{"total":69,"rows":[{"id":"2502.15840","title":"Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents","created":"2025-02-20","cited_by_count":80,"area":"agents"},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74,"area":null},{"id":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72,"area":null},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2410.14182","title":"LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs","created":"2024-10-18","cited_by_count":25,"area":null},{"id":"2502.06124","title":"Foundation Model of Electronic Medical Records for Adaptive Risk Estimation","created":"2025-02-10","cited_by_count":19,"area":null},{"id":"2502.16487","title":"All That Glitters is Not Novel: Plagiarism in AI Generated Research","created":"2025-02-23","cited_by_count":18,"area":null},{"id":"2505.13903","title":"Let's Verify Math Questions Step by Step","created":"2025-05-20","cited_by_count":18,"area":"lr"},{"id":"2505.00662","title":"DeepCritic: Deliberate Critique with Large Language Models","created":"2025-05-01","cited_by_count":17,"area":null},{"id":"2506.00794","title":"Predicting Empirical AI Research Outcomes with Language Models","created":"2025-06-01","cited_by_count":17,"area":null},{"id":"2410.19160","title":"Adversarial Attacks on Large Language Models Using Regularized Relaxation","created":"2024-10-24","cited_by_count":12,"area":null},{"id":"2502.18156","title":"Can LLMs Explain Themselves Counterfactually?","created":"2025-02-25","cited_by_count":10,"area":null},{"id":"2410.01795","title":"Knowledge-Driven Feature Selection and Engineering for Genotype Data with Large Language Models","created":"2024-10-02","cited_by_count":9,"area":null},{"id":"2507.11810","title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","created":"2025-07-16","cited_by_count":9,"area":null},{"id":"2404.04287","title":"CONFLARE: CONFormal LArge language model REtrieval","created":"2024-04-04","cited_by_count":6,"area":"rag"},{"id":"2505.03418","title":"Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey","created":"2025-05-06","cited_by_count":6,"area":"lr"},{"id":"2507.19477","title":"Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impacts","created":"2025-07-25","cited_by_count":6,"area":null},{"id":"2512.19234","title":"DeliveryBench: Can Agents Earn Profit in Real World?","created":"2025-12-22","cited_by_count":6,"area":"agents"},{"id":"2506.14092","title":"Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2510.22095","title":"Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies","created":"2025-10-25","cited_by_count":5,"area":"agents"},{"id":"2505.09820","title":"Adversarial Attack on Large Language Models using Exponentiated Gradient Descent","created":"2025-05-14","cited_by_count":4,"area":"safety"},{"id":"2505.20875","title":"Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2508.15094","title":"Evaluating Sparse Autoencoders for Monosemantic Representation","created":"2025-08-20","cited_by_count":4,"area":"mechinterp"},{"id":"2509.23986","title":"TusoAI: Agentic Optimization for Scientific Methods","created":"2025-09-28","cited_by_count":4,"area":"agents"},{"id":"2511.02599","title":"Next Token Knowledge Tracing: Exploiting Pretrained LLM Representations to Decode Student Behaviour","created":"2025-11-04","cited_by_count":4,"area":null},{"id":"2503.02851","title":"Shakespearean Sparks: The Dance of Hallucination and Creativity in LLMs' Decoding Layers","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2508.05421","title":"LLM-based Multi-Agent Copilot for Quantum Sensor","created":"2025-08-07","cited_by_count":3,"area":"agents"},{"id":"2511.00206","title":"Addressing Longstanding Challenges in Cognitive Science with Language Models","created":"2025-10-31","cited_by_count":3,"area":null},{"id":"2512.14244","title":"From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition","created":"2025-12-16","cited_by_count":3,"area":"inference"},{"id":"2603.14643","title":"Argumentation for Explainable and Globally Contestable Decision Support with LLMs","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2605.06584","title":"NeuroAgent: LLM Agents for Multimodal Neuroimaging Analysis and Research","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2405.09395","title":"Matching domain experts by training from scratch on domain knowledge","created":"2024-05-15","cited_by_count":2,"area":null},{"id":"2503.00330","title":"How Deep is Love in LLMs' Hearts? Exploring Semantic Size in Human-like Cognition","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2503.10652","title":"Can Large Language Models Simulate Human Responses? A Case Study of Stated Preference Experiments in the Context of Heating-related Choices","created":"2025-03-07","cited_by_count":2,"area":"lr"},{"id":"2508.14853","title":"Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent","created":"2025-08-20","cited_by_count":2,"area":"alignment"},{"id":"2509.06858","title":"Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2509.21542","title":"Psychological and behavioural responses in human-agent vs. human-human interactions: a systematic review and meta-analysis","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2512.03549","title":"PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Tasks","created":"2025-12-03","cited_by_count":2,"area":"agents"},{"id":"2512.19570","title":"The Epistemological Consequences of Large Language Models: Rethinking collective intelligence and institutional knowledge","created":"2025-12-22","cited_by_count":2,"area":"lr"},{"id":"2604.06091","title":"Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2408.08083","title":"Confidence-weighted integration of human and machine judgments for superior decision-making","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2501.02348","title":"Thinking with Many Minds: Using Large Language Models for Multi-Perspective Problem-Solving","created":"2025-01-04","cited_by_count":1,"area":"lr"},{"id":"2503.07320","title":"When Trust Collides: Decoding Human-LLM Cooperation Dynamics through the Prisoner's Dilemma","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2505.08739","title":"Probability Consistency in Large Language Models: Theoretical Foundations Meet Empirical Discrepancies","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2508.05116","title":"Beyond Automation: Socratic AI, Epistemic Agency, and the Implications of the Emergence of Orchestrated Multi-Agent Learning Architectures","created":"2025-08-07","cited_by_count":1,"area":"agents"},{"id":"2509.18108","title":"Solve it with EASE","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2512.14306","title":"Inflation Attitudes of Large Language Models","created":"2025-12-16","cited_by_count":1,"area":null},{"id":"2603.14347","title":"Motivation in Large Language Models","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2604.19787","title":"LLM Agents Predict Social Media Reactions but Do Not Outperform Text Classifiers: Benchmarking Simulation Accuracy Using 120K+ Personas of 1511 Humans","created":"2026-03-31","cited_by_count":1,"area":"agents"},{"id":"2405.15640","title":"GECKO: Generative Language Model for English, Code and Korean","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2410.03223","title":"Consultation on Industrial Machine Faults with Large language Models","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2501.01332","title":"Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension","created":"2025-01-02","cited_by_count":0,"area":null},{"id":"2503.20787","title":"Advanced simulation paradigm of human behaviour unveils complex financial systemic projection","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2503.20800","title":"Evidencing Unauthorized Training Data from AI Generated Content using Information Isotopes","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2506.06396","title":"Natural Language Interaction with Databases on Edge Devices in the Internet of Battlefield Things","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2509.08329","title":"Accelerating Reinforcement Learning Algorithms Convergence using Pre-trained Large Language Models as Tutors With Advice Reusing","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2509.24298","title":"Bridging the behavior-neural gap: A multimodal AI reveals the brain's geometry of emotion more accurately than human self-reports","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2512.23217","title":"TCEval: Using Thermal Comfort to Assess Cognitive and Perceptual Abilities of AI","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2606.05206","title":"Ontology-constrained multi-LLM scoring of hypothesis support in the predictive processing literature","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.11533","title":"AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.17739","title":"ED3R: Energy-Aware Distributed Disaster Detection via Cooperative Agents in Robotic Systems","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.06656","title":"Robust Human-AI Complementarity under Uncertainty","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.29347","title":"SeekBrain: An Autonomous Multi-Agent System for Accelerating Neuroscience Discovery","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.00464","title":"Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspective","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.07350","title":"D3ARC: Time-Critical Distributed Disaster Detection for Asynchronous Cooperative Multi-Robot Systems","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.10092","title":"RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases","created":"2026-09-09","cited_by_count":0,"area":"agents"},{"id":"2609.15818","title":"Atria Dawn: The Dawn of Agentic Superintelligence","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.34258","title":"Investigating Human--AI Discrepancies via Multiple-Solution Problems","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00314","title":"Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts","created":"2026-09-29","cited_by_count":0,"area":"agents"}],"next_cursor":null}