{"total":53,"rows":[{"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":"2410.01215","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":"2504.09246","title":"Type-Constrained Code Generation with Language Models","created":"2025-04-12","cited_by_count":35,"area":null},{"id":"2603.24755","title":"SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks","created":"2026-03-25","cited_by_count":30,"area":"agents"},{"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":"2412.17744","title":"RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation","created":"2024-12-23","cited_by_count":23,"area":null},{"id":"2504.14363","title":"Improving RL Exploration for LLM Reasoning through Retrospective Replay","created":"2025-04-19","cited_by_count":19,"area":"lr"},{"id":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"id":"2504.09691","title":"Migrating Code At Scale With LLMs At Google","created":"2025-04-13","cited_by_count":14,"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":"2507.20439","title":"When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions","created":"2025-07-27","cited_by_count":11,"area":null},{"id":"2410.23074","title":"Multi-Programming Language Sandbox for LLMs","created":"2024-10-30","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":"2502.02928","title":"Large Language Model Guided Self-Debugging Code Generation","created":"2025-02-05","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":"2505.24189","title":"Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2601.15812","title":"ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models","created":"2026-01-22","cited_by_count":6,"area":null},{"id":"2410.03234","title":"Showing LLM-Generated Code Selectively Based on Confidence of LLMs","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2505.14394","title":"Knowledge Graph Based Repository-Level Code Generation","created":"2025-05-20","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":"2506.06971","title":"Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation","created":"2025-06-08","cited_by_count":4,"area":"lr"},{"id":"2507.00322","title":"Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2408.16601","title":"Examination of Code generated by Large Language Models","created":"2024-08-29","cited_by_count":3,"area":null},{"id":"2502.17441","title":"Renaissance of Literate Programming in the Era of LLMs: Enhancing LLM-Based Code Generation in Large-Scale Projects","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2409.15228","title":"A Comprehensive Framework for Evaluating API-oriented Code Generation in Large Language Models","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2501.03572","title":"From Code to Compliance: Assessing ChatGPT's Utility in Designing an Accessible Webpage -- A Case Study","created":"2025-01-07","cited_by_count":2,"area":null},{"id":"2502.18499","title":"Mechanistic Understanding of Language Models in Syntactic Code Completion","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2503.21646","title":"Unlocking the Potential of Past Research: Using Generative AI to Reconstruct Healthcare Simulation Models","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2508.19393","title":"GENIE-ASI: Generative Instruction and Executable Code for Analog Subcircuit Identification","created":"2025-08-26","cited_by_count":2,"area":null},{"id":"2602.15843","title":"The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts","created":"2026-01-21","cited_by_count":2,"area":"lr"},{"id":"2501.19204","title":"Autonomous Legacy Web Application Upgrades Using a Multi-Agent System","created":"2025-01-31","cited_by_count":1,"area":"agents"},{"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":"2505.03818","title":"Program Semantic Inequivalence Game with Large Language Models","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2505.05584","title":"PRIMG : Efficient LLM-driven Test Generation Using Mutant Prioritization","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2507.18812","title":"MemoCoder: Automated Function Synthesis using LLM-Supported Agents","created":"2025-07-24","cited_by_count":1,"area":"agents"},{"id":"2601.15728","title":"Benchmarking Text-to-Python against Text-to-SQL: The Impact of Explicit Logic and Ambiguity","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2608.30478","title":"Agents in the Large: Perception-Centered Architecture for Persistent Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2503.14838","title":"Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning","created":"2025-03-19","cited_by_count":0,"area":"lr"},{"id":"2506.12014","title":"code_transformed: The Influence of Large Language Models on Code","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2507.19390","title":"ReCatcher: Towards LLMs Regression Testing for Code Generation","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2508.20119","title":"LLM Agents for Generating Microservice-based Applications: how complex is your specification?","created":"2025-08-22","cited_by_count":0,"area":"agents"},{"id":"2509.20172","title":"Benchmarking Web API Integration Code Generation","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.10216","title":"Learning to Guarantee Type Correctness in Code Generation through Type-Guided Program Synthesis","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2510.11516","title":"Cracking CodeWhisperer: Analyzing Developers' Interactions and Patterns During Programming Tasks","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2510.22614","title":"Does In-IDE Calibration of Large Language Models work at Scale?","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2511.10899","title":"From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models","created":"2025-11-14","cited_by_count":0,"area":"lr"},{"id":"2604.19826","title":"Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.10598","title":"Budget-Efficient Automatic Algorithm Design via Code Graph","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.05936","title":"Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding","created":"2026-07-07","cited_by_count":0,"area":"rag"},{"id":"2607.10187","title":"Knowledge-Conditioned, Single-Pass LLM Synthesis of Executable Unity Game Scenes: A Compiler Error Census across 26 Goal Playable Concepts","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.18161","title":"TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2609.12708","title":"What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.15482","title":"Security in LLM-Assisted Coding: A Systematic Literature Review","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}