{"total":72,"rows":[{"id":"2505.22954","title":"Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents","created":"2025-05-29","cited_by_count":356,"area":"agents"},{"id":"2509.18091","title":"OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System","created":"2025-09-22","cited_by_count":18,"area":"lr"},{"id":"2409.02231","title":"SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration","created":"2024-09-03","cited_by_count":14,"area":"alignment"},{"id":"2505.24214","title":"Benchmarking Foundation Models for Zero-Shot Biometric Tasks","created":"2025-05-30","cited_by_count":14,"area":"mllm"},{"id":"2507.19634","title":"MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks","created":"2025-07-25","cited_by_count":14,"area":"mllm"},{"id":"2402.16929","title":"LangGPT: Rethinking Structured Reusable Prompt Design Framework for LLMs from the Programming Language","created":"2024-02-26","cited_by_count":12,"area":"lr"},{"id":"2407.03179","title":"Motion meets Attention: Video Motion Prompts","created":"2024-07-03","cited_by_count":12,"area":null},{"id":"2507.14241","title":"Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models","created":"2025-07-17","cited_by_count":12,"area":null},{"id":"2511.02108","title":"Metamorphic Testing of Large Language Models for Natural Language Processing","created":"2025-11-03","cited_by_count":12,"area":null},{"id":"2410.12071","title":"Beyond the Comfort Zone: Emerging Solutions to Overcome Challenges in Integrating LLMs into Software Products","created":"2024-10-15","cited_by_count":11,"area":null},{"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":"2407.10380","title":"NTSEBENCH: Cognitive Reasoning Benchmark for Vision Language Models","created":"2024-07-15","cited_by_count":9,"area":"lr"},{"id":"2604.16403","title":"Computational Hermeneutics: Evaluating generative AI as a cultural technology","created":"2026-03-31","cited_by_count":8,"area":null},{"id":"2406.00367","title":"RoBERTa-BiLSTM: A Context-Aware Hybrid Model for Sentiment Analysis","created":"2024-06-01","cited_by_count":7,"area":null},{"id":"2505.11665","title":"Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2505.15741","title":"Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2403.00188","title":"Impact of Decentralized Learning on Player Utilities in Stackelberg Games","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2501.10542","title":"Improved IR-based Bug Localization with Intelligent Relevance Feedback","created":"2025-01-17","cited_by_count":5,"area":null},{"id":"2501.11864","title":"LLM-Agents Driven Automated Simulation Testing and Analysis of small Uncrewed Aerial Systems","created":"2025-01-21","cited_by_count":4,"area":"agents"},{"id":"2510.11195","title":"RAG-Pull: Turning Retrieval into a Code-Injection Channel via Invisible Unicode Perturbations","created":"2025-10-13","cited_by_count":4,"area":"rag"},{"id":"2411.02455","title":"A Course Intelligence Platform for Higher Education: Lessons from AI-Assisted Course Evaluation","created":"2024-11-03","cited_by_count":3,"area":null},{"id":"2504.20946","title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","created":"2025-04-29","cited_by_count":3,"area":"lr"},{"id":"2505.11856","title":"Telco-oRAG: Optimizing Retrieval-augmented Generation for Telecom Queries via Hybrid Retrieval and Neural Routing","created":"2025-05-17","cited_by_count":3,"area":"rag"},{"id":"2506.07436","title":"Prompt to Protection: A Comparative Study of Multimodal LLMs in Construction Hazard Recognition","created":"2025-06-09","cited_by_count":3,"area":"mllm"},{"id":"2510.06931","title":"Textual interpretation of transient image classifications from large language models","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2605.12904","title":"VIP-COP: Context Optimization for Tabular Foundation Models","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2409.00286","title":"OnlySportsLM: Optimizing Sports-Domain Language Models with SOTA Performance under Billion Parameters","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2409.00413","title":"iToT: An Interactive System for Customized Tree-of-Thought Generation","created":"2024-08-31","cited_by_count":2,"area":"lr"},{"id":"2506.10157","title":"One Patient, Many Contexts: Scaling Medical AI with Contextual Intelligence","created":"2025-06-11","cited_by_count":2,"area":"mllm"},{"id":"2507.22936","title":"Evaluating Large Language Models (LLMs) in Financial NLP: A Comparative Study on Financial Report Analysis","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2509.12645","title":"Large Language Models Imitate Logical Reasoning, but at what Cost?","created":"2025-09-16","cited_by_count":2,"area":"lr"},{"id":"2605.24171","title":"PromptAudit: Auditing Prompt Sensitivity in LLM-Based Vulnerability Detection","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2407.20244","title":"Steamroller Problems: An Evaluation of LLM Reasoning Capability with Automated Theorem Prover Strategies","created":"2024-07-17","cited_by_count":1,"area":"lr"},{"id":"2408.04816","title":"FUSE-ing Language Models: Zero-Shot Adapter Discovery for Prompt Optimization Across Tokenizers","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2411.07398","title":"Beyond Keywords: A Context-based Hybrid Approach to Mining Ethical Concern-related App Reviews","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2412.03693","title":"System Test Case Design from Requirements Specifications: Insights and Challenges of Using ChatGPT","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2502.13349","title":"Event Segmentation Applications in Large Language Model Enabled Automated Recall Assessments","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2505.06280","title":"Show or Tell? A Benchmark To Evaluate Visual and Textual Prompts in Semantic Segmentation","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2505.23410","title":"From Parameters to Prompts: Understanding and Mitigating the Factuality Gap between Fine-Tuned LLMs","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.03620","title":"Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPy","created":"2025-07-04","cited_by_count":1,"area":"safety"},{"id":"2510.09970","title":"Follow My Lead: Logical Fallacy Classification with Knowledge-Augmented LLMs","created":"2025-10-11","cited_by_count":1,"area":"lr"},{"id":"2510.22628","title":"Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts","created":"2025-10-26","cited_by_count":1,"area":"safety"},{"id":"2510.23824","title":"Decentralized Multi-Agent Goal Assignment for Path Planning using Large Language Models","created":"2025-10-27","cited_by_count":1,"area":"agents"},{"id":"2601.08061","title":"Universal computation is intrinsic to language model decoding","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2601.11910","title":"A Training-Free Guess What Vision Language Model from Snippets to Open-Vocabulary Object Detection","created":"2026-01-17","cited_by_count":1,"area":"mllm"},{"id":"2603.15909","title":"Prompt Engineering for Scale Development in Generative Psychometrics","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2604.16420","title":"Breaking Validity-Induced Boundaries to Expand Algorithm Search Space: A Two-Stage AST-Based Operator for LLM-Driven Automated Heuristic Evolution","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2605.07799","title":"Toward Privileged Foundation Models:LUPI for Accelerated and Improved Learning","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.13221","title":"An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2607.03615","title":"The Powerless Noise: How Experimental Settings Shape the Reported Power of Noise","created":"2026-07-03","cited_by_count":1,"area":"rag"},{"id":"2608.07494","title":"How to Ask the AI: A User Perspective Survey for Large Language Model Prompting","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2608.26291","title":"Assessing mentalization in humans and large language models","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2507.21532","title":"Automatic Classification of User Requirements from Online Feedback -- A Replication Study","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2510.02326","title":"Hallucination-Resistant, Domain-Specific Research Assistant with Self-Evaluation and Vector-Grounded Retrieval","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.06997","title":"The Limits of Goal-Setting Theory in LLM-Driven Assessment","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":"2511.04179","title":"Explaining Software Vulnerabilities with Large Language Models","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2511.20680","title":"Cognitive bias in LLM reasoning compromises interpretation of clinical oncology notes","created":"2025-11-16","cited_by_count":0,"area":"lr"},{"id":"2512.07474","title":"Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels","created":"2025-12-08","cited_by_count":0,"area":"agents"},{"id":"2602.10149","title":"Semantic Labeling for Third-Party Cybersecurity Risk Assessment: A Semi-Supervised Approach to Intent-Aware Question Retrieval","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.15645","title":"CARE Drive A Framework for Evaluating Reason-Responsiveness of Vision Language Models in Automated Driving","created":"2026-02-17","cited_by_count":0,"area":"lr"},{"id":"2603.12751","title":"Show, Don't Tell: Detecting Novel Objects by Watching Human Videos","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.17021","title":"Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.00046","title":"Large Language Models for Analyzing Enterprise Architecture Debt in Unstructured Documentation","created":"2026-03-29","cited_by_count":0,"area":null},{"id":"2604.15385","title":"Prompt-Driven Code Summarization: A Systematic Literature Review","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.09661","title":"MedMeta: A Benchmark for LLMs in Synthesizing Meta-Analysis Conclusion from Medical Studies","created":"2026-05-10","cited_by_count":0,"area":"rag"},{"id":"2605.10025","title":"Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.20149","title":"Less Back-and-Forth: A Comparative Study of Structured Prompting","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.12210","title":"Can News Predict the Market? Limits of Zero-Shot Financial NLP and the Role of Explainable AI","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.07533","title":"MetaSpace: Metamorphic Testing for Spatial Cognition in Embodied Agents","created":"2026-07-26","cited_by_count":0,"area":"agents"},{"id":"2608.12304","title":"Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Models","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.20966","title":"Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}