{"total":81,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2505.10468","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","created":"2025-05-15","cited_by_count":169,"area":"agents"},{"id":"2409.12278","title":"Making Large Language Models into World Models with Precondition and Effect Knowledge","created":"2024-09-18","cited_by_count":22,"area":"wm"},{"id":"2503.00237","title":"Agentic AI Needs a Systems Theory","created":"2025-02-28","cited_by_count":19,"area":"lr"},{"id":"2502.12435","title":"A Survey on Large Language Models for Automated Planning","created":"2025-02-18","cited_by_count":17,"area":null},{"id":"2506.01622","title":"General agents contain world models","created":"2025-06-02","cited_by_count":17,"area":"wm"},{"id":"2406.14302","title":"Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning","created":"2024-06-20","cited_by_count":16,"area":null},{"id":"2511.02097","title":"A Step Toward World Models: A Survey on Robotic Manipulation","created":"2025-10-31","cited_by_count":15,"area":"wm"},{"id":"2406.16605","title":"CLEAR: Can Language Models Really Understand Causal Graphs?","created":"2024-06-24","cited_by_count":14,"area":"lr"},{"id":"2407.10583","title":"Three Dogmas of Reinforcement Learning","created":"2024-07-15","cited_by_count":14,"area":"deeprl"},{"id":"2504.11609","title":"Towards Interpretable Deep Generative Models via Causal Representation Learning","created":"2025-04-15","cited_by_count":13,"area":null},{"id":"2508.11214","title":"How Causal Abstraction Underpins Computational Explanation","created":"2025-08-15","cited_by_count":11,"area":null},{"id":"2411.06890","title":"SPARTAN: A Sparse Transformer World Model Attending to What Matters","created":"2024-11-11","cited_by_count":10,"area":"wm"},{"id":"2410.19923","title":"Language Agents Meet Causality -- Bridging LLMs and Causal World Models","created":"2024-10-25","cited_by_count":9,"area":"wm"},{"id":"2502.09507","title":"When and How Does CLIP Enable Domain and Compositional Generalization?","created":"2025-02-13","cited_by_count":9,"area":"mllm"},{"id":"2502.09297","title":"When Do Neural Networks Learn World Models?","created":"2025-02-13","cited_by_count":8,"area":"wm"},{"id":"2412.04758","title":"Measuring Goal-Directedness","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2509.05882","title":"Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes","created":"2025-09-07","cited_by_count":7,"area":"agents"},{"id":"2608.09696","title":"Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models","created":"2026-08-10","cited_by_count":7,"area":"wm"},{"id":"2505.00808","title":"A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i","created":"2025-05-01","cited_by_count":6,"area":"mechinterp"},{"id":"2506.02996","title":"Linear Spatial World Models Emerge in Large Language Models","created":"2025-06-03","cited_by_count":6,"area":"wm"},{"id":"2506.05967","title":"Preference Learning for AI Alignment: a Causal Perspective","created":"2025-06-06","cited_by_count":6,"area":"alignment"},{"id":"2608.04653","title":"Overcoming Statistical Bias in Action-Controllable World Models","created":"2026-08-05","cited_by_count":6,"area":"wm"},{"id":"2403.11219","title":"Causality from Bottom to Top: A Survey","created":"2024-03-17","cited_by_count":5,"area":null},{"id":"2405.02325","title":"Are Biological Systems More Intelligent Than Artificial Intelligence?","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2502.10077","title":"Towards Empowerment Gain through Causal Structure Learning in Model-Based RL","created":"2025-02-14","cited_by_count":5,"area":"deeprl"},{"id":"2507.00979","title":"Enhancing LLM Agent Safety via Causal Influence Prompting","created":"2025-07-01","cited_by_count":5,"area":"agents"},{"id":"2502.12707","title":"CausalMan: A physics-based simulator for large-scale causality","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2506.23068","title":"Curious Causality-Seeking Agents Learn Meta Causal World","created":"2025-06-29","cited_by_count":4,"area":"wm"},{"id":"2509.03636","title":"CausalARC: Abstract Reasoning with Causal World Models","created":"2025-09-03","cited_by_count":4,"area":"wm"},{"id":"2502.04512","title":"Safety Must Precede the Deployment of Open-Ended AI","created":"2025-02-06","cited_by_count":3,"area":"deeprl"},{"id":"2506.02923","title":"The Limits of Predicting Agents from Behaviour","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2510.17697","title":"A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2605.30346","title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2409.14545","title":"Why Is Anything Conscious?","created":"2024-09-22","cited_by_count":2,"area":null},{"id":"2502.21123","title":"Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2503.11718","title":"The Relativity of Causal Knowledge","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2504.03185","title":"Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents","created":"2025-04-04","cited_by_count":2,"area":"agents"},{"id":"2505.02074","title":"Learning Local Causal World Models with State Space Models and Attention","created":"2025-05-04","cited_by_count":2,"area":"wm"},{"id":"2603.02491","title":"What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty","created":"2026-03-03","cited_by_count":2,"area":"wm"},{"id":"2603.06445","title":"What if? Emulative Simulation with World Models for Situated Reasoning","created":"2026-03-06","cited_by_count":2,"area":"wm"},{"id":"2608.04396","title":"CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention","created":"2026-08-05","cited_by_count":2,"area":"vla"},{"id":"2404.01794","title":"Imitation Game: A Model-based and Imitation Learning Deep Reinforcement Learning Hybrid","created":"2024-04-02","cited_by_count":1,"area":"offlinerl"},{"id":"2410.00519","title":"Exploring the Learning Capabilities of Language Models using LEVERWORLDS","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2412.02579","title":"Factored space models: Towards causality between levels of abstraction","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2502.09137","title":"Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2503.09719","title":"Towards Causal Model-Based Policy Optimization","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2506.15377","title":"Efficient and Generalizable Environmental Understanding for Visual Navigation","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2602.10282","title":"Linear-LLM-SCM: Benchmarking LLMs for Coefficient Elicitation in Linear-Gaussian Causal Models","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2602.12963","title":"Calculating Mutual Information between a Reward Maximizer and its Environment","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2605.02640","title":"Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.06066","title":"Causal Reinforcement Learning for Complex Card Games: A Magic The Gathering Benchmark","created":"2026-05-07","cited_by_count":1,"area":"wm"},{"id":"2606.12268","title":"The Impossibility of Eliciting Latent Knowledge","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.18746","title":"What Must Generalist Agents Remember?","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2406.10917","title":"Bayesian Intervention Optimization for Causal Discovery","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2406.18178","title":"Games of Knightian Uncertainty as AGI testbeds","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2409.09169","title":"Curricula for Learning Robust Policies with Factored State Representations in Changing Environments","created":"2024-09-13","cited_by_count":0,"area":"deeprl"},{"id":"2410.06349","title":"Robust Domain Generalisation with Causal Invariant Bayesian Neural Networks","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2502.17172","title":"Teleology-Driven Affective Computing: A Causal Framework for Sustained Well-Being","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2505.14396","title":"Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worlds","created":"2025-05-20","cited_by_count":0,"area":"wm"},{"id":"2506.12304","title":"Conditional Average Treatment Effect Estimation Under Hidden Confounders","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2507.12473","title":"The Generalist Brain Module: Module Repetition in Neural Networks in Light of the Minicolumn Hypothesis","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2509.22553","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2602.17676","title":"Epistemic Traps: Rational Misalignment Driven by Model Misspecification","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.23545","title":"Planning under Distribution Shifts with Causal POMDPs","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.02678","title":"Causal Discovery Should Embrace the Wisdom of the Crowd","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.13595","title":"A Causal Framework for Mitigating Data Shifts in Healthcare","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.14691","title":"CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations","created":"2026-04-16","cited_by_count":0,"area":"agents"},{"id":"2605.02681","title":"The Design and Composition of Structural Causal Decision Processes","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.27580","title":"You Are in Control of Your State: Why Human Outcomes Are Controllable Through Causal State Intervention","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.29788","title":"Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.30132","title":"Learning to Extrapolate to New Tasks: A Relational Approach to Task Extrapolation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.29799","title":"The CRISTAL Method: Neurosymbolic analysis from AI-synthesized world models","created":"2026-06-29","cited_by_count":0,"area":"wm"},{"id":"2607.26336","title":"Learning Implicit Causal World Models from Multi-Agent Demonstrations","created":"2026-07-28","cited_by_count":0,"area":"wm"},{"id":"2608.07809","title":"CausalNav: Reliability-Certified Causal World Models for Control under Physical-Parameter Shift","created":"2026-08-07","cited_by_count":0,"area":"wm"},{"id":"2608.12325","title":"Position: Reasoning is a Learnable Rule-Based Process","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.13456","title":"A Unifying Perspective on Causal World Models: From Observations to Representations to Structure","created":"2026-08-13","cited_by_count":0,"area":"wm"},{"id":"2609.15289","title":"Math for AI safety: an invitation for mathematicians","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.31161","title":"I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?","created":"2026-09-25","cited_by_count":0,"area":"wm"},{"id":"2609.32247","title":"Certifying Interventional Agreement Among Observationally Equivalent Causal Models","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}