{"total":121,"rows":[{"id":"2409.04109","title":"Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers","created":"2024-09-06","cited_by_count":363,"area":"agents"},{"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":"2606.09498","title":"Self-Harness: Harnesses That Improve Themselves","created":"2026-06-08","cited_by_count":107,"area":"agents"},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2502.18695","title":"Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models","created":"2025-02-25","cited_by_count":31,"area":"lr"},{"id":"2510.15831","title":"VISTA: A Test-Time Self-Improving Video Generation Agent","created":"2025-10-17","cited_by_count":31,"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":"2508.17692","title":"LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios","created":"2025-08-25","cited_by_count":26,"area":"lr"},{"id":"2509.22067","title":"The Rogue Scalpel: Activation Steering Compromises LLM Safety","created":"2025-09-26","cited_by_count":21,"area":"safety"},{"id":"2501.03544","title":"PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models","created":"2025-01-07","cited_by_count":17,"area":"safety"},{"id":"2509.25651","title":"AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation","created":"2025-09-30","cited_by_count":15,"area":null},{"id":"2509.14744","title":"On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code","created":"2025-09-18","cited_by_count":14,"area":"agents"},{"id":"2509.18052","title":"The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies","created":"2025-09-22","cited_by_count":14,"area":null},{"id":"2512.01939","title":"An Empirical Study of Agent Developer Practices in AI Agent Frameworks","created":"2025-12-01","cited_by_count":14,"area":"agents"},{"id":"2502.07980","title":"CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs","created":"2025-02-11","cited_by_count":11,"area":"lr"},{"id":"2504.07157","title":"GAAPO: Genetic Algorithmic Applied to Prompt Optimization","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2507.13369","title":"VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generation","created":"2025-07-09","cited_by_count":8,"area":null},{"id":"2605.22645","title":"AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters","created":"2026-05-21","cited_by_count":8,"area":"mllm"},{"id":"2503.10968","title":"Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms","created":"2025-03-14","cited_by_count":7,"area":null},{"id":"2504.16005","title":"CAPO: Cost-Aware Prompt Optimization","created":"2025-04-22","cited_by_count":7,"area":null},{"id":"2601.03808","title":"From Brute Force to Semantic Insight: Performance-Guided Data Transformation Design with LLMs","created":"2026-01-07","cited_by_count":7,"area":null},{"id":"2602.04755","title":"When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?","created":"2026-02-04","cited_by_count":7,"area":null},{"id":"2504.08804","title":"Estimating Item Difficulty Using Large Language Models and Tree-Based Machine Learning Algorithms","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2510.05192","title":"From surveillance to signalling: escalation channels as environmental controls for agentic AI","created":"2025-10-06","cited_by_count":6,"area":"agents"},{"id":"2601.18207","title":"PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR","created":"2026-01-26","cited_by_count":6,"area":"lr"},{"id":"2411.19589","title":"Can Large Language Models Reason about the Region Connection Calculus?","created":"2024-11-29","cited_by_count":5,"area":"lr"},{"id":"2505.12837","title":"The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2601.16356","title":"The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes","created":"2026-01-22","cited_by_count":4,"area":"agents"},{"id":"2605.29420","title":"When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2410.12886","title":"AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoning","created":"2024-10-16","cited_by_count":3,"area":"lr"},{"id":"2505.10870","title":"Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate","created":"2025-05-16","cited_by_count":3,"area":"lr"},{"id":"2506.00058","title":"Prompt Engineer: Analyzing Hard and Soft Skill Requirements in the AI Job Market","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2508.01554","title":"Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models","created":"2025-08-03","cited_by_count":3,"area":null},{"id":"2509.03117","title":"PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs","created":"2025-09-03","cited_by_count":3,"area":"safety"},{"id":"2510.07761","title":"Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers","created":"2025-10-09","cited_by_count":3,"area":"lr"},{"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":"2605.25354","title":"Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis","created":"2026-05-25","cited_by_count":3,"area":"lr"},{"id":"2412.15957","title":"Learning Personalized Prompts for Healthcare Guidance","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2506.14670","title":"StreetLens: Enabling Human-Centered AI Agents for Neighborhood Assessment from Street View Imagery","created":"2025-06-17","cited_by_count":2,"area":"agents"},{"id":"2506.20815","title":"Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2509.09544","title":"MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022-2025)","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2510.09316","title":"A Survey of LLM Prompt Datasets: Taxonomy, Linguistic Patterns, and Practical Uses","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2510.20743","title":"Empathic Prompting: Non-Verbal Context Integration for Multimodal LLM Conversations","created":"2025-10-23","cited_by_count":2,"area":"mllm"},{"id":"2510.26253","title":"Pragmatic Theories Enhance Understanding of Implied Meanings in LLMs","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2602.16930","title":"Say It My Way: Exploring Control in Conversational Visual Question Answering with Blind Users","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2603.03512","title":"Baseline Performance of AI Tools in Classifying Cognitive Demand of Mathematical Tasks","created":"2026-03-03","cited_by_count":2,"area":null},{"id":"2605.14553","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2409.16635","title":"Judgment-of-Thought Prompting: A Courtroom-Inspired Framework for Binary Logical Reasoning with Large Language Models","created":"2024-09-25","cited_by_count":1,"area":"lr"},{"id":"2504.06138","title":"Multimedia and Visual Analytics in the Agentic Era","created":"2025-04-08","cited_by_count":1,"area":"agents"},{"id":"2505.18978","title":"AI4Math: A Native Spanish Benchmark for University-Level Mathematical Reasoning in Large Language Models","created":"2025-05-25","cited_by_count":1,"area":"lr"},{"id":"2507.21790","title":"Can large language models assist choice modelling? Insights into prompting strategies and current models' capabilities","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2510.12829","title":"Mathematics with large language models as provers and verifiers","created":"2025-10-11","cited_by_count":1,"area":null},{"id":"2510.13884","title":"Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2510.19850","title":"Prompt Decorators: A Declarative and Composable Syntax for Reasoning, Formatting, and Control in LLMs","created":"2025-10-21","cited_by_count":1,"area":"lr"},{"id":"2512.04469","title":"Mathematical Framing for Different Agent Strategies","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2601.03988","title":"Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures","created":"2026-01-07","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":"2601.16038","title":"Grounding Large Language Models in Reaction Knowledge Graphs for Synthesis Retrieval","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2601.16568","title":"Predicting Startup Success Using Large Language Models: A Novel In-Context Learning Approach","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.04813","title":"Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents","created":"2026-02-04","cited_by_count":1,"area":"agents"},{"id":"2602.09475","title":"ArtifactLens: Hundreds of Labels Are Enough for Artifact Detection with VLMs","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.15909","title":"Prompt Engineering for Scale Development in Generative Psychometrics","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.16827","title":"Prompt Programming for Cultural Bias and Alignment of Large Language Models","created":"2026-03-17","cited_by_count":1,"area":"alignment"},{"id":"2604.04258","title":"Context Engineering: A Practitioner Methodology for Structured Human-AI Collaboration","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2605.04534","title":"Characterizing Students' LLM Usage Behaviors and Their Association with Learning in Critical Thinking Tasks","created":"2026-05-06","cited_by_count":1,"area":"lr"},{"id":"2605.07422","title":"Prompt Engineering Strategies for LLM-based Qualitative Coding of Psychological Safety in Software Engineering Communities: A Controlled Empirical Study","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.26731","title":"It's Not the Capability: Harness Sensitivity Is Non-Monotone Across LLM Agent Tiers","created":"2026-05-26","cited_by_count":1,"area":"agents"},{"id":"2607.27578","title":"What makes prompts a graph: necessary and sufficient conditions for prompt graph engineering","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2410.18105","title":"Improving Embedding Accuracy for Document Retrieval Using Entity Relationship Maps and Model-Aware Contrastive Sampling","created":"2024-10-08","cited_by_count":0,"area":"rag"},{"id":"2503.15205","title":"A Peek Behind the Curtain: Using Step-Around Prompt Engineering to Identify Bias and Misinformation in GenAI Models","created":"2025-03-19","cited_by_count":0,"area":"safety"},{"id":"2503.16728","title":"Natural Language Generation","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2504.07277","title":"Agentic LMs: Hunting Down Test Smells","created":"2025-04-09","cited_by_count":0,"area":"agents"},{"id":"2506.11681","title":"A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentences","created":"2025-06-13","cited_by_count":0,"area":"agents"},{"id":"2506.13172","title":"AI-Facilitated Analysis of Abstracts and Conclusions: Flagging Unsubstantiated Claims and Ambiguous Pronouns","created":"2025-06-16","cited_by_count":0,"area":"lr"},{"id":"2508.10011","title":"Evaluation of GPT-based large language generative AI models as study aids for the national licensure examination for registered dietitians in Japan","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2508.10414","title":"MCP2OSC: Parametric Control by Natural Language","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2508.18870","title":"ReflectivePrompt: Reflective evolution in autoprompting algorithms","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2509.05375","title":"Characterizing Fitness Landscape Structures in Prompt Engineering","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2509.11295","title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2510.00555","title":"PromptPilot: Improving Human-AI Collaboration Through LLM-Enhanced Prompt Engineering","created":"2025-10-01","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":"2510.19173","title":"News-Aware Direct Reinforcement Trading for Financial Markets","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2511.09571","title":"General Intelligence-based Fragmentation (GIF): A framework for peak-labeled spectra simulation","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2512.15816","title":"A Neurosymbolic Approach to Loop Invariant Generation via Weakest Precondition Reasoning","created":"2025-12-17","cited_by_count":0,"area":"lr"},{"id":"2601.13476","title":"A Unified Variational Imputation Framework for Electric Vehicle Charging Data Using Retrieval-Augmented Language Model","created":"2026-01-20","cited_by_count":0,"area":"rag"},{"id":"2601.15575","title":"PromptHelper: A Prompt Recommender System for Encouraging Creativity in AI Chatbot Interactions","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.13890","title":"Evaluating Prompt Engineering Techniques for RAG in Small Language Models: A Multi-Hop QA Approach","created":"2026-02-14","cited_by_count":0,"area":"rag"},{"id":"2602.16500","title":"Optimizing Soft Prompt Tuning via Structural Evolution","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2602.22456","title":"Automating the Detection of Requirement Dependencies Using Large Language Models","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.26244","title":"Automating Domain-Driven Design: Experience with a Prompting Framework","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.21827","title":"Alignment has a Fantasia Problem","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2604.25927","title":"Information Extraction from Electricity Invoices with General-Purpose Large Language Models","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.02170","title":"CLaC at SemEval-2026 Task 6: Response Clarity Detection in Political Discourse","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.16538","title":"LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.20254","title":"Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.25619","title":"Analogies between Transformer Layers and Power Method","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.09004","title":"LATTEArena: An Evaluation Framework for LLM-powered Tabular Feature Engineering (Extended Version)","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.11204","title":"Benchmarking Large Language Models for Safety Data Extraction","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2606.26489","title":"Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News","created":"2026-06-25","cited_by_count":0,"area":null}],"next_cursor":"100"}