{"total":85,"rows":[{"id":"2412.19723","title":"OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis","created":"2024-12-27","cited_by_count":163,"area":"agents"},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2503.01875","title":"Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement","created":"2025-02-26","cited_by_count":82,"area":null},{"id":"2410.17385","title":"Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities","created":"2024-10-22","cited_by_count":59,"area":"mllm"},{"id":"2410.13648","title":"SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs","created":"2024-10-17","cited_by_count":57,"area":null},{"id":"2408.12574","title":"MuMA-ToM: Multi-modal Multi-Agent Theory of Mind","created":"2024-08-22","cited_by_count":51,"area":"agents"},{"id":"2505.14685","title":"Language Models use Lookbacks to Track Beliefs","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2406.05673","title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples","created":"2024-06-09","cited_by_count":30,"area":"lr"},{"id":"2502.11881","title":"Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models","created":"2025-02-17","cited_by_count":29,"area":"lr"},{"id":"2402.17930","title":"Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning","created":"2024-02-27","cited_by_count":28,"area":null},{"id":"2412.20977","title":"UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI","created":"2024-12-30","cited_by_count":25,"area":null},{"id":"2502.20502","title":"On Benchmarking Human-Like Intelligence in Machines","created":"2025-02-27","cited_by_count":25,"area":null},{"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":"2502.15676","title":"AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling","created":"2025-02-21","cited_by_count":23,"area":"agents"},{"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":"2404.11023","title":"Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions","created":"2024-04-17","cited_by_count":22,"area":null},{"id":"2505.17663","title":"Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States","created":"2025-05-23","cited_by_count":19,"area":null},{"id":"2502.21017","title":"PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues","created":"2025-02-28","cited_by_count":17,"area":null},{"id":"2403.11075","title":"GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment","created":"2024-03-17","cited_by_count":16,"area":null},{"id":"2506.23046","title":"SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions","created":"2025-06-29","cited_by_count":16,"area":null},{"id":"2509.00559","title":"Social World Models","created":"2025-08-30","cited_by_count":16,"area":"wm"},{"id":"2410.13854","title":"Can MLLMs Understand the Deep Implication Behind Chinese Images?","created":"2024-10-17","cited_by_count":14,"area":"mllm"},{"id":"2502.15865","title":"Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk","created":"2025-02-21","cited_by_count":13,"area":"agents"},{"id":"2507.04415","title":"MOMENTS: A Comprehensive Multimodal Benchmark for Theory of Mind","created":"2025-07-06","cited_by_count":13,"area":null},{"id":"2412.03822","title":"Beyond the Binary: Capturing Diverse Preferences With Reward Regularization","created":"2024-12-05","cited_by_count":11,"area":"alignment"},{"id":"2502.16671","title":"MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2603.12138","title":"HATS: Hardness-Aware Trajectory Synthesis for GUI Agents","created":"2026-03-12","cited_by_count":9,"area":"mllm"},{"id":"2509.11514","title":"LVLMs are Bad at Overhearing Human Referential Communication","created":"2025-09-15","cited_by_count":8,"area":null},{"id":"2602.00971","title":"Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning","created":"2026-02-01","cited_by_count":8,"area":"lr"},{"id":"2608.12307","title":"AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses","created":"2026-08-12","cited_by_count":7,"area":"distill"},{"id":"2408.12022","title":"Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2409.10849","title":"Pragmatic Embodied Spoken Instruction Following in Human-Robot Collaboration with Theory of Mind","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2503.03340","title":"EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States","created":"2025-03-05","cited_by_count":6,"area":"lr"},{"id":"2505.04147","title":"R^3-VQA: \"Read the Room\" by Video Social Reasoning","created":"2025-05-07","cited_by_count":6,"area":"lr"},{"id":"2506.16755","title":"Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-The-Fly","created":"2025-06-20","cited_by_count":6,"area":"lr"},{"id":"2410.01926","title":"MARPLE: A Benchmark for Long-Horizon Inference","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2410.02613","title":"NL-Eye: Abductive NLI for Images","created":"2024-10-03","cited_by_count":5,"area":"mllm"},{"id":"2411.12977","title":"MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning","created":"2024-11-20","cited_by_count":5,"area":"agents"},{"id":"2411.14137","title":"VAGUE: Visual Contexts Clarify Ambiguous Expressions","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2506.01301","title":"Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner","created":"2025-06-02","cited_by_count":5,"area":"lr"},{"id":"2509.05066","title":"ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions","created":"2025-09-05","cited_by_count":5,"area":null},{"id":"2511.23055","title":"MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents","created":"2025-11-28","cited_by_count":5,"area":"agents"},{"id":"2507.03682","title":"Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning","created":"2025-07-04","cited_by_count":4,"area":null},{"id":"2605.20506","title":"Reinforcing Human Behavior Simulation via Verbal Feedback","created":"2026-05-19","cited_by_count":4,"area":null},{"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":"2605.09826","title":"EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2506.02461","title":"XToM: Exploring the Multilingual Theory of Mind for Large Language Models","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.02510","title":"M$^3$FinMeeting: A Multilingual, Multi-Sector, and Multi-Task Financial Meeting Understanding Evaluation Dataset","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2508.13692","title":"HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2510.15144","title":"HugAgent: A Human Simulation Benchmark for Individual-Level Reasoning","created":"2025-10-16","cited_by_count":2,"area":"lr"},{"id":"2606.09092","title":"From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2503.22093","title":"How Well Can Vison-Language Models Understand Humans' Intention? An Open-ended Theory of Mind Question Evaluation Benchmark","created":"2025-03-28","cited_by_count":1,"area":"lr"},{"id":"2506.01312","title":"Growing Through Experience: Scaling Episodic Grounding in Language Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2509.05091","title":"ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2510.20641","title":"Integrating Machine Learning into Belief-Desire-Intention Agents: Current Advances and Open Challenges","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2511.15887","title":"Mind the Motions: Benchmarking Theory-of-Mind in Everyday Body Language","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2511.22275","title":"RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender Systems","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2511.22536","title":"A Computable Game-Theoretic Framework for Multi-Agent Theory of Mind","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2512.17394","title":"Are Vision Language Models Cross-Cultural Theory of Mind Reasoners?","created":"2025-12-19","cited_by_count":1,"area":"lr"},{"id":"2604.14692","title":"Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2604.17819","title":"PDDL-Mind: Large Language Models are Capable on Belief Reasoning with Reliable State Tracking","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2605.27721","title":"UserHarness: Harnessing User Minds for Stronger Agent Theory-of-Mind","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.03471","title":"A formal definition and meta-model for a machine theory of mind","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2504.02304","title":"Measurement of LLM's Philosophies of Human Nature","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2505.24500","title":"TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2509.14803","title":"OnlineMate: An LLM-Based Multi-Agent Companion System for Cognitive Support in Online Learning","created":"2025-09-18","cited_by_count":0,"area":"agents"},{"id":"2509.25002","title":"Circuit Distillation","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2510.07974","title":"Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoning","created":"2025-10-09","cited_by_count":0,"area":"wm"},{"id":"2511.00261","title":"Spot The Ball: A Benchmark for Visual Social Inference","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2512.19992","title":"S$^3$IT: A Benchmark for Spatially Situated Social Intelligence Test","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2601.13687","title":"Understanding Mental States to Guide Social Influence in Multi-Person Group Dialogue","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.16826","title":"HiVAE: Hierarchical Latent Variables for Scalable Theory of Mind","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2602.17815","title":"Neural Synchrony Between Socially Interacting Language Models","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.04161","title":"Traces of Social Competence in Large Language Models","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.11915","title":"CoMMET: A Psychologically Grounded Benchmark for Evaluating Theory of Mind in Multimodal LLMs","created":"2026-03-12","cited_by_count":0,"area":"mllm"},{"id":"2603.24484","title":"Video-Only ToM: Enhancing Theory of Mind in Multimodal Large Language Models","created":"2026-03-25","cited_by_count":0,"area":"mllm"},{"id":"2604.10031","title":"CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2606.00240","title":"MindZero: Learning Online Mental Reasoning With Zero Annotations","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2606.01063","title":"MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2608.01598","title":"PICTURE: Enhancing Theory-of-Mind in Large Language Models by Revealing, Not Hiding, Characters' Lack of Knowledge","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.05825","title":"MoCA: Implicit Social Context Analysis","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.09222","title":"Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.20763","title":"CARD: Diagnosing Belief to Action Routing Failures in Vision Language Models","created":"2026-08-21","cited_by_count":0,"area":"mllm"},{"id":"2610.08966","title":"Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}