-T5: Structure-Aware Pretraining for Code Generation and Understanding","created":"2024-01-05","cited_by_count":33,"area":null},{"id":"2410.06101","title":"Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning","created":"2024-10-08","cited_by_count":33,"area":"agents"},{"id":"2502.20380","title":"Multi-Turn Code Generation Through Single-Step Rewards","created":"2025-02-27","cited_by_count":28,"area":"alignment"},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27,"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":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2306.06755","title":"CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution","created":"2023-06-11","cited_by_count":22,"area":null},{"id":"2310.01045","title":"Tool-Augmented Reward Modeling","created":"2023-10-02","cited_by_count":20,"area":"alignment"},{"id":"2504.14363","title":"Improving RL Exploration for LLM Reasoning through Retrospective Replay","created":"2025-04-19","cited_by_count":19,"area":"lr"},{"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":"2410.02743","title":"MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions","created":"2024-10-03","cited_by_count":15,"area":"alignment"},{"id":"2309.09826","title":"Efficient Avoidance of Vulnerabilities in Auto-completed Smart Contract Code Using Vulnerability-constrained Decoding","created":"2023-09-18","cited_by_count":14,"area":null},{"id":"2405.16661","title":"RLSF: Fine-tuning LLMs via Symbolic Feedback","created":"2024-05-26","cited_by_count":14,"area":"alignment"},{"id":"2504.15804","title":"Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning with Testbench Feedback","created":"2025-04-22","cited_by_count":14,"area":"alignment"},{"id":"2507.06920","title":"Rethinking Verification for LLM Code Generation: From Generation to Testing","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2307.05337","title":"Explaining Competitive-Level Programming Solutions using LLMs","created":"2023-07-11","cited_by_count":13,"area":null},{"id":"2310.03331","title":"Fine-tune Language Models to Approximate Unbiased In-context Learning","created":"2023-10-05","cited_by_count":12,"area":null},{"id":"2310.18239","title":"Fine-Tuning Language Models Using Formal Methods Feedback","created":"2023-10-27","cited_by_count":12,"area":"alignment"},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","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":"2508.05710","title":"Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning","created":"2025-08-07","cited_by_count":9,"area":"lr"},{"id":"2602.05998","title":"VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2312.05657","title":"PerfRL: A Small Language Model Framework for Efficient Code Optimization","created":"2023-12-09","cited_by_count":8,"area":null},{"id":"2406.06887","title":"$\\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases","created":"2024-06-11","cited_by_count":8,"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":"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":"2509.22824","title":"Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning","created":"2025-09-26","cited_by_count":7,"area":"lr"},{"id":"2411.05199","title":"CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement","created":"2024-11-07","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":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2503.13992","title":"The KoLMogorov Test: Compression by Code Generation","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2503.19217","title":"LLM Benchmarking with LLaMA2: Evaluating Code Development Performance Across Multiple Programming Languages","created":"2025-03-24","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":"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":"2603.16158","title":"Execution-Grounded Credit Assignment for GRPO in Code Generation","created":"2026-03-17","cited_by_count":5,"area":"lr"},{"id":"2412.08859","title":"ViUniT: Visual Unit Tests for More Robust Visual Programming","created":"2024-12-12","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":"2504.00019","title":"ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding","created":"2025-03-27","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":"2602.03806","title":"Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation","created":"2026-02-03","cited_by_count":4,"area":"offlinerl"},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2309.02632","title":"Deep Reinforcement Learning from Hierarchical Preference Design","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2402.12222","title":"CovRL: Fuzzing JavaScript Engines with Coverage-Guided Reinforcement Learning for LLM-based Mutation","created":"2024-02-19","cited_by_count":3,"area":null},{"id":"2503.15129","title":"Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models","created":"2025-03-19","cited_by_count":3,"area":"agents"},{"id":"2504.09643","title":"Iterative Self-Training for Code Generation via Reinforced Re-Ranking","created":"2025-04-13","cited_by_count":3,"area":"synth"},{"id":"2609.02987","title":"Tail-Likelihood Reinforcement Learning","created":"2026-09-02","cited_by_count":3,"area":"deeprl"},{"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":"2506.21608","title":"SysTemp: A Multi-Agent System for Template-Based Generation of SysML v2","created":"2025-06-20","cited_by_count":2,"area":null},{"id":"2511.12033","title":"EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation","created":"2025-11-15","cited_by_count":2,"area":null},{"id":"2602.01685","title":"Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment","created":"2026-02-02","cited_by_count":2,"area":"alignment"},{"id":"2603.07777","title":"Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models","created":"2026-03-08","cited_by_count":2,"area":"lr"},{"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":"2607.01867","title":"An Exploratory Study on LLM-Generated Code and Comments in Code Repositories","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2607.04395","title":"NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation","created":"2026-07-05","cited_by_count":2,"area":"agents"},{"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":"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":"2410.17126","title":"Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards","created":"2024-10-22","cited_by_count":1,"area":"alignment"},{"id":"2503.09020","title":"Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning","created":"2025-03-12","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":"2601.15879","title":"Evaluating and Achieving Controllable Code Completion in Code LLM","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2603.01409","title":"MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning","created":"2026-03-02","cited_by_count":1,"area":"lr"},{"id":"2603.07927","title":"SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"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":"2604.18027","title":"CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora","created":"2026-04-20","cited_by_count":1,"area":"synth"},{"id":"2605.03862","title":"Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2605.21467","title":"DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2608.18682","title":"RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training","created":"2026-08-19","cited_by_count":1,"area":"lr"},{"id":"2507.15889","title":"Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing","created":"2025-07-20","cited_by_count":0,"area":"synth"},{"id":"2508.02091","title":"CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search","created":"2025-08-04","cited_by_count":0,"area":"lr"},{"id":"2508.07179","title":"Schema Lineage Extraction at Scale: Multilingual Pipelines, Composite Evaluation, and Language-Model Benchmarks","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2602.02554","title":"BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.01849","title":"From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code Completion","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.11435","title":"Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2605.07276","title":"Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.11299","title":"Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.13229","title":"Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization","created":"2026-05-13","cited_by_count":0,"area":"alignment"},{"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":"2605.21180","title":"Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.25638","title":"Reinforcement Learning from Denoising Feedback","created":"2026-05-25","cited_by_count":0,"area":"diffusion"},{"id":"2606.03130","title":"Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation","created":"2026-06-02","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":"2610.05966","title":"HuatuoGPT-3: RL-Only Domain Adaptation from Base Models","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}