{"total":102,"rows":[{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238,"area":null},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157,"area":"agents"},{"id":"2302.07867","title":"Learning Performance-Improving Code Edits","created":"2023-02-15","cited_by_count":106,"area":null},{"id":"2405.16433","title":"CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling","created":"2024-05-26","cited_by_count":89,"area":null},{"id":"2502.06193","title":"Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering","created":"2025-02-10","cited_by_count":67,"area":null},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57,"area":null},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55,"area":"alignment"},{"id":"2304.14317","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","created":"2023-04-27","cited_by_count":52,"area":null},{"id":"2504.12522","title":"Evaluating the Diversity and Quality of LLM Generated Content","created":"2025-04-16","cited_by_count":51,"area":"lr"},{"id":"2410.02184","title":"CodeJudge: Evaluating Code Generation with Large Language Models","created":"2024-10-03","cited_by_count":44,"area":null},{"id":"2411.12924","title":"Human-In-the-Loop Software Development Agents","created":"2024-11-19","cited_by_count":42,"area":"agents"},{"id":"2410.03131","title":"Code Comprehension then Auditing for Unsupervised LLM Evaluation","created":"2024-10-04","cited_by_count":32,"area":null},{"id":"2310.14053","title":"Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain","created":"2023-10-21","cited_by_count":31,"area":"lr"},{"id":"2310.17680","title":"CodeFusion: A Pre-trained Diffusion Model for Code Generation","created":"2023-10-26","cited_by_count":31,"area":"diffusion"},{"id":"2503.23989","title":"Rubric Is All You Need: Enhancing LLM-based Code Evaluation With Question-Specific Rubrics","created":"2025-03-31","cited_by_count":29,"area":null},{"id":"2510.06186","title":"RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback","created":"2025-10-07","cited_by_count":25,"area":"alignment"},{"id":"2402.08699","title":"Unsupervised Evaluation of Code LLMs with Round-Trip Correctness","created":"2024-02-13","cited_by_count":23,"area":null},{"id":"2309.17446","title":"L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models","created":"2023-09-29","cited_by_count":22,"area":null},{"id":"2503.20589","title":"What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond","created":"2025-03-26","cited_by_count":22,"area":"rag"},{"id":"2410.04194","title":"Consistent Autoformalization for Constructing Mathematical Libraries","created":"2024-10-05","cited_by_count":21,"area":null},{"id":"2406.10710","title":"SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task","created":"2024-06-15","cited_by_count":19,"area":"synth"},{"id":"2410.20527","title":"CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming","created":"2024-10-27","cited_by_count":19,"area":null},{"id":"2505.16222","title":"Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation","created":"2025-05-22","cited_by_count":18,"area":null},{"id":"2309.14846","title":"Supersonic: Learning to Generate Source Code Optimizations in C/C++","created":"2023-09-26","cited_by_count":16,"area":null},{"id":"2411.01063","title":"InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation","created":"2024-11-01","cited_by_count":16,"area":null},{"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":"2303.09128","title":"Exploring Distributional Shifts in Large Language Models for Code Analysis","created":"2023-03-16","cited_by_count":14,"area":null},{"id":"2308.16753","title":"Context Aware Query Rewriting for Text Rankers using LLM","created":"2023-08-31","cited_by_count":14,"area":null},{"id":"2408.11081","title":"What can Large Language Models Capture about Code Functional Equivalence?","created":"2024-08-20","cited_by_count":14,"area":null},{"id":"2505.20538","title":"AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy","created":"2025-05-26","cited_by_count":13,"area":null},{"id":"2311.02807","title":"QualEval: Qualitative Evaluation for Model Improvement","created":"2023-11-06","cited_by_count":11,"area":null},{"id":"2503.00691","title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","created":"2025-03-02","cited_by_count":11,"area":null},{"id":"2411.06638","title":"Model Editing for LLMs4Code: How Far are We?","created":"2024-11-11","cited_by_count":10,"area":null},{"id":"2510.19873","title":"From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph","created":"2025-10-22","cited_by_count":10,"area":"lr"},{"id":"2403.17214","title":"Output Format Biases in the Evaluation of Large Language Models for Code Translation","created":"2024-03-25","cited_by_count":9,"area":null},{"id":"2503.13505","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2409.19801","title":"CRScore: Grounding Automated Evaluation of Code Review Comments in Code Claims and Smells","created":"2024-09-29","cited_by_count":8,"area":null},{"id":"2502.17657","title":"StatLLM: A Dataset for Evaluating the Performance of Large Language Models in Statistical Analysis","created":"2025-02-24","cited_by_count":8,"area":null},{"id":"2507.13290","title":"Towards Formal Verification of LLM-Generated Code from Natural Language Prompts","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2601.11895","title":"DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models","created":"2026-01-17","cited_by_count":8,"area":null},{"id":"2406.06559","title":"Harnessing Business and Media Insights with Large Language Models","created":"2024-06-02","cited_by_count":7,"area":null},{"id":"2402.07518","title":"Efficient and Universal Watermarking for LLM-Generated Code Detection","created":"2024-02-12","cited_by_count":6,"area":"safety"},{"id":"2405.01580","title":"On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2502.17956","title":"Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments","created":"2025-02-25","cited_by_count":6,"area":"lr"},{"id":"2310.04047","title":"AutoParLLM: GNN-guided Context Generation for Zero-Shot Code Parallelization using LLMs","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2405.14753","title":"A Transformer-Based Approach for Smart Invocation of Automatic Code Completion","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2506.14280","title":"Improving LoRA with Variational Learning","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2604.02028","title":"Why Gaussian Diffusion Models Fail on Discrete Data and How to Prevent It?","created":"2026-04-02","cited_by_count":5,"area":"diffusion"},{"id":"2308.13354","title":"On the Impact of Language Selection for Training and Evaluating Programming Language Models","created":"2023-08-25","cited_by_count":4,"area":null},{"id":"2406.00037","title":"Aligning LLMs through Multi-perspective User Preference Ranking-based Feedback for Programming Question Answering","created":"2024-05-27","cited_by_count":4,"area":"alignment"},{"id":"2408.13745","title":"DOCE: Finding the Sweet Spot for Execution-Based Code Generation","created":"2024-08-25","cited_by_count":4,"area":null},{"id":"2408.15630","title":"CodeSift: An LLM-Based Reference-Less Framework for Automatic Code Validation","created":"2024-08-28","cited_by_count":4,"area":null},{"id":"2504.19730","title":"Evaluate-and-Purify: Fortifying Code Language Models Against Adversarial Attacks Using LLM-as-a-Judge","created":"2025-04-28","cited_by_count":4,"area":null},{"id":"2506.08800","title":"Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents","created":"2025-06-10","cited_by_count":4,"area":"agents"},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","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":"2502.07835","title":"Bridging LLM-Generated Code and Requirements: Reverse Generation technique and SBC Metric for Developer Insights","created":"2025-02-11","cited_by_count":3,"area":null},{"id":"2504.15564","title":"OpenClassGen: A Large-Scale Corpus of Real-World Python Classes for LLM Research","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2504.18693","title":"Technical Challenges in Maintaining Tax Prep Software with Large Language Models","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2510.21513","title":"Wisdom and Delusion of LLM Ensembles for Code Generation and Repair","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2603.02787","title":"Rethinking Code Similarity for Automated Algorithm Design with LLMs","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2403.10575","title":"Exploring Language Model's Code Generation Ability with Auxiliary Functions","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2501.04811","title":"Fast, Fine-Grained Equivalence Checking for Neural Decompilers","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2505.15469","title":"A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.19502","title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation","created":"2025-05-26","cited_by_count":2,"area":"lr"},{"id":"2509.08541","title":"CM-Align: Consistency-based Multilingual Alignment for Large Language Models","created":"2025-09-10","cited_by_count":2,"area":"alignment"},{"id":"2511.10691","title":"Evaluating from Benign to Dynamic Adversarial: A Squid Game for Large Language Models","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2511.19422","title":"SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2511.22258","title":"Beyond Query-Level Comparison: Fine-Grained Reinforcement Learning for Text-to-SQL with Automated Interpretable Critiques","created":"2025-11-27","cited_by_count":2,"area":"lr"},{"id":"2512.08810","title":"Multicalibration for LLM-based Code Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2407.14530","title":"FuncEvalGMN: Evaluating Functional Correctness of SQL via Graph Matching Network","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2412.03612","title":"Chatting with Logs: An exploratory study on Finetuning LLMs for LogQL","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2504.17665","title":"Evaluating Intermediate Reasoning of Code-Assisted Large Language Models for Mathematics","created":"2025-04-24","cited_by_count":1,"area":"lr"},{"id":"2506.11237","title":"LLM-as-a-Judge for Reference-less Automatic Code Validation and Refinement for Natural Language to Bash in IT Automation","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2509.11942","title":"VisDocSketcher: Towards Scalable Visual Documentation with Agentic Systems","created":"2025-09-15","cited_by_count":1,"area":"agents"},{"id":"2510.23169","title":"MATCH: Task-Driven Code Evaluation through Contrastive Learning","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2512.18748","title":"Code2Doc: A Quality-First Curated Dataset for Code Documentation","created":"2025-12-21","cited_by_count":1,"area":null},{"id":"2601.04801","title":"MPM-LLM4DSE: Reaching the Pareto Frontier in HLS with Multimodal Learning and LLM-Driven Exploration","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.12146","title":"From LLMs to Agents in Programming: The Impact of Providing an LLM with a Compiler","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2603.09004","title":"Can AI Agents Generate Microservices? How Far are We?","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2603.20210","title":"CRoCoDiL: Continuous and Robust Conditioned Diffusion for Language","created":"2026-03-02","cited_by_count":1,"area":"diffusion"},{"id":"2606.07822","title":"The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2607.25130","title":"Learning from 53.6K Real-World Developer Edits of AI-Generated Code","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2407.19772","title":"Generating Unseen Code Tests In Infinitum","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2408.09134","title":"Better Python Programming for all: With the focus on Maintainability","created":"2024-08-17","cited_by_count":0,"area":null},{"id":"2409.13928","title":"Eliciting Instruction-tuned Code Language Models' Capabilities to Utilize Auxiliary Function for Code Generation","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2501.03783","title":"How to Select Pre-Trained Code Models for Reuse? A Learning Perspective","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2502.12189","title":"Self-supervised Attribute-aware Dynamic Preference Ranking Alignment","created":"2025-02-15","cited_by_count":0,"area":"alignment"},{"id":"2505.14664","title":"AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2510.09898","title":"Learning Bug Context for PyTorch-to-JAX Translation with LLMs","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.21537","title":"Excision Score: Evaluating Edits with Surgical Precision","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2511.04849","title":"Software Defined Vehicle Code Generation: A Few-Shot Prompting Approach","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2602.10249","title":"Modeling Programming Skills with Source Code Embeddings for Context-aware Exercise Recommendation","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2604.25778","title":"Can Code Evaluation Metrics Detect Code Plagiarism?","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.13138","title":"A Comprehensive Evaluation of Code Language Models for Security Patch Detection","created":"2026-05-13","cited_by_count":0,"area":null},{"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":"2606.19988","title":"Repository-Level Solidity Code Generation with Large Language Models: From Prompting to Fine-Tuning","created":"2026-06-18","cited_by_count":0,"area":"rag"}],"next_cursor":"100"}