{"total":62,"rows":[{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856,"area":"lr"},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713,"area":null},{"id":"2211.15657","title":"Is Conditional Generative Modeling all you need for Decision-Making?","created":"2022-11-28","cited_by_count":516,"area":"diffusion"},{"id":"2309.10668","title":"Language Modeling Is Compression","created":"2023-09-19","cited_by_count":225,"area":null},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2309.13638","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","created":"2023-09-24","cited_by_count":178,"area":null},{"id":"2309.16534","title":"MotionLM: Multi-Agent Motion Forecasting as Language Modeling","created":"2023-09-28","cited_by_count":156,"area":"agents"},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107,"area":null},{"id":"2208.02957","title":"Meaning without reference in large language models","created":"2022-08-05","cited_by_count":76,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2205.15967","title":"You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments","created":"2022-05-31","cited_by_count":63,"area":"offlinerl"},{"id":"2305.19308","title":"SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models","created":"2023-05-30","cited_by_count":57,"area":null},{"id":"2304.05524","title":"Understanding Causality with Large Language Models: Feasibility and Opportunities","created":"2023-04-11","cited_by_count":53,"area":null},{"id":"2210.09539","title":"Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving","created":"2022-10-18","cited_by_count":44,"area":"driving"},{"id":"2112.03763","title":"Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning","created":"2021-12-07","cited_by_count":40,"area":null},{"id":"2112.11941","title":"CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models","created":"2021-12-22","cited_by_count":34,"area":null},{"id":"2208.02225","title":"Sequence Model Imitation Learning with Unobserved Contexts","created":"2022-08-03","cited_by_count":34,"area":"offlinerl"},{"id":"2310.19704","title":"A Survey on Knowledge Editing of Neural Networks","created":"2023-10-30","cited_by_count":34,"area":null},{"id":"2410.05434","title":"Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback","created":"2024-10-07","cited_by_count":24,"area":"agents"},{"id":"2305.16183","title":"Passive learning of active causal strategies in agents and language models","created":"2023-05-25","cited_by_count":21,"area":"agents"},{"id":"2410.07071","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","created":"2024-10-09","cited_by_count":21,"area":"rag"},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2405.15815","title":"A social path to human-like artificial intelligence","created":"2024-05-22","cited_by_count":20,"area":null},{"id":"2402.08733","title":"Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2206.10816","title":"Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming","created":"2022-06-22","cited_by_count":15,"area":null},{"id":"2304.12502","title":"Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning Approach","created":"2023-04-25","cited_by_count":14,"area":"offlinerl"},{"id":"2304.06848","title":"CAR-DESPOT: Causally-Informed Online POMDP Planning for Robots in Confounded Environments","created":"2023-04-13","cited_by_count":12,"area":null},{"id":"2302.03189","title":"Emergent Causality and the Foundation of Consciousness","created":"2023-02-07","cited_by_count":9,"area":null},{"id":"2312.01097","title":"Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty","created":"2023-12-02","cited_by_count":9,"area":null},{"id":"2405.17009","title":"Position: Foundation Agents as the Paradigm Shift for Decision Making","created":"2024-05-27","cited_by_count":9,"area":"agents"},{"id":"2409.15730","title":"Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous Driving","created":"2024-09-24","cited_by_count":8,"area":"wm"},{"id":"2306.01157","title":"Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding","created":"2023-06-01","cited_by_count":7,"area":"offlinerl"},{"id":"2505.16477","title":"Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2510.08803","title":"Man-Made Heuristics Are Dead. Long Live Code Generators!","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2210.04303","title":"Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap","created":"2022-10-09","cited_by_count":5,"area":null},{"id":"2211.02667","title":"Deconfounding Imitation Learning with Variational Inference","created":"2022-11-04","cited_by_count":5,"area":"offlinerl"},{"id":"2308.09720","title":"On the Unexpected Abilities of Large Language Models","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2307.15980","title":"Initial State Interventions for Deconfounded Imitation Learning","created":"2023-07-29","cited_by_count":4,"area":"offlinerl"},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2407.18414","title":"Adversarially Robust Decision Transformer","created":"2024-07-25","cited_by_count":4,"area":"offlinerl"},{"id":"2606.12683","title":"From AGI to ASI","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2411.04653","title":"IGDrivSim: A Benchmark for the Imitation Gap in Autonomous Driving","created":"2024-11-07","cited_by_count":3,"area":"driving"},{"id":"2201.11218","title":"DNNFuser: Generative Pre-Trained Transformer as a Generalized Mapper for Layer Fusion in DNN Accelerators","created":"2022-01-26","cited_by_count":2,"area":null},{"id":"2206.01192","title":"Uniqueness and Complexity of Inverse MDP Models","created":"2022-06-02","cited_by_count":2,"area":null},{"id":"2311.10215","title":"Predictive Minds: LLMs As Atypical Active Inference Agents","created":"2023-11-16","cited_by_count":2,"area":"agents"},{"id":"2407.00495","title":"A Bayesian Solution To The Imitation Gap","created":"2024-06-29","cited_by_count":2,"area":"offlinerl"},{"id":"2409.18624","title":"Unsupervised Cognition","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2510.01620","title":"Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2402.05829","title":"Limitations of Agents Simulated by Predictive Models","created":"2024-02-08","cited_by_count":1,"area":"agents"},{"id":"2405.01139","title":"It Couldn't Help But Overhear: On the Limits of Modelling Meta-Communicative Grounding Acts with Supervised Learning","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2502.07656","title":"Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confounding","created":"2025-02-11","cited_by_count":1,"area":"offlinerl"},{"id":"2601.15714","title":"Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2606.29657","title":"Safety from Honesty in a Disinterested AI Predictor","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2403.14488","title":"COBRA-PPM: A Causal Bayesian Reasoning Architecture Using Probabilistic Programming for Robot Manipulation Under Uncertainty","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2410.07928","title":"The Function-Representation Model of Computation","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2502.19325","title":"Partition Tree Weighting for Non-Stationary Stochastic Bandits","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2505.08453","title":"Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges","created":"2025-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2601.22206","title":"Causal Imitation Learning Under Measurement Error and Distribution Shift","created":"2026-01-29","cited_by_count":0,"area":"offlinerl"},{"id":"2606.22495","title":"Grounded Scaling: Why Agentic AI Needs Deterministic Environments","created":"2026-06-21","cited_by_count":0,"area":"agents"},{"id":"2607.17003","title":"Scalable Causal Imitation Learning","created":"2026-07-18","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}