{"total":138,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136,"area":"mllm"},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171,"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":"2401.05507","title":"InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks","created":"2024-01-10","cited_by_count":140,"area":"agents"},{"id":"2307.04349","title":"RLTF: Reinforcement Learning from Unit Test Feedback","created":"2023-07-10","cited_by_count":114,"area":null},{"id":"2406.01304","title":"CodeR: Issue Resolving with Multi-Agent and Task Graphs","created":"2024-06-03","cited_by_count":91,"area":null},{"id":"2310.00658","title":"The Robots are Here: Navigating the Generative AI Revolution in Computing Education","created":"2023-10-01","cited_by_count":86,"area":null},{"id":"2310.00367","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","created":"2023-09-30","cited_by_count":79,"area":null},{"id":"2401.00812","title":"If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents","created":"2024-01-01","cited_by_count":79,"area":"agents"},{"id":"2404.10952","title":"Can Language Models Solve Olympiad Programming?","created":"2024-04-16","cited_by_count":72,"area":null},{"id":"2310.00280","title":"Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration","created":"2023-09-30","cited_by_count":70,"area":"lr"},{"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":"2410.03981","title":"A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages","created":"2024-10-04","cited_by_count":66,"area":null},{"id":"2403.08937","title":"Bugs in Large Language Models Generated Code: An Empirical Study","created":"2024-03-13","cited_by_count":60,"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":"2308.01240","title":"Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation","created":"2023-08-02","cited_by_count":50,"area":null},{"id":"2404.15676","title":"Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs","created":"2024-04-24","cited_by_count":48,"area":"lr"},{"id":"2312.04372","title":"LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs","created":"2023-12-07","cited_by_count":45,"area":"driving"},{"id":"2403.01131","title":"LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation","created":"2024-03-02","cited_by_count":45,"area":null},{"id":"2403.18746","title":"CYCLE: Learning to Self-Refine the Code Generation","created":"2024-03-27","cited_by_count":42,"area":null},{"id":"2411.12924","title":"Human-In-the-Loop Software Development Agents","created":"2024-11-19","cited_by_count":42,"area":"agents"},{"id":"2402.05200","title":"Are LLMs Ready for Real-World Materials Discovery?","created":"2024-02-07","cited_by_count":40,"area":null},{"id":"2406.07003","title":"GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model","created":"2024-06-11","cited_by_count":40,"area":"rag"},{"id":"2402.07844","title":"Mercury: A Code Efficiency Benchmark for Code Large Language Models","created":"2024-02-12","cited_by_count":35,"area":null},{"id":"2406.07243","title":"MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs","created":"2024-06-11","cited_by_count":35,"area":null},{"id":"2408.14354","title":"SWE-bench-java: A GitHub Issue Resolving Benchmark for Java","created":"2024-08-26","cited_by_count":34,"area":null},{"id":"2305.11169","title":"Emergent Representations of Program Semantics in Language Models Trained on Programs","created":"2023-05-18","cited_by_count":30,"area":"wm"},{"id":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30,"area":null},{"id":"2501.12372","title":"Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL","created":"2025-01-21","cited_by_count":30,"area":null},{"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":"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":"2406.00215","title":"HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent","created":"2024-05-31","cited_by_count":24,"area":"agents"},{"id":"2502.01715","title":"Process-Supervised Reinforcement Learning for Code Generation","created":"2025-02-03","cited_by_count":22,"area":null},{"id":"2407.02099","title":"Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior","created":"2024-07-02","cited_by_count":21,"area":null},{"id":"2408.13204","title":"DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation","created":"2024-08-23","cited_by_count":21,"area":null},{"id":"2411.07464","title":"BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks","created":"2024-11-12","cited_by_count":19,"area":"agents"},{"id":"2405.07530","title":"Prompt-based Code Completion via Multi-Retrieval Augmented Generation","created":"2024-05-13","cited_by_count":16,"area":"rag"},{"id":"2401.09074","title":"Code Simulation Challenges for Large Language Models","created":"2024-01-17","cited_by_count":15,"area":null},{"id":"2407.00456","title":"Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models","created":"2024-06-29","cited_by_count":15,"area":null},{"id":"2307.08220","title":"FRANC: A Lightweight Framework for High-Quality Code Generation","created":"2023-07-17","cited_by_count":14,"area":null},{"id":"2308.12415","title":"Benchmarking Causal Study to Interpret Large Language Models for Source Code","created":"2023-08-23","cited_by_count":14,"area":null},{"id":"2504.14119","title":"CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning","created":"2025-04-19","cited_by_count":14,"area":"lr"},{"id":"2407.02211","title":"PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning","created":"2024-07-02","cited_by_count":13,"area":null},{"id":"2502.15343","title":"Tokenization is Sensitive to Language Variation","created":"2025-02-21","cited_by_count":13,"area":null},{"id":"2311.07599","title":"Testing LLMs on Code Generation with Varying Levels of Prompt Specificity","created":"2023-11-10","cited_by_count":12,"area":null},{"id":"2402.14558","title":"LLMs with Industrial Lens: Deciphering the Challenges and Prospects -- A Survey","created":"2024-02-22","cited_by_count":12,"area":null},{"id":"2506.20495","title":"ReCode: Updating Code API Knowledge with Reinforcement Learning","created":"2025-06-25","cited_by_count":12,"area":"alignment"},{"id":"2308.07505","title":"Data Race Detection Using Large Language Models","created":"2023-08-15","cited_by_count":11,"area":null},{"id":"2505.11604","title":"Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation","created":"2025-05-16","cited_by_count":11,"area":null},{"id":"2508.18190","title":"ST-Raptor: LLM-Powered Semi-Structured Table Question Answering","created":"2025-08-25","cited_by_count":11,"area":null},{"id":"2406.12902","title":"JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2502.18851","title":"Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code","created":"2025-02-26","cited_by_count":10,"area":"safety"},{"id":"2509.09969","title":"Large Language Models Meet Legal Artificial Intelligence: A Survey","created":"2025-09-12","cited_by_count":10,"area":null},{"id":"2403.15230","title":"An Exploratory Investigation into Code License Infringements in Large Language Model Training Datasets","created":"2024-03-22","cited_by_count":9,"area":null},{"id":"2408.10210","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","created":"2024-07-12","cited_by_count":9,"area":"distill"},{"id":"2409.08692","title":"B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests","created":"2024-09-13","cited_by_count":9,"area":null},{"id":"2412.11014","title":"CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation","created":"2024-12-15","cited_by_count":9,"area":"agents"},{"id":"2501.05396","title":"FairCoder: Probing LLM Bias in High-Stakes Decision Making via Coding Tasks","created":"2025-01-09","cited_by_count":9,"area":null},{"id":"2508.11425","title":"Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments","created":"2025-08-15","cited_by_count":9,"area":"agents"},{"id":"2306.07285","title":"TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills","created":"2023-05-23","cited_by_count":8,"area":"mechinterp"},{"id":"2410.04617","title":"Evaluation of Code LLMs on Geospatial Code Generation","created":"2024-10-06","cited_by_count":8,"area":null},{"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":"2503.12440","title":"HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs","created":"2025-03-16","cited_by_count":8,"area":null},{"id":"2504.20964","title":"OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification","created":"2025-04-29","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":"2405.03998","title":"Sketch Then Generate: Providing Incremental User Feedback and Guiding LLM Code Generation through Language-Oriented Code Sketches","created":"2024-05-07","cited_by_count":7,"area":null},{"id":"2407.03611","title":"An Empirical Study on Capability of Large Language Models in Understanding Code Semantics","created":"2024-07-04","cited_by_count":7,"area":null},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2501.15000","title":"MDEval: Evaluating and Enhancing Markdown Awareness in Large Language Models","created":"2025-01-25","cited_by_count":7,"area":null},{"id":"2502.03568","title":"Code Simulation as a Proxy for High-order Tasks in Large Language Models","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2508.02053","title":"ProCut: LLM Prompt Compression via Attribution Estimation","created":"2025-08-04","cited_by_count":6,"area":"inference"},{"id":"2312.15614","title":"A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2402.03130","title":"User Centric Evaluation of Code Generation Tools","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2402.09615","title":"API Pack: A Massive Multi-Programming Language Dataset for API Call Generation","created":"2024-02-14","cited_by_count":5,"area":null},{"id":"2402.10436","title":"I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Models","created":"2024-02-16","cited_by_count":5,"area":null},{"id":"2407.08956","title":"Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss","created":"2024-07-12","cited_by_count":5,"area":"safety"},{"id":"2409.07489","title":"RAGent: Retrieval-based Access Control Policy Generation","created":"2024-09-08","cited_by_count":5,"area":null},{"id":"2503.17953","title":"Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts","created":"2025-03-23","cited_by_count":5,"area":"safety"},{"id":"2505.23851","title":"ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2507.22080","title":"CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback","created":"2025-07-25","cited_by_count":5,"area":null},{"id":"2309.13218","title":"Language Models for Business Optimisation with a Real World Case Study in Production Scheduling","created":"2023-09-22","cited_by_count":4,"area":null},{"id":"2403.01570","title":"Small Models are LLM Knowledge Triggers on Medical Tabular Prediction","created":"2024-03-03","cited_by_count":4,"area":null},{"id":"2502.08298","title":"Improving Existing Optimization Algorithms with LLMs","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2602.23876","title":"RF-Agent: Automated Reward Function Design via Language Agent Tree Search","created":"2026-02-27","cited_by_count":4,"area":"agents"},{"id":"2311.01490","title":"The Behavior of Large Language Models When Prompted to Generate Code Explanations","created":"2023-11-02","cited_by_count":3,"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":"2404.02512","title":"Towards Large Language Model driven Reference-less Translation Evaluation for English and Indian Languages","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2404.02540","title":"CSEPrompts: A Benchmark of Introductory Computer Science Prompts","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2405.01556","title":"Semantically Aligned Question and Code Generation for Automated Insight Generation","created":"2024-03-21","cited_by_count":3,"area":null},{"id":"2405.04955","title":"Improving Long Text Understanding with Knowledge Distilled from Summarization Model","created":"2024-05-08","cited_by_count":3,"area":null},{"id":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2502.11466","title":"GiFT: Gibbs Fine-Tuning for Code Generation","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2503.07693","title":"Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models","created":"2025-03-10","cited_by_count":3,"area":"agents"}],"next_cursor":"100"}