{"total":88,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232,"area":"agents"},{"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":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75,"area":"agents"},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2406.05498","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","created":"2024-06-08","cited_by_count":63,"area":"safety"},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62,"area":null},{"id":"2401.16185","title":"LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning","created":"2024-01-29","cited_by_count":59,"area":"lr"},{"id":"2309.07062","title":"Large Language Models for Compiler Optimization","created":"2023-09-11","cited_by_count":52,"area":null},{"id":"2412.10133","title":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","created":"2024-12-13","cited_by_count":47,"area":"agents"},{"id":"2308.09895","title":"Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs","created":"2023-08-19","cited_by_count":45,"area":null},{"id":"2408.05534","title":"Can LLMs Replace Manual Annotation of Software Engineering Artifacts?","created":"2024-08-10","cited_by_count":42,"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":"2401.10510","title":"When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges","created":"2024-01-19","cited_by_count":20,"area":null},{"id":"2312.15099","title":"Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models","created":"2023-12-22","cited_by_count":18,"area":"lr"},{"id":"2407.05138","title":"Are LLMs Correctly Integrated into Software Systems?","created":"2024-07-06","cited_by_count":15,"area":"rag"},{"id":"2410.21060","title":"CTINexus: Automatic Cyber Threat Intelligence Knowledge Graph Construction Using Large Language Models","created":"2024-10-28","cited_by_count":14,"area":null},{"id":"2310.19813","title":"Enhancing Genetic Improvement Mutations Using Large Language Models","created":"2023-10-18","cited_by_count":13,"area":null},{"id":"2502.18474","title":"A Contemporary Survey of Large Language Model Assisted Program Analysis","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2512.07533","title":"VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection","created":"2025-12-08","cited_by_count":11,"area":"lr"},{"id":"2402.15727","title":"LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper","created":"2024-02-24","cited_by_count":10,"area":"safety"},{"id":"2408.03519","title":"RepoMasterEval: Evaluating Code Completion via Real-World Repositories","created":"2024-08-07","cited_by_count":10,"area":null},{"id":"2508.05188","title":"Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination","created":"2025-08-07","cited_by_count":10,"area":null},{"id":"2508.21302","title":"Locus: Agentic Predicate Synthesis for Directed Fuzzing","created":"2025-08-29","cited_by_count":9,"area":"agents"},{"id":"2408.07846","title":"A System for Automated Unit Test Generation Using Large Language Models and Assessment of Generated Test Suites","created":"2024-08-14","cited_by_count":8,"area":null},{"id":"2502.00735","title":"`From Prompt to Perturbation': An Adaptive Framework for Voice-Based Jailbreaks on Audio LLMs","created":"2025-02-02","cited_by_count":7,"area":"safety"},{"id":"2504.18050","title":"Validating Network Protocol Parsers with Traceable RFC Document Interpretation","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2511.03995","title":"Hybrid Fuzzing with LLM-Guided Input Mutation and Semantic Feedback","created":"2025-11-06","cited_by_count":7,"area":null},{"id":"2511.17330","title":"Agentic Verification of Software Systems","created":"2025-11-21","cited_by_count":6,"area":"agents"},{"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":"2501.00655","title":"Finding Missed Code Size Optimizations in Compilers using LLMs","created":"2024-12-31","cited_by_count":5,"area":null},{"id":"2503.11185","title":"Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks","created":"2025-03-14","cited_by_count":5,"area":"safety"},{"id":"2507.22462","title":"IFEvalCode: Controlled Code Generation","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2512.04680","title":"Generative AI for Self-Adaptive Systems: State of the Art and Research Roadmap","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2605.25232","title":"Specification-Based Code-Text-Code Reengineering for LLM-Mediated Software Evolution","created":"2026-05-24","cited_by_count":5,"area":null},{"id":"2402.00350","title":"On the Challenges of Fuzzing Techniques via Large Language Models","created":"2024-02-01","cited_by_count":4,"area":null},{"id":"2505.15039","title":"LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2604.11950","title":"AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection","created":"2026-04-13","cited_by_count":4,"area":"agents"},{"id":"2404.06856","title":"Beyond Random Inputs: A Novel ML-Based Hardware Fuzzing","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2409.04597","title":"Detecting Buggy Contracts via Smart Testing","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2410.18957","title":"Bridge-Coder: Unlocking LLMs' Potential to Overcome Language Gaps in Low-Resource Code","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2507.15058","title":"LibLMFuzz: LLM-Augmented Fuzz Target Generation for Black-box Libraries","created":"2025-07-20","cited_by_count":3,"area":null},{"id":"2510.03879","title":"Adversarial Agent Collaboration for Correctness Improvements of C to Safe Rust Translation","created":"2025-10-04","cited_by_count":3,"area":"agents"},{"id":"2512.19297","title":"Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2603.20075","title":"Agentic Harness for Real-World Compilers","created":"2026-03-20","cited_by_count":3,"area":"agents"},{"id":"2605.21779","title":"FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction","created":"2026-05-20","cited_by_count":3,"area":"agents"},{"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":"2411.10842","title":"CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkit","created":"2024-11-16","cited_by_count":2,"area":null},{"id":"2501.12339","title":"Treefix: Enabling Execution with a Tree of Prefixes","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2507.09481","title":"Evaluating LLMs on Sequential API Call Through Automated Test Generation","created":"2025-07-13","cited_by_count":2,"area":"agents"},{"id":"2507.22065","title":"Fuzzing: Randomness? Reasoning! Efficient Directed Fuzzing via Large Language Models","created":"2025-06-30","cited_by_count":2,"area":"lr"},{"id":"2510.10066","title":"OBsmith: LLM-Powered JavaScript Obfuscator Testing","created":"2025-10-11","cited_by_count":2,"area":null},{"id":"2604.07624","title":"Program Analysis Guided LLM Agent for Proof-of-Concept Generation","created":"2026-04-08","cited_by_count":2,"area":"agents"},{"id":"2606.05548","title":"ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer","created":"2026-06-04","cited_by_count":2,"area":"agents"},{"id":"2607.02345","title":"SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2607.06195","title":"LogicHunter: Testing LLM Agent Frameworks with an Agentic Oracle","created":"2026-07-07","cited_by_count":2,"area":"agents"},{"id":"2502.15506","title":"Construction and Evaluation of LLM-based agents for Semi-Autonomous penetration testing","created":"2025-02-21","cited_by_count":1,"area":"agents"},{"id":"2506.15648","title":"deepSURF: Detecting Memory Safety Vulnerabilities in Rust Through Fuzzing LLM-Augmented Harnesses","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2506.17369","title":"Re-Evaluating Code LLM Benchmarks Under Semantic Mutation","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2509.23835","title":"HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2510.02694","title":"MALF: A Multi-Agent LLM Framework for Intelligent Fuzzing of Industrial Control Protocols","created":"2025-10-03","cited_by_count":1,"area":"agents"},{"id":"2511.20403","title":"LLMs for Automated Unit Test Generation and Assessment in Java: The AgoneTest Framework","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2602.05279","title":"Hallucination-Resistant Security Planning with a Large Language Model","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2603.17673","title":"Towards Reliable Local Security Agents: Verifiable Post-Training for Linux Privilege Escalation","created":"2026-03-18","cited_by_count":1,"area":"agents"},{"id":"2603.21530","title":"LLM-Based Test Case Generation in DBMS through Monte Carlo Tree Search","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2603.26270","title":"Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization","created":"2026-03-27","cited_by_count":1,"area":"agents"},{"id":"2605.11202","title":"Continuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing","created":"2026-05-11","cited_by_count":1,"area":"inference"},{"id":"2606.22263","title":"Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases","created":"2026-06-20","cited_by_count":1,"area":"agents"},{"id":"2608.06153","title":"Learning Globally Reusable Skills for Coding Agents","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2503.22575","title":"On the Mistaken Assumption of Interchangeable Deep Reinforcement Learning Implementations","created":"2025-03-28","cited_by_count":0,"area":"deeprl"},{"id":"2507.04055","title":"Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAG","created":"2025-07-05","cited_by_count":0,"area":null},{"id":"2508.20340","title":"Once4All: Skeleton-Guided SMT Solver Fuzzing with LLM-Synthesized Generators","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.19533","title":"Semantic-Aware Fuzzing: An Empirical Framework for LLM-Guided, Reasoning-Driven Input Mutation","created":"2025-09-23","cited_by_count":0,"area":"lr"},{"id":"2509.25196","title":"APRIL: API Synthesis with Automatic Prompt Optimization and Reinforcement Learning","created":"2025-08-29","cited_by_count":0,"area":"lr"},{"id":"2510.06645","title":"Distilling Lightweight Language Models for C/C++ Vulnerabilities","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2510.10179","title":"LLMs are All You Need? Improving Fuzz Testing for MOJO with Large Language Models","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2510.10407","title":"PrediQL: Automated Testing of GraphQL APIs with LLMs","created":"2025-10-12","cited_by_count":0,"area":"rag"},{"id":"2512.18102","title":"From Coverage to Causes: Data-Centric Fuzzing for JavaScript Engines","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2603.27247","title":"SCOPE: Tree-based Self-Correcting Online Log Parsing via Syntactic-Semantic Collaboration","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2605.05000","title":"Agentic Vulnerability Reasoning on COTS Binaries","created":"2026-05-06","cited_by_count":0,"area":"agents"},{"id":"2606.18619","title":"Code-Augur: Agentic Vulnerability Detection via Specification Inference","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2607.22898","title":"AssumptionMiner: Extracting, Tracing, and Revising Implicit Assumptions in LLM Code Generation","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.06397","title":"Agentic Planning for Symbolic Execution","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2608.07947","title":"Directed Neuro-Symbolic Stochastic Execution for Verification of Distributed Parallel AI Programs","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.13450","title":"LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.07434","title":"CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.23889","title":"SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.38275","title":"When Correct Memory Goes Wrong: Fuzzing Persistent Memory Use in LLM Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"}],"next_cursor":null}