{"total":137,"rows":[{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2407.04973","title":"LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts","created":"2024-07-06","cited_by_count":245,"area":"lr"},{"id":"2408.04667","title":"Non-Determinism of \"Deterministic\" LLM Settings","created":"2024-08-06","cited_by_count":92,"area":null},{"id":"2311.08596","title":"Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment","created":"2023-11-14","cited_by_count":77,"area":null},{"id":"2402.18225","title":"CogBench: a large language model walks into a psychology lab","created":"2024-02-28","cited_by_count":63,"area":null},{"id":"2402.12329","title":"Query-Based Adversarial Prompt Generation","created":"2024-02-19","cited_by_count":62,"area":"alignment"},{"id":"2506.09501","title":"Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference","created":"2025-06-11","cited_by_count":53,"area":null},{"id":"2403.14541","title":"EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling","created":"2024-03-21","cited_by_count":45,"area":null},{"id":"2312.17476","title":"Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameters","created":"2023-12-29","cited_by_count":32,"area":null},{"id":"2402.09664","title":"CodeMind: Evaluating Large Language Models for Code Reasoning","created":"2024-02-15","cited_by_count":32,"area":"lr"},{"id":"2405.19616","title":"Easy Problems That LLMs Get Wrong","created":"2024-05-30","cited_by_count":30,"area":"lr"},{"id":"2505.21298","title":"Large Language Models Miss the Multi-Agent Mark","created":"2025-05-27","cited_by_count":26,"area":"agents"},{"id":"2409.08775","title":"What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use","created":"2024-09-13","cited_by_count":24,"area":null},{"id":"2502.15844","title":"Hallucination Detection in Large Language Models with Metamorphic Relations","created":"2025-02-20","cited_by_count":24,"area":null},{"id":"2311.11123","title":"(Why) Is My Prompt Getting Worse? Rethinking Regression Testing for Evolving LLM APIs","created":"2023-11-18","cited_by_count":23,"area":"lr"},{"id":"2408.08333","title":"CodeMirage: Hallucinations in Code Generated by Large Language Models","created":"2024-08-14","cited_by_count":23,"area":null},{"id":"2510.21236","title":"AgentBound: Securing Execution Boundaries of AI Agents","created":"2025-10-24","cited_by_count":23,"area":"agents"},{"id":"2501.17167","title":"QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks","created":"2025-01-20","cited_by_count":22,"area":"agents"},{"id":"2312.06056","title":"METAL: Metamorphic Testing Framework for Analyzing Large-Language Model Qualities","created":"2023-12-11","cited_by_count":20,"area":null},{"id":"2505.16222","title":"Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation","created":"2025-05-22","cited_by_count":18,"area":null},{"id":"2404.03398","title":"Scaling Up Video Summarization Pretraining with Large Language Models","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2602.07150","title":"On Randomness in Agentic Evals","created":"2026-02-06","cited_by_count":17,"area":"agents"},{"id":"2504.16429","title":"Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection","created":"2025-04-23","cited_by_count":16,"area":"rag"},{"id":"2509.11252","title":"Exploring the Potential of Diffusion Large Language Models in Code Generation","created":"2025-09-14","cited_by_count":16,"area":null},{"id":"2509.13941","title":"An Empirical Study on Failures in Automated Issue Solving","created":"2025-09-17","cited_by_count":16,"area":"agents"},{"id":"2310.06680","title":"Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach","created":"2023-10-10","cited_by_count":15,"area":null},{"id":"2410.09112","title":"HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction","created":"2024-10-10","cited_by_count":15,"area":null},{"id":"2412.04494","title":"MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification","created":"2024-11-28","cited_by_count":12,"area":"agents"},{"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":"2411.00585","title":"Fairness Testing of Large Language Models in Role-Playing","created":"2024-11-01","cited_by_count":11,"area":null},{"id":"2507.01438","title":"EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices","created":"2025-07-02","cited_by_count":11,"area":"inference"},{"id":"2605.26563","title":"TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems","created":"2026-05-26","cited_by_count":11,"area":"agents"},{"id":"2309.16573","title":"Language Models as a Service: Overview of a New Paradigm and its Challenges","created":"2023-09-28","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":"2511.19933","title":"Failure Modes in LLM Systems: A System-Level Taxonomy for Reliable AI Applications","created":"2025-11-25","cited_by_count":10,"area":null},{"id":"2403.03997","title":"Guiding Enumerative Program Synthesis with Large Language Models","created":"2024-03-06","cited_by_count":9,"area":null},{"id":"2409.00921","title":"Statically Contextualizing Large Language Models with Typed Holes","created":"2024-09-02","cited_by_count":9,"area":null},{"id":"2502.03233","title":"Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation","created":"2025-02-05","cited_by_count":9,"area":"rag"},{"id":"2601.15322","title":"Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents","created":"2026-01-17","cited_by_count":7,"area":"agents"},{"id":"2602.23330","title":"Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks","created":"2026-02-26","cited_by_count":7,"area":"agents"},{"id":"2401.16310","title":"An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors","created":"2024-01-29","cited_by_count":6,"area":"lr"},{"id":"2402.15943","title":"Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware","created":"2024-02-25","cited_by_count":6,"area":null},{"id":"2406.06864","title":"Validating LLM-Generated Programs with Metamorphic Prompt Testing","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2410.07391","title":"The Cognitive Capabilities of Generative AI: A Comparative Analysis with Human Benchmarks","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2601.15232","title":"When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling","created":"2026-01-21","cited_by_count":6,"area":"agents"},{"id":"2403.08430","title":"Search-based Optimisation of LLM Learning Shots for Story Point Estimation","created":"2024-03-13","cited_by_count":5,"area":null},{"id":"2501.11354","title":"Towards Advancing Code Generation with Large Language Models: A Research Roadmap","created":"2025-01-20","cited_by_count":5,"area":null},{"id":"2503.06791","title":"AutoMisty: A Multi-Agent LLM Framework for Automated Code Generation in the Misty Social Robot","created":"2025-03-09","cited_by_count":5,"area":"agents"},{"id":"2401.17626","title":"Generative AI to Generate Test Data Generators","created":"2024-01-31","cited_by_count":4,"area":null},{"id":"2407.09974","title":"To what extent is ChatGPT useful for language teacher lesson plan creation?","created":"2024-04-25","cited_by_count":4,"area":null},{"id":"2410.07793","title":"Do Current Language Models Support Code Intelligence for R Programming Language?","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2412.11761","title":"Harnessing Language for Coordination: A Framework and Benchmark for LLM-Driven Multi-Agent Control","created":"2024-12-16","cited_by_count":4,"area":"agents"},{"id":"2502.20825","title":"LADs: Leveraging LLMs for AI-Driven DevOps","created":"2025-02-28","cited_by_count":4,"area":null},{"id":"2504.03714","title":"Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models","created":"2025-03-28","cited_by_count":4,"area":"mllm"},{"id":"2604.05150","title":"Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2607.13304","title":"Where Does the Noise Come From? A Variance-Components Decomposition of Non-Determinism in LLM Brand Answers","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2401.07994","title":"Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2402.01723","title":"An Empirical Study on Large Language Models in Accuracy and Robustness under Chinese Industrial Scenarios","created":"2024-01-27","cited_by_count":3,"area":null},{"id":"2407.21227","title":"TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2409.15324","title":"Cognitive phantoms in LLMs through the lens of latent variables","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2502.18487","title":"AuPair: Golden Example Pairs for Code Repair","created":"2025-02-12","cited_by_count":3,"area":"lr"},{"id":"2509.09705","title":"The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2602.05883","title":"A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2602.19948","title":"Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming","created":"2026-02-23","cited_by_count":3,"area":"safety"},{"id":"2604.13413","title":"Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models","created":"2026-04-15","cited_by_count":3,"area":"diffusion"},{"id":"2607.15684","title":"Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reports","created":"2026-07-17","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2312.13521","title":"Preparing to Integrate Generative Pretrained Transformer Series 4 models into Genetic Variant Assessment Workflows: Assessing Performance, Drift, and Nondeterminism Characteristics Relative to Classifying Functional Evidence in Literature","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2408.02964","title":"Accuracy and Consistency of LLMs in the Registered Dietitian Exam: The Impact of Prompt Engineering and Knowledge Retrieval","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2506.18783","title":"TRIZ Agents: A Multi-Agent LLM Approach for TRIZ-Based Innovation","created":"2025-06-23","cited_by_count":2,"area":"agents"},{"id":"2508.11257","title":"Hallucination in LLM-Based Code Generation: An Automotive Case Study","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2508.14288","title":"Measuring LLM Code Generation Stability via Structural Entropy","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2508.16646","title":"Equinox: Holistic Fair Scheduling in Serving Large Language Models","created":"2025-08-19","cited_by_count":2,"area":"inference"},{"id":"2510.03795","title":"Investigating LLM Variability in Personalized Conversational Information Retrieval","created":"2025-10-04","cited_by_count":2,"area":null},{"id":"2601.10220","title":"Agentic Pipelines in Embedded Software Engineering: Emerging Practices and Challenges","created":"2026-01-15","cited_by_count":2,"area":"agents"},{"id":"2602.08565","title":"Agent-Supported Foresight for AI Systemic Risks: AI Agents for Breadth, Experts for Judgment","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2604.09552","title":"MCERF: Advancing Multimodal LLM Evaluation of Engineering Documentation with Enhanced Retrieval","created":"2026-01-31","cited_by_count":2,"area":"rag"},{"id":"2604.22411","title":"Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2607.00911","title":"From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2607.02436","title":"Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study","created":"2026-07-02","cited_by_count":2,"area":"lr"},{"id":"2312.17353","title":"Towards Auto-Modeling of Formal Verification for NextG Protocols: A Multimodal cross- and self-attention Large Language Model Approach","created":"2023-12-28","cited_by_count":1,"area":null},{"id":"2405.14075","title":"$T^2$ of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models","created":"2024-05-23","cited_by_count":1,"area":"lr"},{"id":"2412.10587","title":"Evaluation of GPT-4o and GPT-4o-mini's Vision Capabilities for Compositional Analysis from Dried Solution Drops","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2501.00691","title":"Labels Generated by Large Language Models Help Measure People's Empathy in Vitro","created":"2025-01-01","cited_by_count":1,"area":null},{"id":"2501.06461","title":"Assessing instructor-AI cooperation for grading essay-type questions in an introductory sociology course","created":"2025-01-11","cited_by_count":1,"area":null},{"id":"2504.16485","title":"On Developers' Self-Declaration of AI-Generated Code: An Analysis of Practices","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2504.17531","title":"Towards Machine-Generated Code for the Resolution of User Intentions","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2505.15088","title":"Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.19353","title":"Architectures of Error: A Philosophical Inquiry into AI and Human Code Generation","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2506.17367","title":"Cash or Comfort? How LLMs Value Your Inconvenience","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2507.23087","title":"On LLM-Assisted Generation of Smart Contracts from Business Processes","created":"2025-07-30","cited_by_count":1,"area":null},{"id":"2509.13345","title":"Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2510.02679","title":"Automated Constraint Specification for Job Scheduling by Regulating Generative Model with Domain-Specific Representation","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2512.07276","title":"Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagery","created":"2025-12-08","cited_by_count":1,"area":"lr"},{"id":"2512.23711","title":"CAT: A Metric-Driven Framework for Analyzing the Consistency-Accuracy Relation of LLMs under Controlled Input Variations","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2601.05579","title":"RISE: Rule-Driven SQL Dialect Translation via Query Reduction","created":"2026-01-09","cited_by_count":1,"area":null},{"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":"2602.06190","title":"Generics in science communication: Misaligned interpretations across laypeople, scientists, and large language models","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2604.16756","title":"Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2605.02431","title":"ARIADNE: Agentic Reward-Informed Adaptive Decision Exploration via Blackboard-Driven MCTS for Competitive Program Generation","created":"2026-05-04","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}