{"total":69,"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":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2308.01861","title":"ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation","created":"2023-08-03","cited_by_count":168,"area":null},{"id":"2403.04642","title":"Teaching Large Language Models to Reason with Reinforcement Learning","created":"2024-03-07","cited_by_count":160,"area":"lr"},{"id":"2506.09965","title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing","created":"2025-06-11","cited_by_count":136,"area":"lr"},{"id":"2308.10335","title":"Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation","created":"2023-08-20","cited_by_count":73,"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":"2411.00622","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","created":"2024-11-01","cited_by_count":61,"area":"agents"},{"id":"2409.09030","title":"Agents in Software Engineering: Survey, Landscape, and Vision","created":"2024-09-13","cited_by_count":60,"area":"agents"},{"id":"2312.15224","title":"LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination","created":"2023-12-23","cited_by_count":48,"area":"agents"},{"id":"2410.02184","title":"CodeJudge: Evaluating Code Generation with Large Language Models","created":"2024-10-03","cited_by_count":44,"area":null},{"id":"2312.14187","title":"WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning","created":"2023-12-20","cited_by_count":42,"area":null},{"id":"2405.19782","title":"Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion","created":"2024-05-30","cited_by_count":40,"area":null},{"id":"2410.07869","title":"Benchmarking Agentic Workflow Generation","created":"2024-10-10","cited_by_count":37,"area":"agents"},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2311.02303","title":"MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning","created":"2023-11-04","cited_by_count":35,"area":null},{"id":"2311.06503","title":"Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering","created":"2023-11-11","cited_by_count":29,"area":"alignment"},{"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":"2403.16443","title":"CodeS: Natural Language to Code Repository via Multi-Layer Sketch","created":"2024-03-25","cited_by_count":28,"area":null},{"id":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28,"area":null},{"id":"2406.18676","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","created":"2024-06-26","cited_by_count":27,"area":"rag"},{"id":"2309.14021","title":"LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression","created":"2023-09-25","cited_by_count":26,"area":null},{"id":"2308.16458","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","created":"2023-08-31","cited_by_count":25,"area":null},{"id":"2312.02143","title":"Competition-Level Problems are Effective LLM Evaluators","created":"2023-12-04","cited_by_count":25,"area":"lr"},{"id":"2409.12452","title":"Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning","created":"2024-09-19","cited_by_count":25,"area":"lr"},{"id":"2411.03562","title":"Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance","created":"2024-11-05","cited_by_count":25,"area":"agents"},{"id":"2401.00788","title":"Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models","created":"2024-01-01","cited_by_count":23,"area":null},{"id":"2310.06046","title":"LLM for SoC Security: A Paradigm Shift","created":"2023-10-09","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":"2401.13920","title":"LocMoE: A Low-Overhead MoE for Large Language Model Training","created":"2024-01-25","cited_by_count":19,"area":"moe"},{"id":"2311.09868","title":"INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair","created":"2023-11-16","cited_by_count":18,"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":"2310.13571","title":"Why Can Large Language Models Generate Correct Chain-of-Thoughts?","created":"2023-10-20","cited_by_count":16,"area":"lr"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2310.06266","title":"CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model","created":"2023-10-10","cited_by_count":14,"area":null},{"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":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13,"area":null},{"id":"2502.02955","title":"ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation","created":"2025-02-05","cited_by_count":13,"area":"agents"},{"id":"2504.14597","title":"a1: Steep Test-time Scaling Law via Environment Augmented Generation","created":"2025-04-20","cited_by_count":13,"area":"lr"},{"id":"2404.00614","title":"Learning to Plan for Language Modeling from Unlabeled Data","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2308.07505","title":"Data Race Detection Using Large Language Models","created":"2023-08-15","cited_by_count":11,"area":null},{"id":"2402.09136","title":"DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2409.15895","title":"Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation","created":"2024-09-24","cited_by_count":10,"area":"rag"},{"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":"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":"2308.16824","title":"Can Programming Languages Boost Each Other via Instruction Tuning?","created":"2023-08-31","cited_by_count":7,"area":null},{"id":"2401.07870","title":"JumpCoder: Go Beyond Autoregressive Coder via Online Modification","created":"2024-01-15","cited_by_count":7,"area":null},{"id":"2402.19366","title":"Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2505.02931","title":"The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models","created":"2025-05-05","cited_by_count":7,"area":null},{"id":"2411.05199","title":"CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement","created":"2024-11-07","cited_by_count":6,"area":null},{"id":"2504.13472","title":"CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation","created":"2025-04-18","cited_by_count":6,"area":"agents"},{"id":"2505.05057","title":"Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware","created":"2025-05-08","cited_by_count":6,"area":"rag"},{"id":"2510.23272","title":"Code Aesthetics with Agentic Reward Feedback","created":"2025-10-27","cited_by_count":6,"area":"agents"},{"id":"2405.02355","title":"CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation","created":"2024-05-03","cited_by_count":4,"area":"rag"},{"id":"2412.08859","title":"ViUniT: Visual Unit Tests for More Robust Visual Programming","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2403.00338","title":"Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models","created":"2024-03-01","cited_by_count":3,"area":"synth"},{"id":"2407.04180","title":"Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing","created":"2024-07-04","cited_by_count":3,"area":null},{"id":"2506.18923","title":"Mix-of-Language-Experts Architecture for Multilingual Programming","created":"2025-06-18","cited_by_count":3,"area":null},{"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":"2502.12492","title":"Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation","created":"2025-02-18","cited_by_count":2,"area":"lr"},{"id":"2511.09794","title":"Evaluating Software Process Models for Multi-Agent Class-Level Code Generation","created":"2025-11-12","cited_by_count":2,"area":"agents"},{"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":"2507.18812","title":"MemoCoder: Automated Function Synthesis using LLM-Supported Agents","created":"2025-07-24","cited_by_count":1,"area":"agents"},{"id":"2605.30808","title":"Differentially Private Preference Data Synthesis for Large Language Model Alignment","created":"2026-05-29","cited_by_count":1,"area":"alignment"},{"id":"2309.11385","title":"Safurai 001: New Qualitative Approach for Code LLM Evaluation","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2311.03243","title":"Safurai-Csharp: Harnessing Synthetic Data to improve language-specific Code LLM","created":"2023-11-06","cited_by_count":0,"area":"synth"},{"id":"2607.14816","title":"Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality","created":"2026-07-16","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}],"next_cursor":null}