{"total":57,"rows":[{"id":"2402.01817","title":"LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks","created":"2024-02-02","cited_by_count":179,"area":"lr"},{"id":"2306.15448","title":"Understanding Social Reasoning in Language Models with Language Models","created":"2023-06-21","cited_by_count":172,"area":"lr"},{"id":"2305.14763","title":"Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models","created":"2023-05-24","cited_by_count":163,"area":"lr"},{"id":"2402.08115","title":"On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks","created":"2024-02-12","cited_by_count":142,"area":"lr"},{"id":"2406.11050","title":"A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners","created":"2024-06-16","cited_by_count":73,"area":"lr"},{"id":"2306.03917","title":"Turning large language models into cognitive models","created":"2023-06-06","cited_by_count":67,"area":"lr"},{"id":"2310.16755","title":"HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models","created":"2023-10-25","cited_by_count":63,"area":"lr"},{"id":"2402.06044","title":"OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models","created":"2024-02-08","cited_by_count":54,"area":"lr"},{"id":"2411.12580","title":"Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models","created":"2024-11-19","cited_by_count":41,"area":"lr"},{"id":"2412.12175","title":"Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning","created":"2024-12-12","cited_by_count":33,"area":"lr"},{"id":"2410.19599","title":"Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina","created":"2024-10-25","cited_by_count":29,"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":"2502.15109","title":"Social Genome: Grounded Social Reasoning Abilities of Multimodal Models","created":"2025-02-21","cited_by_count":26,"area":"lr"},{"id":"2306.06548","title":"Inductive reasoning in humans and large language models","created":"2023-06-11","cited_by_count":24,"area":"lr"},{"id":"2410.10479","title":"TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs","created":"2024-10-14","cited_by_count":24,"area":"lr"},{"id":"2401.17882","title":"I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench","created":"2024-01-31","cited_by_count":21,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2304.11164","title":"Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs","created":"2023-04-22","cited_by_count":20,"area":"lr"},{"id":"2405.13966","title":"On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models","created":"2024-05-22","cited_by_count":17,"area":"lr"},{"id":"2501.09056","title":"Decompose-ToM: Enhancing Theory of Mind Reasoning in Large Language Models through Simulation and Task Decomposition","created":"2025-01-15","cited_by_count":17,"area":"lr"},{"id":"2409.09239","title":"Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer","created":"2024-09-14","cited_by_count":16,"area":"lr"},{"id":"2504.10839","title":"Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective","created":"2025-04-15","cited_by_count":14,"area":"lr"},{"id":"2505.18943","title":"MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems","created":"2025-05-25","cited_by_count":13,"area":"lr"},{"id":"2506.06958","title":"Simulating Society Requires Simulating Thought","created":"2025-06-08","cited_by_count":13,"area":"lr"},{"id":"2402.10735","title":"Assessing the Reasoning Capabilities of LLMs in the context of Evidence-based Claim Verification","created":"2024-02-16","cited_by_count":9,"area":"lr"},{"id":"2412.13631","title":"Mind Your Theory: Theory of Mind Goes Deeper Than Reasoning","created":"2024-12-18","cited_by_count":9,"area":"lr"},{"id":"2408.08651","title":"Chain of Thought Still Thinks Fast: APriCoT Helps with Thinking Slow","created":"2024-08-16","cited_by_count":8,"area":"lr"},{"id":"2409.12437","title":"Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data","created":"2024-09-19","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":"2504.01698","title":"Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?","created":"2025-04-02","cited_by_count":8,"area":"lr"},{"id":"2605.20087","title":"ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions","created":"2026-05-19","cited_by_count":7,"area":"lr"},{"id":"2307.13779","title":"Is GPT a Computational Model of Emotion? Detailed Analysis","created":"2023-07-25","cited_by_count":6,"area":"lr"},{"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":"2406.09464","title":"GPT-ology, Computational Models, Silicon Sampling: How should we think about LLMs in Cognitive Science?","created":"2024-06-13","cited_by_count":5,"area":"lr"},{"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":"2603.09249","title":"Social-R1: Towards Human-like Social Reasoning in LLMs","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2605.29512","title":"MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs","created":"2026-05-28","cited_by_count":5,"area":"lr"},{"id":"2506.13065","title":"MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2506.20664","title":"The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind","created":"2025-06-25","cited_by_count":4,"area":"lr"},{"id":"2505.09396","title":"The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners","created":"2025-05-14","cited_by_count":3,"area":"lr"},{"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":"2602.00380","title":"Clause-Internal or Clause-External? Testing Turkish Reflexive Binding in Adapted versus Chain of Thought Large Language Models","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2602.16085","title":"Language Statistics and False Belief Reasoning: Evidence from 41 Open-Weight LMs","created":"2026-02-17","cited_by_count":3,"area":"lr"},{"id":"2504.13898","title":"Social Human Robot Embodied Conversation (SHREC) Dataset: Benchmarking Foundational Models' Social Reasoning","created":"2025-04-07","cited_by_count":2,"area":"lr"},{"id":"2601.12269","title":"Simulated Annealing Enhances Theory-of-Mind Reasoning in Autoregressive Language Models","created":"2026-01-18","cited_by_count":2,"area":"lr"},{"id":"2606.11724","title":"Mind the Perspective: Let's Reason Recursively for Theory of Mind","created":"2026-06-10","cited_by_count":2,"area":"lr"},{"id":"2608.09128","title":"Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent Game Tournaments","created":"2026-08-10","cited_by_count":2,"area":"lr"},{"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":"2503.16437","title":"Haunted House: A text-based game for comparing the flexibility of mental models in humans and LLMs","created":"2025-02-12","cited_by_count":0,"area":"lr"},{"id":"2601.16853","title":"Reasoning Promotes Robustness in Theory of Mind Tasks","created":"2026-01-23","cited_by_count":0,"area":"lr"},{"id":"2603.06680","title":"VB: Visibility Benchmark for Visibility and Perspective Reasoning in Images","created":"2026-03-03","cited_by_count":0,"area":"lr"},{"id":"2603.09993","title":"CEI: A Benchmark for Evaluating Pragmatic Reasoning in Language Models","created":"2026-02-14","cited_by_count":0,"area":"lr"},{"id":"2606.00240","title":"MindZero: Learning Online Mental Reasoning With Zero Annotations","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"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":"2609.25284","title":"When LLM Agents Fail to Read the Room: ReAdapt for Relational Social Reasoning","created":"2026-09-21","cited_by_count":0,"area":"lr"}],"next_cursor":null}