{"total":114,"rows":[{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2503.13657","title":"Why Do Multi-Agent LLM Systems Fail?","created":"2025-03-17","cited_by_count":604,"area":"agents"},{"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":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136,"area":"alignment"},{"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":"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":"2405.14431","title":"RaFe: Ranking Feedback Improves Query Rewriting for RAG","created":"2024-05-23","cited_by_count":49,"area":"rag"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"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":"2502.14948","title":"Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation","created":"2025-02-20","cited_by_count":35,"area":"synth"},{"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":"2409.14826","title":"ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback","created":"2024-09-23","cited_by_count":29,"area":"agents"},{"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":"2505.17989","title":"Outcome-based Reinforcement Learning to Predict the Future","created":"2025-05-23","cited_by_count":22,"area":"lr"},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2504.14363","title":"Improving RL Exploration for LLM Reasoning through Retrospective Replay","created":"2025-04-19","cited_by_count":19,"area":"lr"},{"id":"2601.20103","title":"Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis","created":"2026-01-27","cited_by_count":18,"area":"alignment"},{"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":"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":"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":"2410.02743","title":"MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions","created":"2024-10-03","cited_by_count":15,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"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":"2502.02955","title":"ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation","created":"2025-02-05","cited_by_count":13,"area":"agents"},{"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":"2409.19715","title":"Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code","created":"2024-09-29","cited_by_count":9,"area":"alignment"},{"id":"2410.18585","title":"Aligning CodeLLMs with Direct Preference Optimization","created":"2024-10-24","cited_by_count":9,"area":"alignment"},{"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":"2502.13820","title":"Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning","created":"2025-02-19","cited_by_count":9,"area":"lr"},{"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":"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":"2506.18485","title":"A Simple \"Motivation\" Can Enhance Reinforcement Finetuning of Large Reasoning Models","created":"2025-06-23","cited_by_count":7,"area":"lr"},{"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":"2605.02909","title":"Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR","created":"2026-04-06","cited_by_count":7,"area":"lr"},{"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":"2505.03418","title":"Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey","created":"2025-05-06","cited_by_count":6,"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":"2504.07527","title":"Supervised Optimism Correction: Be Confident When LLMs Are Sure","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2511.07922","title":"SERL: Self-Examining Reinforcement Learning on Open-Domain","created":"2025-11-11","cited_by_count":5,"area":"lr"},{"id":"2601.03525","title":"Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation","created":"2026-01-07","cited_by_count":5,"area":"alignment"},{"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":"2603.12698","title":"EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning","created":"2026-03-13","cited_by_count":5,"area":"lr"},{"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":"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":"2605.02944","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2605.07153","title":"Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2606.28430","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","created":"2026-06-26","cited_by_count":4,"area":"agents"},{"id":"2609.07925","title":"FrogNano: Training a 4B Coding Agent via Online Task Synthesis","created":"2026-09-07","cited_by_count":4,"area":"agents"},{"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":"2609.02987","title":"Tail-Likelihood Reinforcement Learning","created":"2026-09-02","cited_by_count":3,"area":"deeprl"},{"id":"2502.02628","title":"e-SimFT: Alignment of Generative Models with Simulation Feedback for Pareto-Front Design Exploration","created":"2025-02-04","cited_by_count":2,"area":"alignment"},{"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":"2601.13097","title":"RM -RF: Reward Model for Run-Free Unit Test Evaluation","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2602.01685","title":"Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment","created":"2026-02-02","cited_by_count":2,"area":"alignment"},{"id":"2602.23407","title":"Learning to Generate Secure Code via Token-Level Rewards","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2603.06065","title":"ChatShopBuddy: Towards Reliable Conversational Shopping Agents via Reinforcement Learning","created":"2026-03-06","cited_by_count":2,"area":"agents"},{"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":"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":"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":"2601.20439","title":"PEARL: Plan Exploration and Adaptive Reinforcement Learning for Multihop Tool Use","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"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":"2603.01409","title":"MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning","created":"2026-03-02","cited_by_count":1,"area":"lr"},{"id":"2603.29292","title":"Self-Improving Code Generation via Semantic Entropy and Behavioral Consensus","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"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":"2609.30878","title":"TISD: On-Policy Self-Distillation with Trajectory Intervention","created":"2026-09-25","cited_by_count":1,"area":"distill"},{"id":"2504.12365","title":"Themisto: Jupyter-Based Runtime Benchmark","created":"2025-04-16","cited_by_count":0,"area":null},{"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":"2509.24207","title":"Humanline: Online Alignment as Perceptual Loss","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2601.05467","title":"STELP: Secure Transpilation and Execution of LLM-Generated Programs","created":"2026-01-09","cited_by_count":0,"area":"agents"},{"id":"2602.20333","title":"DMCD: Semantic-Statistical Framework for Causal Discovery","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2602.22227","title":"Dynamic Adversarial Reinforcement Learning for Robust Multimodal Large Language Models","created":"2026-01-24","cited_by_count":0,"area":"mllm"},{"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":"2605.08399","title":"CoCoDA: Co-evolving Compositional DAG for Tool-Augmented Agents","created":"2026-05-08","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}