{"total":139,"rows":[{"id":"2406.10149","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","created":"2024-06-14","cited_by_count":215,"area":"lr"},{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197,"area":null},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"id":"2310.08566","title":"Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining","created":"2023-10-12","cited_by_count":83,"area":"offlinerl"},{"id":"2403.15371","title":"Can large language models explore in-context?","created":"2024-03-22","cited_by_count":76,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50,"area":null},{"id":"2506.07918","title":"CausalPFN: Amortized Causal Effect Estimation via In-Context Learning","created":"2025-06-09","cited_by_count":49,"area":null},{"id":"2309.17382","title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","created":"2023-09-29","cited_by_count":46,"area":"wm"},{"id":"2312.03801","title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","created":"2023-12-06","cited_by_count":39,"area":null},{"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":"2410.06238","title":"EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration","created":"2024-10-08","cited_by_count":34,"area":"lr"},{"id":"2402.14951","title":"In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization","created":"2024-02-22","cited_by_count":33,"area":null},{"id":"2412.01441","title":"LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations","created":"2024-12-02","cited_by_count":32,"area":"offlinerl"},{"id":"2506.10914","title":"Foundation Models for Causal Inference via Prior-Data Fitted Networks","created":"2025-06-12","cited_by_count":32,"area":null},{"id":"2502.17543","title":"Training a Generally Curious Agent","created":"2025-02-24","cited_by_count":31,"area":"agents"},{"id":"2506.06303","title":"Reward Is Enough: LLMs Are In-Context Reinforcement Learners","created":"2025-05-21","cited_by_count":31,"area":null},{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29,"area":null},{"id":"2312.12275","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","created":"2023-12-19","cited_by_count":27,"area":null},{"id":"2405.20692","title":"In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought","created":"2024-05-31","cited_by_count":26,"area":"lr"},{"id":"2312.13327","title":"In-Context Reinforcement Learning for Variable Action Spaces","created":"2023-12-20","cited_by_count":24,"area":null},{"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":"2312.06937","title":"Can a Transformer Represent a Kalman Filter?","created":"2023-12-12","cited_by_count":20,"area":null},{"id":"2505.00234","title":"Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks","created":"2025-05-01","cited_by_count":19,"area":"agents"},{"id":"2406.00079","title":"Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling","created":"2024-05-31","cited_by_count":18,"area":"ssm"},{"id":"2501.13896","title":"GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration","created":"2025-01-23","cited_by_count":18,"area":null},{"id":"2402.02429","title":"Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning","created":"2024-02-04","cited_by_count":17,"area":"offlinerl"},{"id":"2405.19883","title":"From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems","created":"2024-05-30","cited_by_count":17,"area":null},{"id":"2501.02709","title":"Horizon Generalization in Reinforcement Learning","created":"2025-01-06","cited_by_count":17,"area":"deeprl"},{"id":"2504.20997","title":"Toward Efficient Exploration by Large Language Model Agents","created":"2025-04-29","cited_by_count":17,"area":"agents"},{"id":"2406.12125","title":"Efficient Sequential Decision Making with Large Language Models","created":"2024-06-17","cited_by_count":16,"area":null},{"id":"2412.04759","title":"REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments","created":"2024-12-06","cited_by_count":16,"area":"rag"},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2311.00267","title":"Rethinking Decision Transformer via Hierarchical Reinforcement Learning","created":"2023-11-01","cited_by_count":14,"area":"offlinerl"},{"id":"2406.08973","title":"XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning","created":"2024-06-13","cited_by_count":14,"area":"deeprl"},{"id":"2410.22391","title":"A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks","created":"2024-10-29","cited_by_count":14,"area":"deeprl"},{"id":"2406.05565","title":"Medical Vision Generalist: Unifying Medical Imaging Tasks in Context","created":"2024-06-08","cited_by_count":13,"area":null},{"id":"2502.19009","title":"Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning","created":"2025-02-26","cited_by_count":13,"area":"deeprl"},{"id":"2506.10341","title":"Formalizing Learning from Language Feedback with Provable Guarantees","created":"2025-06-12","cited_by_count":13,"area":null},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","cited_by_count":11,"area":null},{"id":"2310.08549","title":"Cross-Episodic Curriculum for Transformer Agents","created":"2023-10-12","cited_by_count":10,"area":null},{"id":"2405.08989","title":"What is it for a Machine Learning Model to Have a Capability?","created":"2024-05-14","cited_by_count":10,"area":null},{"id":"2406.05064","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","created":"2024-06-07","cited_by_count":10,"area":"offlinerl"},{"id":"2501.19400","title":"Vintix: Action Model via In-Context Reinforcement Learning","created":"2025-01-31","cited_by_count":10,"area":"deeprl"},{"id":"2502.17666","title":"Yes, Q-learning Helps Offline In-Context RL","created":"2025-02-24","cited_by_count":10,"area":"offlinerl"},{"id":"2311.00226","title":"Transformers are Provably Optimal In-context Estimators for Wireless Communications","created":"2023-11-01","cited_by_count":8,"area":null},{"id":"2410.14001","title":"Personalized Adaptation via In-Context Preference Learning","created":"2024-10-17","cited_by_count":8,"area":"alignment"},{"id":"2502.00225","title":"Should You Use Your Large Language Model to Explore or Exploit?","created":"2025-01-31","cited_by_count":8,"area":null},{"id":"2505.13150","title":"Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2506.05426","title":"Mixture-of-Experts Meets In-Context Reinforcement Learning","created":"2025-06-05","cited_by_count":8,"area":"moe"},{"id":"2410.02751","title":"ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI","created":"2024-10-03","cited_by_count":7,"area":"deeprl"},{"id":"2411.01958","title":"N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs","created":"2024-11-04","cited_by_count":7,"area":"deeprl"},{"id":"2502.01118","title":"Large Language Model-Enhanced Multi-Armed Bandits","created":"2025-02-03","cited_by_count":7,"area":null},{"id":"2510.26389","title":"Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2602.04089","title":"Scaling In-Context Online Learning Capability of LLMs via Cross-Episode Meta-RL","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2307.10936","title":"PASTA: Pretrained Action-State Transformer Agents","created":"2023-07-20","cited_by_count":6,"area":"agents"},{"id":"2405.17234","title":"Benchmarking General-Purpose In-Context Learning","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2412.04111","title":"Adult Glioma Segmentation in Sub-Saharan Africa using Transfer Learning on Stratified Finetuning Data","created":"2024-12-05","cited_by_count":6,"area":null},{"id":"2505.10704","title":"ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data","created":"2025-05-15","cited_by_count":6,"area":null},{"id":"2405.14219","title":"Understanding the Training and Generalization of Pretrained Transformer for Sequential Decision Making","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2502.05187","title":"An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising","created":"2025-01-26","cited_by_count":5,"area":null},{"id":"2504.15046","title":"Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision","created":"2025-04-21","cited_by_count":5,"area":"offlinerl"},{"id":"2505.15143","title":"Filtering Learning Histories Enhances In-Context Reinforcement Learning","created":"2025-05-21","cited_by_count":5,"area":"deeprl"},{"id":"2506.01299","title":"Scalable In-Context Q-Learning","created":"2025-06-02","cited_by_count":5,"area":"wm"},{"id":"2507.09041","title":"Behavioral Exploration: Learning to Explore via In-Context Adaptation","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2507.15759","title":"Interaction as Intelligence: Deep Research With Human-AI Partnership","created":"2025-07-21","cited_by_count":5,"area":null},{"id":"2508.06659","title":"In-Context Reinforcement Learning via Communicative World Models","created":"2025-08-08","cited_by_count":5,"area":"wm"},{"id":"2510.12624","title":"Learning-To-Measure: In-Context Active Feature Acquisition","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2502.02869","title":"Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds","created":"2025-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2502.15609","title":"On the Robustness of Transformers against Context Hijacking for Linear Classification","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2604.12151","title":"Distinct mechanisms underlying in-context learning in transformers","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2406.18505","title":"Mental Modeling of Reinforcement Learning Agents by Language Models","created":"2024-06-26","cited_by_count":3,"area":"agents"},{"id":"2408.01384","title":"NOLO: Navigate Only Look Once","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2501.14176","title":"RL + Transformer = A General-Purpose Problem Solver","created":"2025-01-24","cited_by_count":3,"area":"deeprl"},{"id":"2503.19371","title":"Flow to Learn: Flow Matching on Neural Network Parameters","created":"2025-03-25","cited_by_count":3,"area":"diffusion"},{"id":"2505.14042","title":"Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2506.14448","title":"How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparison","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2506.21037","title":"RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment","created":"2025-06-26","cited_by_count":3,"area":"deeprl"},{"id":"2509.22353","title":"Context and Diversity Matter: The Emergence of In-Context Learning in World Models","created":"2025-09-26","cited_by_count":3,"area":"wm"},{"id":"2509.24923","title":"When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2509.25582","title":"Safe In-Context Reinforcement Learning","created":"2025-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2605.05755","title":"Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement","created":"2026-05-07","cited_by_count":3,"area":"deeprl"},{"id":"2311.04082","title":"Time-Efficient Reinforcement Learning with Stochastic Stateful Policies","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2401.00031","title":"Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges","created":"2023-12-29","cited_by_count":2,"area":null},{"id":"2403.03020","title":"SplAgger: Split Aggregation for Meta-Reinforcement Learning","created":"2024-03-05","cited_by_count":2,"area":"deeprl"},{"id":"2404.07266","title":"Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2410.19982","title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons","created":"2024-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2505.10861","title":"Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2511.06430","title":"CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models","created":"2025-11-09","cited_by_count":2,"area":null},{"id":"2601.14523","title":"Large Language Model-Powered Evolutionary Code Optimization on a Phylogenetic Tree","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2601.20116","title":"In-Context Reinforcement Learning From Suboptimal Historical Data","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2605.24423","title":"Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork","created":"2026-05-23","cited_by_count":2,"area":"deeprl"},{"id":"2405.11397","title":"Preparing for Black Swans: The Antifragility Imperative for Machine Learning","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2410.09701","title":"Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2411.19746","title":"HVAC-DPT: A Decision Pretrained Transformer for HVAC Control","created":"2024-11-29","cited_by_count":1,"area":null},{"id":"2506.19686","title":"From Memories to Maps: Mechanisms of In-Context Reinforcement Learning in Transformers","created":"2025-06-24","cited_by_count":1,"area":"deeprl"},{"id":"2507.10623","title":"Flows and Diffusions on the Neural Manifold","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2509.22764","title":"In-Context Learning can Perform Continual Learning Like Humans","created":"2025-09-26","cited_by_count":1,"area":null}],"next_cursor":"100"}