{"total":57,"rows":[{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27,"area":null},{"id":"2508.08228","title":"LL3M: Large Language 3D Modelers","created":"2025-08-11","cited_by_count":20,"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":"2505.17104","title":"P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark","created":"2025-05-21","cited_by_count":17,"area":null},{"id":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16,"area":null},{"id":"2503.24260","title":"MaintainCoder: Maintainable Code Generation Under Dynamic Requirements","created":"2025-03-31","cited_by_count":14,"area":null},{"id":"2512.16856","title":"Distributional AGI Safety","created":"2025-12-18","cited_by_count":12,"area":null},{"id":"2603.00680","title":"MemPO: Self-Memory Policy Optimization for Long-Horizon Agents","created":"2026-02-28","cited_by_count":12,"area":null},{"id":"2503.11060","title":"BannerAgency: Advertising Banner Design with Multimodal LLM Agents","created":"2025-03-14","cited_by_count":11,"area":null},{"id":"2506.02961","title":"FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2502.18489","title":"LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness","created":"2025-02-17","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":"2506.02049","title":"EvoGit: Decentralized Code Evolution via Git-Based Multi-Agent Collaboration","created":"2025-06-01","cited_by_count":9,"area":null},{"id":"2502.02928","title":"Large Language Model Guided Self-Debugging Code Generation","created":"2025-02-05","cited_by_count":8,"area":null},{"id":"2601.21448","title":"ChipBench: A Next-Step Benchmark for Evaluating LLM Performance in AI-Aided Chip Design","created":"2026-01-29","cited_by_count":8,"area":null},{"id":"2411.14503","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","created":"2024-11-21","cited_by_count":7,"area":null},{"id":"2405.16072","title":"SynthAI: A Multi Agent Generative AI Framework for Automated Modular HLS Design Generation","created":"2024-05-25","cited_by_count":6,"area":null},{"id":"2510.14509","title":"E2Edev: Benchmarking Large Language Models in End-to-End Software Development Task","created":"2025-10-16","cited_by_count":6,"area":null},{"id":"2506.18403","title":"The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs","created":"2025-06-23","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":"2502.16395","title":"AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science","created":"2025-02-23","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":"2607.01883","title":"PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation","created":"2026-07-02","cited_by_count":4,"area":null},{"id":"2409.04114","title":"Multi-Programming Language Ensemble for Code Generation in Large Language Model","created":"2024-09-06","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":"2505.12925","title":"CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming","created":"2025-05-19","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":"2601.04219","title":"AgentTutor: Empowering Personalized Learning with Multi-Turn Interactive Teaching in Intelligent Education Systems","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2605.05023","title":"CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels","created":"2026-05-06","cited_by_count":2,"area":null},{"id":"2510.15842","title":"Paper2Web: Let's Make Your Paper Alive!","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2510.16439","title":"FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2512.02812","title":"Enhancing Automated Paper Reproduction via Prompt-Free Collaborative Agents","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2601.01320","title":"Adaptive Hierarchical Evaluation of LLMs and SAST tools for CWE Prediction in Python","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2601.11332","title":"Idea First, Code Later: Disentangling Problem Solving from Code Generation in Evaluating LLMs for Competitive Programming","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2603.18604","title":"AutORAN: LLM-driven Natural Language Programming for Agile xApp Development","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.08963","title":"Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.18073","title":"A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.27631","title":"Poison with Style: A Practical Poisoning Attack on Code Large Language Models","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.29999","title":"AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2410.14627","title":"CELI: Controller-Embedded Language Model Interactions","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2507.05512","title":"Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2508.19603","title":"CompLex: Music Theory Lexicon Constructed by Autonomous Agents for Automatic Music Generation","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2602.04291","title":"Disentangling Intrinsic Importance from Emergent Structure in Multi-Expert Orchestration","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.05780","title":"Automated Customization of LLMs for Enterprise Code Repositories Using Semantic Scopes","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.18985","title":"InfEngine: A Self-Verifying and Self-Optimizing Intelligent Engine for Infrared Radiation Computing","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2604.11514","title":"DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.13946","title":"CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.19825","title":"SolidCoder: Bridging the Mental-Reality Gap in LLM Code Generation through Concrete Execution","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.21598","title":"You Don't Need Public Tests to Generate Correct Code","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2607.02390","title":"DecompRL: Solving Harder Problems by Learning Modular Code Generation","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.21069","title":"From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.22471","title":"MineValiCoder: Reliable Code Generation with Test Case Quality Mining and Bipartite Graph-Based Mutual Validation","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.04439","title":"ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.23918","title":"MARS: Multi-Specialist LLM Relay System for Competitive Programming","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.26480","title":"GVS5H: Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performance","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.34717","title":"ReMCTS: Reflection-Enhanced Monte Carlo Tree Search for Code Generation","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}