{"total":73,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"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":"2402.01145","title":"ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution","created":"2024-02-02","cited_by_count":276,"area":null},{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232,"area":null},{"id":"2305.13062","title":"Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study","created":"2023-05-22","cited_by_count":116,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2306.03081","title":"Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs","created":"2023-06-05","cited_by_count":80,"area":null},{"id":"2303.06833","title":"Transformer-based Planning for Symbolic Regression","created":"2023-03-13","cited_by_count":79,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2310.11689","title":"Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs","created":"2023-10-18","cited_by_count":50,"area":null},{"id":"2402.10890","title":"When is Tree Search Useful for LLM Planning? It Depends on the Discriminator","created":"2024-02-16","cited_by_count":47,"area":null},{"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":"2504.13139","title":"Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo","created":"2025-04-17","cited_by_count":46,"area":null},{"id":"2305.14591","title":"ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers","created":"2023-05-24","cited_by_count":41,"area":null},{"id":"2407.09007","title":"Benchmarking Language Model Creativity: A Case Study on Code Generation","created":"2024-07-12","cited_by_count":40,"area":null},{"id":"2408.12159","title":"Search-Based LLMs for Code Optimization","created":"2024-08-22","cited_by_count":28,"area":null},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27,"area":null},{"id":"2503.01245","title":"Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2309.04369","title":"Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation","created":"2023-09-08","cited_by_count":24,"area":null},{"id":"2307.13883","title":"ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis","created":"2023-07-26","cited_by_count":17,"area":null},{"id":"2505.11122","title":"Navigating the Alpha Jungle: An LLM-Powered MCTS Framework for Formulaic Factor Mining","created":"2025-05-16","cited_by_count":16,"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":"2401.08664","title":"Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges","created":"2023-12-27","cited_by_count":13,"area":null},{"id":"2404.05449","title":"RoT: Enhancing Large Language Models with Reflection on Search Trees","created":"2024-04-08","cited_by_count":12,"area":null},{"id":"2409.14907","title":"Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization","created":"2024-09-23","cited_by_count":11,"area":null},{"id":"2410.08696","title":"AMPO: Automatic Multi-Branched Prompt Optimization","created":"2024-10-11","cited_by_count":11,"area":null},{"id":"2410.22296","title":"Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2508.16456","title":"A Probabilistic Inference Scaling Theory for LLM Self-Correction","created":"2025-08-22","cited_by_count":9,"area":null},{"id":"2402.08073","title":"Grounding Data Science Code Generation with Input-Output Specifications","created":"2024-02-12","cited_by_count":7,"area":null},{"id":"2405.01453","title":"Creative Problem Solving in Large Language and Vision Models -- What Would it Take?","created":"2024-05-02","cited_by_count":7,"area":null},{"id":"2503.12293","title":"Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models","created":"2025-03-15","cited_by_count":7,"area":null},{"id":"2507.19598","title":"MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2406.07025","title":"Entropy-Reinforced Planning with Large Language Models for Drug Discovery","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2410.01363","title":"PCQPR: Proactive Conversational Question Planning with Reflection","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2601.03764","title":"Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model","created":"2026-01-07","cited_by_count":6,"area":null},{"id":"2403.03962","title":"Identify Critical Nodes in Complex Network with Large Language Models","created":"2024-03-01","cited_by_count":5,"area":null},{"id":"2407.04831","title":"Code Hallucination","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2410.16655","title":"Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generation","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2512.07404","title":"On LLMs' Internal Representation of Code Correctness","created":"2025-12-08","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":"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":"2504.07433","title":"From Token to Line: Enhancing Code Generation with a Long-Term Perspective","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2505.15356","title":"NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2403.00046","title":"Exploring Data-Efficient Adaptation of Large Language Models for Code Generation","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2412.02410","title":"AutoPLC: Generating Vendor-Aware Structured Text for Programmable Logic Controllers","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2412.08063","title":"ContextModule: Improving Code Completion via Repository-level Contextual Information","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2502.06891","title":"ScaffoldGPT: A Scaffold-based GPT Model for Drug Optimization","created":"2025-02-09","cited_by_count":3,"area":null},{"id":"2508.21294","title":"BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2512.00319","title":"RL-Struct: A Lightweight Reinforcement Learning Framework for Reliable Structured Output in LLMs","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2410.08898","title":"Low-Dimension-to-High-Dimension Generalization And Its Implications for Length Generalization","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2503.08738","title":"Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2509.15796","title":"Monte Carlo Tree Diffusion with Multiple Experts for Protein Design","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2403.00783","title":"On the Roles of LLMs in Planning: Embedding LLMs into Planning Graphs","created":"2024-02-18","cited_by_count":1,"area":null},{"id":"2406.02103","title":"A Bayesian Approach to Online Planning","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2406.11249","title":"Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2502.08756","title":"From PowerPoint UI Sketches to Web-Based Applications: Pattern-Driven Code Generation for GIS Dashboard Development Using Knowledge-Augmented LLMs, Context-Aware Visual Prompting, and the React Framework","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2504.17531","title":"Towards Machine-Generated Code for the Resolution of User Intentions","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2505.14744","title":"Beyond Either-Or Reasoning: Transduction and Induction as Cooperative Problem-Solving Paradigms","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2406.13877","title":"A Systematic Literature Review on the Use of Machine Learning in Software Engineering","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2502.16279","title":"Beyond Trusting Trust: Multi-Model Validation for Robust Code Generation","created":"2025-02-22","cited_by_count":0,"area":null},{"id":"2503.01804","title":"$\\texttt{SEM-CTRL}$: Semantically Controlled Decoding","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2602.00066","title":"IntentCoding: Amplifying User Intent in Code Generation","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.09312","title":"Don't Shoot The Breeze: Topic Continuity Model Using Nonlinear Naive Bayes With Attention","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.16038","title":"Heuristic Search as Language-Guided Program Optimization","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.19284","title":"CDEoH: Category-Driven Automatic Algorithm Design With Large Language Models","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.23989","title":"Understanding Scattered Forest Search: A Version-Space Perspective on Multi-Turn Program Correction","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.00618","title":"Efficient Test-time Inference for Generative Planning Models with OCL Search","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2607.26820","title":"Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.03461","title":"Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.14653","title":"Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2610.03799","title":"StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.11963","title":"Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}