{"total":56,"rows":[{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2410.03768","title":"Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs","created":"2024-10-02","cited_by_count":55,"area":null},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53,"area":null},{"id":"2406.11912","title":"AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology","created":"2024-06-16","cited_by_count":46,"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":"2409.05001","title":"A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement","created":"2024-09-08","cited_by_count":21,"area":null},{"id":"2502.11027","title":"On the Effect of Sampling Diversity in Scaling LLM Inference","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2601.00376","title":"In Line with Context: Repository-Level Code Generation via Context Inlining","created":"2026-01-01","cited_by_count":18,"area":null},{"id":"2604.11641","title":"CodeTracer: Towards Traceable Agent States","created":"2026-04-13","cited_by_count":16,"area":null},{"id":"2502.10802","title":"CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2504.19099","title":"VeriDebug: A Unified LLM for Verilog Debugging via Contrastive Embedding and Guided Correction","created":"2025-04-27","cited_by_count":12,"area":null},{"id":"2409.09464","title":"Measuring the Influence of Incorrect Code on Test Generation","created":"2024-09-14","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":"2505.23953","title":"Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach","created":"2025-05-29","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":"2510.09854","title":"NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering","created":"2025-10-10","cited_by_count":10,"area":null},{"id":"2411.02317","title":"Defining and Evaluating Physical Safety for Large Language Models","created":"2024-11-04","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":"2501.18784","title":"Successor-Generator Planning with LLM-generated Heuristics","created":"2025-01-30","cited_by_count":7,"area":null},{"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":"2408.11198","title":"Automated Prompt Engineering for Cost-Effective Code Generation Using Evolutionary Algorithm","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2506.11003","title":"EmbedAgent: Benchmarking Large Language Models in Embedded System Development","created":"2025-04-19","cited_by_count":5,"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":"2507.21485","title":"HLSDebugger: Identification and Correction of Logic Bugs in HLS Code with LLM Solutions","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2509.04078","title":"RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models","created":"2025-09-04","cited_by_count":5,"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":"2605.24812","title":"CoRe-Code: Collaborative Reinforcement Learning for Code Generation","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2606.31511","title":"Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models","created":"2026-06-30","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":"2506.13824","title":"MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios","created":"2025-06-15","cited_by_count":3,"area":null},{"id":"2512.24635","title":"DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2608.11772","title":"Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction","created":"2026-08-12","cited_by_count":3,"area":null},{"id":"2410.15966","title":"Self-Explained Keywords Empower Large Language Models for Code Generation","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2502.12669","title":"Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2504.15080","title":"Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2506.18315","title":"Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2507.19399","title":"Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2511.07998","title":"Self-Correction Distillation for Structured Data Question Answering","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2604.00491","title":"Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2604.17338","title":"Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2501.12106","title":"Can open source large language models be used for tumor documentation in Germany? -- An evaluation on urological doctors' notes","created":"2025-01-21","cited_by_count":1,"area":null},{"id":"2505.13553","title":"Towards Functional Correctness of Large Code Models with Selective Generation","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2602.05905","title":"Codified Finite-state Machines for Role-playing","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2606.17514","title":"Unlocking LLM Code Correction with Iterative Feedback Loops","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2503.22388","title":"Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2510.09049","title":"MEC$^3$O: Multi-Expert Consensus for Code Time Complexity Prediction","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.15004","title":"Automated Snippet-Alignment Data Augmentation for Code Translation","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2511.01316","title":"Exploringand Unleashing the Power of Large Language Models in CI/CD Configuration Translation","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2511.07382","title":"Retriv at BLP-2025 Task 2: Test-Driven Feedback-Guided Framework for Bangla-to-Python Code Generation","created":"2025-11-10","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":"2608.11513","title":"Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation","created":"2026-08-11","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":"2609.12489","title":"Confidence-Gated Transductive Test Generation for Code Reranking","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.13145","title":"VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.19213","title":"PREFER: From Player Experience to Personalized Game Refinement","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20027","title":"LintEval: Benchmarking LLMs on Linter-Guided File Refactoring","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}