{"total":56,"rows":[{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592,"area":null},{"id":"2206.14576","title":"Using cognitive psychology to understand GPT-3","created":"2022-06-21","cited_by_count":398,"area":null},{"id":"2305.11014","title":"Generalized Planning in PDDL Domains with Pretrained Large Language Models","created":"2023-05-18","cited_by_count":139,"area":null},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2302.05128","title":"Translating Natural Language to Planning Goals with Large-Language Models","created":"2023-02-10","cited_by_count":133,"area":null},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119,"area":"wm"},{"id":"2205.10893","title":"Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers","created":"2022-05-22","cited_by_count":98,"area":null},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83,"area":"lr"},{"id":"2504.16736","title":"A Survey of AI Agent Protocols","created":"2025-04-23","cited_by_count":81,"area":"agents"},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2402.18225","title":"CogBench: a large language model walks into a psychology lab","created":"2024-02-28","cited_by_count":63,"area":null},{"id":"2411.01855","title":"Can Language Models Learn to Skip Steps?","created":"2024-11-04","cited_by_count":59,"area":"lr"},{"id":"2409.02387","title":"Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges","created":"2024-09-04","cited_by_count":49,"area":null},{"id":"2305.05252","title":"Distilling Script Knowledge from Large Language Models for Constrained Language Planning","created":"2023-05-09","cited_by_count":45,"area":null},{"id":"2410.11905","title":"A Scalable Communication Protocol for Networks of Large Language Models","created":"2024-10-14","cited_by_count":45,"area":null},{"id":"2503.18971","title":"LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models","created":"2025-03-22","cited_by_count":38,"area":null},{"id":"2402.02805","title":"Graph-enhanced Large Language Models in Asynchronous Plan Reasoning","created":"2024-02-05","cited_by_count":37,"area":"lr"},{"id":"2311.09682","title":"MacGyver: Are Large Language Models Creative Problem Solvers?","created":"2023-11-16","cited_by_count":34,"area":null},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2401.11839","title":"AI for social science and social science of AI: A Survey","created":"2024-01-22","cited_by_count":29,"area":null},{"id":"2502.20502","title":"On Benchmarking Human-Like Intelligence in Machines","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2405.13245","title":"A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddings","created":"2024-05-21","cited_by_count":24,"area":null},{"id":"2306.14325","title":"The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs","created":"2023-06-25","cited_by_count":23,"area":null},{"id":"2405.04215","title":"NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions","created":"2024-05-07","cited_by_count":22,"area":"wm"},{"id":"2310.19671","title":"Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding","created":"2023-10-30","cited_by_count":20,"area":null},{"id":"2509.10723","title":"Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight","created":"2025-09-12","cited_by_count":16,"area":"agents"},{"id":"2305.01020","title":"Evaluating statistical language models as pragmatic reasoners","created":"2023-05-01","cited_by_count":15,"area":"lr"},{"id":"2403.00092","title":"PROC2PDDL: Open-Domain Planning Representations from Texts","created":"2024-02-29","cited_by_count":15,"area":null},{"id":"2405.19793","title":"PDDLEGO: Iterative Planning in Textual Environments","created":"2024-05-30","cited_by_count":14,"area":null},{"id":"2507.12547","title":"Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models","created":"2025-07-16","cited_by_count":14,"area":null},{"id":"2211.01202","title":"Human-in-the-Loop Mixup","created":"2022-11-02","cited_by_count":8,"area":null},{"id":"2312.04578","title":"Towards a Psychological Generalist AI: A Survey of Current Applications of Large Language Models and Future Prospects","created":"2023-12-01","cited_by_count":8,"area":null},{"id":"2410.21490","title":"Can Large Language Models Act as Symbolic Reasoners?","created":"2024-10-28","cited_by_count":8,"area":"lr"},{"id":"2508.18507","title":"Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies","created":"2025-08-25","cited_by_count":7,"area":"wm"},{"id":"2401.07868","title":"Consolidating Trees of Robotic Plans Generated Using Large Language Models to Improve Reliability","created":"2024-01-15","cited_by_count":6,"area":null},{"id":"2405.11841","title":"Evaluating and Modeling Social Intelligence: A Comparative Study of Human and AI Capabilities","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2407.11000","title":"Autonomous Prompt Engineering in Large Language Models","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2502.02066","title":"Anticipate & Act : Integrating LLMs and Classical Planning for Efficient Task Execution in Household Environments","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2303.04229","title":"Understanding Natural Language Understanding Systems. A Critical Analysis","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2305.19472","title":"PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2404.00884","title":"Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2407.14095","title":"People use fast, goal-directed simulation to reason about novel games","created":"2024-07-19","cited_by_count":4,"area":null},{"id":"2502.15678","title":"Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models","created":"2025-02-21","cited_by_count":4,"area":"mllm"},{"id":"2503.06980","title":"Exploring Multimodal Perception in Large Language Models Through Perceptual Strength Ratings","created":"2025-03-10","cited_by_count":3,"area":"mllm"},{"id":"2505.01800","title":"Distinguishing AI-Generated and Human-Written Text Through Psycholinguistic Analysis","created":"2025-05-03","cited_by_count":3,"area":null},{"id":"2505.20184","title":"THiNK: Can Large Language Models Think-aloud?","created":"2025-05-26","cited_by_count":3,"area":"lr"},{"id":"2602.06033","title":"Can Vision Language Models Learn Intuitive Physics from Interaction?","created":"2026-02-05","cited_by_count":2,"area":"mllm"},{"id":"2302.09068","title":"A Pilot Evaluation of ChatGPT and DALL-E 2 on Decision Making and Spatial Reasoning","created":"2023-02-15","cited_by_count":1,"area":"lr"},{"id":"2311.04403","title":"Human-Centered Planning","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2506.01474","title":"Integrating Neural and Symbolic Components in a Model of Pragmatic Question-Answering","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2601.21214","title":"Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2605.30326","title":"RoboWits: Unexpected Challenges for Robotic Creative Problem Solving","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2309.15991","title":"Targeted Image Data Augmentation Increases Basic Skills Captioning Robustness","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2403.19339","title":"An Interactive Human-Machine Learning Interface for Collecting and Learning from Complex Annotations","created":"2024-03-28","cited_by_count":0,"area":null},{"id":"2509.25941","title":"Boosting Process-Correct CoT Reasoning by Modeling Solvability of Multiple-Choice QA","created":"2025-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.21259","title":"CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":null}