{"total":358,"rows":[{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554,"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":"2505.13259","title":"From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery","created":"2025-05-19","cited_by_count":93,"area":null},{"id":"2408.04667","title":"Non-Determinism of \"Deterministic\" LLM Settings","created":"2024-08-06","cited_by_count":92,"area":null},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83,"area":null},{"id":"2410.14716","title":"A Systematic Survey on Large Language Models for Algorithm Design","created":"2024-10-11","cited_by_count":69,"area":null},{"id":"2408.03910","title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","created":"2024-08-07","cited_by_count":65,"area":null},{"id":"2509.13312","title":"WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research","created":"2025-09-16","cited_by_count":46,"area":null},{"id":"2507.04952","title":"ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation","created":"2025-07-07","cited_by_count":42,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2407.02524","title":"Meta Large Language Model Compiler: Foundation Models of Compiler Optimization","created":"2024-06-27","cited_by_count":39,"area":null},{"id":"2504.09246","title":"Type-Constrained Code Generation with Language Models","created":"2025-04-12","cited_by_count":35,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2502.01715","title":"Process-Supervised Reinforcement Learning for Code Generation","created":"2025-02-03","cited_by_count":22,"area":null},{"id":"2503.02863","title":"SteerConf: Steering LLMs for Confidence Elicitation","created":"2025-03-04","cited_by_count":20,"area":null},{"id":"2503.17181","title":"A Study of LLMs' Preferences for Libraries and Programming Languages","created":"2025-03-21","cited_by_count":20,"area":null},{"id":"2508.08228","title":"LL3M: Large Language 3D Modelers","created":"2025-08-11","cited_by_count":20,"area":null},{"id":"2412.09879","title":"On the Limit of Language Models as Planning Formalizers","created":"2024-12-13","cited_by_count":18,"area":null},{"id":"2406.07411","title":"VersiCode: Towards Version-controllable Code Generation","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2504.21751","title":"CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation","created":"2025-04-30","cited_by_count":17,"area":null},{"id":"2508.16546","title":"RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs","created":"2025-08-22","cited_by_count":17,"area":null},{"id":"2412.14234","title":"Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis","created":"2024-12-18","cited_by_count":16,"area":null},{"id":"2503.17502","title":"Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets","created":"2025-03-21","cited_by_count":16,"area":null},{"id":"2509.11252","title":"Exploring the Potential of Diffusion Large Language Models in Code Generation","created":"2025-09-14","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":"2503.13310","title":"Generative AI for Software Architecture. Applications, Challenges, and Future Directions","created":"2025-03-17","cited_by_count":15,"area":null},{"id":"2502.11075","title":"Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models","created":"2025-02-16","cited_by_count":14,"area":null},{"id":"2503.24260","title":"MaintainCoder: Maintainable Code Generation Under Dynamic Requirements","created":"2025-03-31","cited_by_count":14,"area":null},{"id":"2508.10111","title":"Constrained Decoding of Diffusion LLMs with Context-Free Grammars","created":"2025-08-13","cited_by_count":14,"area":null},{"id":"2410.14208","title":"Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning","created":"2024-10-18","cited_by_count":13,"area":null},{"id":"2412.20545","title":"The Impact of Prompt Programming on Function-Level Code Generation","created":"2024-12-29","cited_by_count":13,"area":null},{"id":"2506.00894","title":"CODEMENV: Benchmarking Large Language Models on Code Migration","created":"2025-06-01","cited_by_count":13,"area":null},{"id":"2507.21928","title":"Vibe Coding as a Reconfiguration of Intent Mediation in Software Development: Definition, Implications, and Research Agenda","created":"2025-07-29","cited_by_count":13,"area":null},{"id":"2410.06667","title":"Large Language Models as Code Executors: An Exploratory Study","created":"2024-10-09","cited_by_count":12,"area":null},{"id":"2505.19030","title":"RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data","created":"2025-05-25","cited_by_count":12,"area":null},{"id":"2512.16856","title":"Distributional AGI Safety","created":"2025-12-18","cited_by_count":12,"area":null},{"id":"2601.07348","title":"Controlled Self-Evolution for Algorithmic Code Optimization","created":"2026-01-12","cited_by_count":12,"area":null},{"id":"2408.00019","title":"WebApp1K: A Practical Code-Generation Benchmark for Web App Development","created":"2024-07-30","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":"2409.06741","title":"Generative AI for Requirements Engineering: A Systematic Literature Review","created":"2024-09-10","cited_by_count":11,"area":null},{"id":"2410.11863","title":"ChatVis: Automating Scientific Visualization with a Large Language Model","created":"2024-10-07","cited_by_count":11,"area":null},{"id":"2410.19605","title":"CoqPilot, a plugin for LLM-based generation of proofs","created":"2024-10-25","cited_by_count":11,"area":null},{"id":"2411.00932","title":"LLMs: A Game-Changer for Software Engineers?","created":"2024-11-01","cited_by_count":11,"area":null},{"id":"2503.13733","title":"CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2504.20799","title":"Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges","created":"2025-04-29","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":"2506.21408","title":"Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference","created":"2025-06-26","cited_by_count":11,"area":null},{"id":"2508.01473","title":"TreeDiff: AST-Guided Code Generation with Diffusion LLMs","created":"2025-08-02","cited_by_count":11,"area":null},{"id":"2408.03519","title":"RepoMasterEval: Evaluating Code Completion via Real-World Repositories","created":"2024-08-07","cited_by_count":10,"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":"2503.00686","title":"GPIoT: Tailoring Small Language Models for IoT Program Synthesis and Development","created":"2025-03-02","cited_by_count":10,"area":null},{"id":"2505.15337","title":"Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors","created":"2025-05-21","cited_by_count":10,"area":null},{"id":"2506.10948","title":"Execution Guided Line-by-Line Code Generation","created":"2025-06-12","cited_by_count":10,"area":null},{"id":"2508.15830","title":"DAIQ: Auditing Demographic Attribute Inference from Question in LLMs","created":"2025-08-18","cited_by_count":10,"area":null},{"id":"2508.16671","title":"Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2601.02997","title":"From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures","created":"2026-01-06","cited_by_count":10,"area":null},{"id":"2412.18241","title":"An Automatic Graph Construction Framework based on Large Language Models for Recommendation","created":"2024-12-24","cited_by_count":9,"area":null},{"id":"2503.02497","title":"A PennyLane-Centric Dataset to Enhance LLM-based Quantum Code Generation using RAG","created":"2025-03-04","cited_by_count":9,"area":null},{"id":"2505.20881","title":"Generalizable Heuristic Generation Through LLMs with Meta-Optimization","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2506.06821","title":"Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems","created":"2025-06-07","cited_by_count":9,"area":null},{"id":"2508.05995","title":"Optimizing Prompt Sequences using Monte Carlo Tree Search for LLM-Based Optimization","created":"2025-08-08","cited_by_count":9,"area":null},{"id":"2509.10858","title":"Large Language Models for Security Operations Centers: A Comprehensive Survey","created":"2025-09-13","cited_by_count":9,"area":null},{"id":"2510.16844","title":"FinSight: Towards Real-World Financial Deep Research","created":"2025-10-19","cited_by_count":9,"area":null},{"id":"2601.05106","title":"Token-Level LLM Collaboration via FusionRoute","created":"2026-01-08","cited_by_count":9,"area":null},{"id":"2601.17058","title":"Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs","created":"2026-01-22","cited_by_count":9,"area":null},{"id":"2408.13467","title":"LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs","created":"2024-08-24","cited_by_count":8,"area":null},{"id":"2410.08806","title":"Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs","created":"2024-10-11","cited_by_count":8,"area":null},{"id":"2410.10075","title":"RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2412.06071","title":"KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models","created":"2024-12-08","cited_by_count":8,"area":null},{"id":"2412.14656","title":"Length Controlled Generation for Black-box LLMs","created":"2024-12-19","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":"2506.16393","title":"From LLM-anation to LLM-orchestrator: Coordinating Small Models for Data Labeling","created":"2025-06-19","cited_by_count":8,"area":null},{"id":"2510.26130","title":"Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation","created":"2025-10-30","cited_by_count":8,"area":null},{"id":"2512.00020","title":"Large Language Model for Verilog Code Generation: Literature Review and the Road Ahead","created":"2025-10-29","cited_by_count":8,"area":null},{"id":"2603.09652","title":"MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants","created":"2026-03-10","cited_by_count":8,"area":null},{"id":"2407.17404","title":"Grammar-based Game Description Generation using Large Language Models","created":"2024-07-24","cited_by_count":7,"area":null},{"id":"2411.16111","title":"LLMPirate: LLMs for Black-box Hardware IP Piracy","created":"2024-11-25","cited_by_count":7,"area":null},{"id":"2503.17195","title":"TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2505.16477","title":"Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2506.00309","title":"Evaluation of LLMs for mathematical problem solving","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2508.21137","title":"How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations","created":"2025-08-28","cited_by_count":7,"area":null},{"id":"2603.05863","title":"ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2501.06283","title":"Dafny as Verification-Aware Intermediate Language for Code Generation","created":"2025-01-10","cited_by_count":6,"area":null},{"id":"2501.07653","title":"Large Language Models for Interpretable Mental Health Diagnosis","created":"2025-01-13","cited_by_count":6,"area":null},{"id":"2505.15740","title":"HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2507.00057","title":"Incoherence as Oracle-less Measure of Error in LLM-Based Code Generation","created":"2025-06-26","cited_by_count":6,"area":null},{"id":"2507.10614","title":"Fine-tuning Large Language Model for Automated Algorithm Design","created":"2025-07-13","cited_by_count":6,"area":null},{"id":"2408.01050","title":"The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines","created":"2024-08-02","cited_by_count":5,"area":null},{"id":"2410.14748","title":"ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2501.11354","title":"Towards Advancing Code Generation with Large Language Models: A Research Roadmap","created":"2025-01-20","cited_by_count":5,"area":null},{"id":"2502.08884","title":"ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2503.08823","title":"ResBench: Benchmarking LLM-Generated FPGA Designs with Resource Awareness","created":"2025-03-11","cited_by_count":5,"area":null},{"id":"2503.22444","title":"Scaling Laws in Scientific Discovery with AI and Robot Scientists","created":"2025-03-28","cited_by_count":5,"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":"2504.09685","title":"Can LLMs Revolutionize the Design of Explainable and Efficient TinyML Models?","created":"2025-04-13","cited_by_count":5,"area":null},{"id":"2505.04406","title":"YABLoCo: Yet Another Benchmark for Long Context Code Generation","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2505.08542","title":"Guiding LLM-based Smart Contract Generation with Finite State Machine","created":"2025-05-13","cited_by_count":5,"area":null},{"id":"2505.18724","title":"LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2506.01074","title":"How Programming Concepts and Neurons Are Shared in Code Language Models","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2506.01084","title":"zip2zip: Inference-Time Adaptive Tokenization via Online Compression","created":"2025-06-01","cited_by_count":5,"area":null}],"next_cursor":"100"}