{"total":181,"rows":[{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634,"area":"wm"},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"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":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178,"area":"agents"},{"id":"2410.14684","title":"RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph","created":"2024-10-03","cited_by_count":91,"area":null},{"id":"2401.10034","title":"Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap","created":"2024-01-18","cited_by_count":90,"area":null},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86,"area":"agents"},{"id":"2402.02037","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","created":"2024-02-03","cited_by_count":64,"area":null},{"id":"2508.16949","title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning","created":"2025-08-23","cited_by_count":63,"area":"lr"},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"area":"agents"},{"id":"2403.16437","title":"Reasoning Runtime Behavior of a Program with LLM: How Far Are We?","created":"2024-03-25","cited_by_count":45,"area":"lr"},{"id":"2402.05200","title":"Are LLMs Ready for Real-World Materials Discovery?","created":"2024-02-07","cited_by_count":40,"area":null},{"id":"2503.14443","title":"EnvBench: A Benchmark for Automated Environment Setup","created":"2025-03-18","cited_by_count":36,"area":null},{"id":"2407.07959","title":"Source Code Summarization in the Era of Large Language Models","created":"2024-07-09","cited_by_count":31,"area":null},{"id":"2405.15189","title":"EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization","created":"2024-05-24","cited_by_count":30,"area":null},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2506.16395","title":"OJBench: A Competition Level Code Benchmark For Large Language Models","created":"2025-06-19","cited_by_count":26,"area":"lr"},{"id":"2501.12862","title":"Mutation-Guided LLM-based Test Generation at Meta","created":"2025-01-22","cited_by_count":25,"area":null},{"id":"2406.00215","title":"HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent","created":"2024-05-31","cited_by_count":24,"area":"agents"},{"id":"2406.07737","title":"The Future of AI-Driven Software Engineering","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2412.06294","title":"Beyond pip install: Evaluating LLM Agents for the Automated Installation of Python Projects","created":"2024-12-09","cited_by_count":21,"area":"agents"},{"id":"2402.01386","title":"Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis","created":"2024-02-02","cited_by_count":20,"area":"agents"},{"id":"2510.25694","title":"Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents","created":"2025-10-29","cited_by_count":18,"area":"agents"},{"id":"2406.10300","title":"Large Language Models as Software Components: A Taxonomy for LLM-Integrated Applications","created":"2024-06-13","cited_by_count":17,"area":null},{"id":"2501.12934","title":"Correctness Assessment of Code Generated by Large Language Models Using Internal Representations","created":"2025-01-22","cited_by_count":17,"area":null},{"id":"2411.01063","title":"InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation","created":"2024-11-01","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":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","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":"2602.17037","title":"Wink: Recovering from Misbehaviors in Coding Agents","created":"2026-02-19","cited_by_count":15,"area":"agents"},{"id":"2410.17375","title":"AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration","created":"2024-10-22","cited_by_count":14,"area":"inference"},{"id":"2503.24260","title":"MaintainCoder: Maintainable Code Generation Under Dynamic Requirements","created":"2025-03-31","cited_by_count":14,"area":null},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2404.07940","title":"InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models","created":"2024-03-11","cited_by_count":13,"area":null},{"id":"2504.20462","title":"TAMO: Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent with Multi-Modality Observation Data in Cloud-Native Systems","created":"2025-04-29","cited_by_count":13,"area":"agents"},{"id":"2602.01785","title":"Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding","created":"2026-02-02","cited_by_count":13,"area":"mllm"},{"id":"2406.01698","title":"Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models","created":"2024-06-03","cited_by_count":12,"area":"inference"},{"id":"2510.25506","title":"Reflections on the Reproducibility of Commercial LLM Performance in Empirical Software Engineering Studies","created":"2025-10-29","cited_by_count":12,"area":null},{"id":"2404.06371","title":"Model Generation with LLMs: From Requirements to UML Sequence Diagrams","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2407.12522","title":"Struct-X: Enhancing Large Language Models Reasoning with Structured Data","created":"2024-07-17","cited_by_count":11,"area":"lr"},{"id":"2408.11710","title":"Leveraging Large Language Models for Enhancing the Understandability of Generated Unit Tests","created":"2024-08-21","cited_by_count":11,"area":null},{"id":"2407.11470","title":"Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2409.15204","title":"RAMBO: Enhancing RAG-based Repository-Level Method Body Completion","created":"2024-09-23","cited_by_count":10,"area":null},{"id":"2505.20127","title":"Agentic AI Process Observability: Discovering Behavioral Variability","created":"2025-05-26","cited_by_count":10,"area":"agents"},{"id":"2312.14856","title":"Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code","created":"2023-12-22","cited_by_count":9,"area":null},{"id":"2403.17214","title":"Output Format Biases in the Evaluation of Large Language Models for Code Translation","created":"2024-03-25","cited_by_count":9,"area":null},{"id":"2408.04820","title":"Natural Language Outlines for Code: Literate Programming in the LLM Era","created":"2024-08-09","cited_by_count":9,"area":null},{"id":"2408.10210","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","created":"2024-07-12","cited_by_count":9,"area":"distill"},{"id":"2412.11698","title":"On Large Language Models in Mission-Critical IT Governance: Are We Ready Yet?","created":"2024-12-16","cited_by_count":9,"area":null},{"id":"2407.01646","title":"ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization","created":"2024-07-01","cited_by_count":8,"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":"2502.04008","title":"Automating a Complete Software Test Process Using LLMs: An Automotive Case Study","created":"2025-02-06","cited_by_count":8,"area":null},{"id":"2507.14230","title":"Intent-Based Network for RAN Management with Large Language Models","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2409.10033","title":"Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugs","created":"2024-09-16","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":"2508.14727","title":"Assessing the Quality and Security of AI-Generated Code: A Quantitative Analysis","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2404.08517","title":"Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward","created":"2024-04-12","cited_by_count":6,"area":null},{"id":"2408.03964","title":"Telecom Foundation Models: Applications, Challenges, and Future Trends","created":"2024-08-02","cited_by_count":6,"area":null},{"id":"2410.09012","title":"Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2603.16475","title":"Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures","created":"2026-03-17","cited_by_count":6,"area":"lr"},{"id":"2402.09615","title":"API Pack: A Massive Multi-Programming Language Dataset for API Call Generation","created":"2024-02-14","cited_by_count":5,"area":null},{"id":"2411.04156","title":"Crystal: Illuminating LLM Abilities on Language and Code","created":"2024-11-06","cited_by_count":5,"area":null},{"id":"2503.15079","title":"LogiAgent: Automated Logical Testing for REST Systems with LLM-Based Multi-Agents","created":"2025-03-19","cited_by_count":5,"area":"agents"},{"id":"2505.04406","title":"YABLoCo: Yet Another Benchmark for Long Context Code Generation","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2310.14211","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2406.03376","title":"Log Parsing using LLMs with Self-Generated In-Context Learning and Self-Correction","created":"2024-06-05","cited_by_count":4,"area":"synth"},{"id":"2411.08254","title":"Toward Automated Validation of Language Model Synthesized Test Cases using Semantic Entropy","created":"2024-11-13","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2504.08207","title":"DRAFT-ing Architectural Design Decisions using LLMs","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2507.03156","title":"The Impact of LLM-Assistants on Software Developer Productivity: A Systematic Review and Mapping Study","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2508.02611","title":"Meta-RAG on Large Codebases Using Code Summarization","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2508.08661","title":"Hallucinations in Code Change to Natural Language Generation: Prevalence and Evaluation of Detection Metrics","created":"2025-08-12","cited_by_count":4,"area":null},{"id":"2508.19558","title":"Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking","created":"2025-08-27","cited_by_count":4,"area":"synth"},{"id":"2511.01348","title":"The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2605.00073","title":"AgentReputation: A Decentralized Agentic AI Reputation Framework","created":"2026-04-30","cited_by_count":4,"area":"agents"},{"id":"2406.11439","title":"GPT-Powered Elicitation Interview Script Generator for Requirements Engineering Training","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2504.13769","title":"Detecting Malicious Source Code in PyPI Packages with LLMs: Does RAG Come in Handy?","created":"2025-04-18","cited_by_count":3,"area":"rag"},{"id":"2504.18693","title":"Technical Challenges in Maintaining Tax Prep Software with Large Language Models","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2506.13171","title":"Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches","created":"2025-06-16","cited_by_count":3,"area":"agents"},{"id":"2509.05540","title":"Combining TSL and LLM to Automate REST API Testing: A Comparative Study","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2510.21513","title":"Wisdom and Delusion of LLM Ensembles for Code Generation and Repair","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2510.22944","title":"Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2602.08915","title":"Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance","created":"2026-02-09","cited_by_count":3,"area":"agents"},{"id":"2602.20934","title":"Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence","created":"2026-02-24","cited_by_count":3,"area":"lr"},{"id":"2603.07287","title":"Do Deployment Constraints Make LLMs Hallucinate Citations? An Empirical Study across Four Models and Five Prompting Regimes","created":"2026-03-07","cited_by_count":3,"area":null},{"id":"2404.09249","title":"Test Code Generation for Telecom Software Systems using Two-Stage Generative Model","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2404.09384","title":"Generative transformations and patterns in LLM-native approaches for software verification and falsification","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2408.09735","title":"Icing on the Cake: Automatic Code Summarization at Ericsson","created":"2024-08-19","cited_by_count":2,"area":null},{"id":"2411.10842","title":"CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkit","created":"2024-11-16","cited_by_count":2,"area":null},{"id":"2502.10696","title":"Improving Retrieval-Augmented Deep Assertion Generation via Joint Training","created":"2025-02-15","cited_by_count":2,"area":"rag"},{"id":"2503.23466","title":"Codehacks: A Dataset of Adversarial Tests for Competitive Programming Problems Obtained from Codeforces","created":"2025-03-30","cited_by_count":2,"area":null},{"id":"2504.17198","title":"Automatically Generating Rules of Malicious Software Packages via Large Language Model","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2505.19310","title":"Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarking","created":"2025-05-25","cited_by_count":2,"area":"rag"},{"id":"2507.15157","title":"Can LLMs Generate User Stories and Assess Their Quality?","created":"2025-07-20","cited_by_count":2,"area":null},{"id":"2508.09648","title":"ReqInOne: A Large Language Model-Based Agent for Software Requirements Specification Generation","created":"2025-08-13","cited_by_count":2,"area":"agents"},{"id":"2510.11218","title":"The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form Answers","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2604.15468","title":"The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE","created":"2026-04-16","cited_by_count":2,"area":"agents"},{"id":"2606.07314","title":"QBugLM: An Agentic Benchmarking Framework for LLM-based Quantum Software Debugging","created":"2026-06-05","cited_by_count":2,"area":"agents"},{"id":"2402.01663","title":"Killer Apps: Low-Speed, Large-Scale AI Weapons","created":"2024-01-14","cited_by_count":1,"area":null}],"next_cursor":"100"}