{"total":72,"rows":[{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780,"area":null},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316,"area":null},{"id":"2404.08819","title":"The Illusion of State in State-Space Models","created":"2024-04-12","cited_by_count":187,"area":null},{"id":"2402.14811","title":"Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking","created":"2024-02-22","cited_by_count":149,"area":null},{"id":"2406.03689","title":"Evaluating the World Model Implicit in a Generative Model","created":"2024-06-06","cited_by_count":113,"area":"wm"},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112,"area":"agents"},{"id":"2309.05858","title":"Uncovering mesa-optimization algorithms in Transformers","created":"2023-09-11","cited_by_count":100,"area":null},{"id":"2402.18659","title":"Large Language Models and Games: A Survey and Roadmap","created":"2024-02-28","cited_by_count":93,"area":null},{"id":"2306.09200","title":"ChessGPT: Bridging Policy Learning and Language Modeling","created":"2023-06-15","cited_by_count":75,"area":null},{"id":"2402.04494","title":"Amortized Planning with Large-Scale Transformers: A Case Study on Chess","created":"2024-02-07","cited_by_count":49,"area":null},{"id":"2507.06952","title":"What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models","created":"2025-07-09","cited_by_count":47,"area":"wm"},{"id":"2305.02363","title":"Entity Tracking in Language Models","created":"2023-05-03","cited_by_count":44,"area":null},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43,"area":null},{"id":"2306.17840","title":"Statler: State-Maintaining Language Models for Embodied Reasoning","created":"2023-06-30","cited_by_count":40,"area":"wm"},{"id":"2406.00877","title":"Evidence of Learned Look-Ahead in a Chess-Playing Neural Network","created":"2024-06-02","cited_by_count":34,"area":null},{"id":"2305.00833","title":"Learning to Reason and Memorize with Self-Notes","created":"2023-05-01","cited_by_count":30,"area":"lr"},{"id":"2305.11169","title":"Emergent Representations of Program Semantics in Language Models Trained on Programs","created":"2023-05-18","cited_by_count":30,"area":"wm"},{"id":"2503.07639","title":"Mixture of Experts Made Intrinsically Interpretable","created":"2025-03-05","cited_by_count":24,"area":"moe"},{"id":"2412.01800","title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2402.05110","title":"Opening the AI black box: program synthesis via mechanistic interpretability","created":"2024-02-07","cited_by_count":20,"area":"mechinterp"},{"id":"2406.11741","title":"Transcendence: Generative Models Can Outperform The Experts That Train Them","created":"2024-06-17","cited_by_count":20,"area":null},{"id":"2502.20129","title":"Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking","created":"2025-02-27","cited_by_count":18,"area":"lr"},{"id":"2512.01992","title":"LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess","created":"2025-12-01","cited_by_count":15,"area":"lr"},{"id":"2212.08195","title":"Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines","created":"2022-12-15","cited_by_count":13,"area":"lr"},{"id":"2410.03893","title":"Human-aligned Chess with a Bit of Search","created":"2024-10-04","cited_by_count":11,"area":null},{"id":"2410.06555","title":"ING-VP: MLLMs cannot Play Easy Vision-based Games Yet","created":"2024-10-09","cited_by_count":11,"area":"mllm"},{"id":"2502.19805","title":"Implicit Search via Discrete Diffusion: A Study on Chess","created":"2025-02-27","cited_by_count":11,"area":"diffusion"},{"id":"2411.00308","title":"GPT for Games: An Updated Scoping Review (2020-2024)","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2308.15118","title":"Large Language Models on the Chessboard: A Study on ChatGPT's Formal Language Comprehension and Complex Reasoning Skills","created":"2023-08-29","cited_by_count":9,"area":"lr"},{"id":"2304.14918","title":"Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers","created":"2023-04-28","cited_by_count":8,"area":null},{"id":"2410.05565","title":"Chain and Causal Attention for Efficient Entity Tracking","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2507.21513","title":"What Does it Mean for a Neural Network to Learn a \"World Model\"?","created":"2025-07-29","cited_by_count":8,"area":"wm"},{"id":"2412.07446","title":"A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment","created":"2024-12-10","cited_by_count":6,"area":"wm"},{"id":"2505.21785","title":"Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2506.02996","title":"Linear Spatial World Models Emerge in Large Language Models","created":"2025-06-03","cited_by_count":6,"area":"wm"},{"id":"2512.21577","title":"A Unified Definition of Hallucination: It's The World Model, Stupid!","created":"2025-12-25","cited_by_count":6,"area":"wm"},{"id":"2602.14814","title":"Learning State-Tracking from Code Using Linear RNNs","created":"2026-02-16","cited_by_count":6,"area":null},{"id":"2605.30233","title":"Do Language Models Track Entities Across State Changes?","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2310.16135","title":"Can You Follow Me? Testing Situational Understanding in ChatGPT","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2508.19851","title":"Tracking World States with Language Models: State-Based Evaluation Using Chess","created":"2025-08-27","cited_by_count":4,"area":"wm"},{"id":"2410.14890","title":"Reasoning, Memorization, and Fine-Tuning Language Models for Non-Cooperative Games","created":"2024-10-18","cited_by_count":3,"area":"lr"},{"id":"2506.02923","title":"The Limits of Predicting Agents from Behaviour","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2603.08436","title":"Can Vision-Language Models Solve the Shell Game?","created":"2026-03-09","cited_by_count":3,"area":"mllm"},{"id":"2603.12133","title":"TopoBench: Benchmarking LLMs on Hard Topological Reasoning","created":"2026-03-12","cited_by_count":3,"area":"lr"},{"id":"2509.13389","title":"From Next Token Prediction to (STRIPS) World Models","created":"2025-09-16","cited_by_count":2,"area":"wm"},{"id":"2509.24125","title":"The Impossibility of Inverse Permutation Learning in Transformer Models","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.20783","title":"Out-of-distribution Tests Reveal Compositionality in Chess Transformers","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2405.06499","title":"Aspect-based Sentiment Evaluation of Chess Moves (ASSESS): an NLP-based Method for Evaluating Chess Strategies from Textbooks","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2407.08195","title":"A Text-to-Game Engine for UGC-Based Role-Playing Games","created":"2024-07-11","cited_by_count":1,"area":null},{"id":"2410.00519","title":"Exploring the Learning Capabilities of Language Models using LEVERWORLDS","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2502.10886","title":"MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models","created":"2025-02-15","cited_by_count":1,"area":"wm"},{"id":"2506.16584","title":"Measuring Intent Comprehension in LLMs","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2601.16471","title":"Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.04447","title":"Mixture of Masters: Sparse Chess Language Models with Player Routing","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.10298","title":"On Emergent Social World Models -- Evidence for Functional Integration of Theory of Mind and Pragmatic Reasoning in Language Models","created":"2026-02-10","cited_by_count":1,"area":"wm"},{"id":"2605.20784","title":"Interaction Locality in Hierarchical Recursive Reasoning","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2605.30100","title":"Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences","created":"2026-05-28","cited_by_count":1,"area":"wm"},{"id":"2609.25438","title":"PermuFormer: Multi-Task Pretraining for Permutation Representation in Algebraic Combinatorics","created":"2026-09-21","cited_by_count":1,"area":null},{"id":"2410.12686","title":"Automatic Mapping of Anatomical Landmarks from Free-Text Using Large Language Models: Insights from Llama-2","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2412.03359","title":"WiS Platform: Enhancing Evaluation of LLM-Based Multi-Agent Systems Through Game-Based Analysis","created":"2024-12-04","cited_by_count":0,"area":"agents"},{"id":"2510.27009","title":"Causal Masking on Spatial Data: An Information-Theoretic Case for Learning Spatial Datasets with Unimodal Language Models","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2603.29761","title":"Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.21896","title":"Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models","created":"2026-04-23","cited_by_count":0,"area":"agents"},{"id":"2605.04899","title":"A geometric relation of the error introduced by sampling a language model's output distribution to its internal state","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.12691","title":"Two-Layer Linear Auto-Regressive Models Estimate Latent States","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.11953","title":"When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.05206","title":"Otter: A Time-Aware, History-Conditioned Human Chess AI","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.14851","title":"Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.35161","title":"Small transformers track Bayesian evidence for latent common causes via a context-invariant mechanism","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.02425","title":"Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.03695","title":"Language Models that Play Chess and Explain Their Moves","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04098","title":"Representation-Aligned Auxiliary Supervision for Language Model Adaptation","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}