{"total":61,"rows":[{"id":"2407.01284","title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","created":"2024-07-01","cited_by_count":286,"area":"lr"},{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166,"area":"wm"},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2505.14685","title":"Language Models use Lookbacks to Track Beliefs","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2411.02280","title":"The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units","created":"2024-11-04","cited_by_count":34,"area":"lr"},{"id":"2412.19726","title":"Position: Theory of Mind Benchmarks are Broken for Large Language Models","created":"2024-12-27","cited_by_count":31,"area":null},{"id":"2409.18142","title":"A Survey on Multimodal Benchmarks: In the Era of Large AI Models","created":"2024-09-21","cited_by_count":27,"area":"mllm"},{"id":"2505.00026","title":"Theory of Mind in Large Language Models: Assessment and Enhancement","created":"2025-04-26","cited_by_count":25,"area":null},{"id":"2502.21098","title":"Re-evaluating Theory of Mind evaluation in large language models","created":"2025-02-28","cited_by_count":23,"area":null},{"id":"2407.06004","title":"Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models","created":"2024-07-08","cited_by_count":22,"area":null},{"id":"2509.10127","title":"Population-Aligned Persona Generation for LLM-based Social Simulation","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2406.05862","title":"II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models","created":"2024-06-09","cited_by_count":16,"area":"mllm"},{"id":"2411.02432","title":"Can LLMs make trade-offs involving stipulated pain and pleasure states?","created":"2024-11-01","cited_by_count":16,"area":null},{"id":"2407.15814","title":"Perceptions of Linguistic Uncertainty by Language Models and Humans","created":"2024-07-22","cited_by_count":15,"area":null},{"id":"2410.13854","title":"Can MLLMs Understand the Deep Implication Behind Chinese Images?","created":"2024-10-17","cited_by_count":14,"area":"mllm"},{"id":"2410.18819","title":"From Imitation to Introspection: Probing Self-Consciousness in Language Models","created":"2024-10-24","cited_by_count":14,"area":null},{"id":"2505.22961","title":"ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind","created":"2025-05-29","cited_by_count":12,"area":null},{"id":"2409.15454","title":"In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models","created":"2024-09-23","cited_by_count":8,"area":"lr"},{"id":"2412.11373","title":"Codenames as a Benchmark for Large Language Models","created":"2024-12-16","cited_by_count":8,"area":"lr"},{"id":"2502.06470","title":"A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2506.06211","title":"PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts","created":"2025-06-06","cited_by_count":8,"area":"lr"},{"id":"2509.11514","title":"LVLMs are Bad at Overhearing Human Referential Communication","created":"2025-09-15","cited_by_count":8,"area":null},{"id":"2410.05217","title":"Organizing Unstructured Image Collections using Natural Language","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2509.19003","title":"Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards","created":"2025-09-23","cited_by_count":6,"area":"lr"},{"id":"2503.08193","title":"Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents","created":"2025-03-11","cited_by_count":5,"area":"lr"},{"id":"2511.04715","title":"First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation","created":"2025-11-06","cited_by_count":5,"area":null},{"id":"2603.09249","title":"Social-R1: Towards Human-like Social Reasoning in LLMs","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2503.02976","title":"Teaching AI to Handle Exceptions: Supervised Fine-Tuning with Human-Aligned Judgment","created":"2025-03-04","cited_by_count":4,"area":"agents"},{"id":"2503.16468","title":"Towards properly implementing Theory of Mind in AI systems: An account of four misconceptions","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2505.17348","title":"DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2505.10718","title":"AI-enhanced semantic feature norms for 786 concepts","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2603.26089","title":"Selective Deficits in LLM Mental Self-Modeling in a Behavior-Based Test of Theory of Mind","created":"2026-03-27","cited_by_count":2,"area":null},{"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":"2407.19492","title":"Heads Up eXperience (HUX): Always-On AI Companion for Human Computer Environment Interaction","created":"2024-07-28","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":"2505.12321","title":"BeliefNest: A Joint Action Simulator for Embodied Agents with Theory of Mind","created":"2025-05-18","cited_by_count":1,"area":"agents"},{"id":"2505.22907","title":"Conversational Alignment with Artificial Intelligence in Context","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2508.08276","title":"Evaluating Contrast Localizer for Identifying Causal Units in Social & Mathematical Tasks in Language Models","created":"2025-07-31","cited_by_count":1,"area":"lr"},{"id":"2601.02378","title":"Modeling the Mental World for Embodied AI: A Comprehensive Review","created":"2025-12-17","cited_by_count":1,"area":"wm"},{"id":"2602.17045","title":"Large Language Models Persuade Without Planning Theory of Mind","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2605.03255","title":"Do LLMs have core beliefs?","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2605.06965","title":"AI and Consciousness: Shifting Focus Towards Tractable Questions","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.31916","title":"Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2607.28607","title":"Inducing language models to assert their own consciousness restores human beliefs and values","created":"2026-07-30","cited_by_count":1,"area":"alignment"},{"id":"2608.18078","title":"Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2411.02435","title":"Narrative Analysis of True Crime Podcasts With Knowledge Graph-Augmented Large Language Models","created":"2024-11-01","cited_by_count":0,"area":"safety"},{"id":"2504.04238","title":"Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models","created":"2025-04-05","cited_by_count":0,"area":null},{"id":"2507.02935","title":"Theory of Mind in Action: The Instruction Inference Task in Dynamic Human-Agent Collaboration","created":"2025-06-26","cited_by_count":0,"area":"agents"},{"id":"2508.01581","title":"Polymorphic Combinatorial Frameworks (PCF): Guiding the Design of Mathematically-Grounded, Adaptive AI Agents","created":"2025-08-03","cited_by_count":0,"area":"agents"},{"id":"2510.05458","title":"SocialNLI: A Dialogue-Centric Social Inference Dataset","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2601.16853","title":"Reasoning Promotes Robustness in Theory of Mind Tasks","created":"2026-01-23","cited_by_count":0,"area":"lr"},{"id":"2603.14646","title":"Dynamic Theory of Mind as a Temporal Memory Problem: Evidence from Large Language Models","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2605.12920","title":"Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue","created":"2026-05-13","cited_by_count":0,"area":"wm"},{"id":"2605.20423","title":"OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.27909","title":"Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2606.28524","title":"Developmental Trajectories of Situation Modeling and Mentalizing in Transformer Language Models","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.11363","title":"Beyond Sally-Anne: Evaluating Theory of Mind in LLMs using Epistemic Schelling Points","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.04646","title":"Evaluating Theory of Mind in Reasoning Models: Robustness over Reasoning","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.11354","title":"Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2610.16895","title":"Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17777","title":"Beyond Belief Nesting: Rethinking Higher-Order Theory of Mind in Large Language Models","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}