{"total":83,"rows":[{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2403.15371","title":"Can large language models explore in-context?","created":"2024-03-22","cited_by_count":76,"area":null},{"id":"2312.06528","title":"Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context","created":"2023-12-11","cited_by_count":63,"area":null},{"id":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2402.01258","title":"Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape","created":"2024-02-02","cited_by_count":46,"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":"2502.17543","title":"Training a Generally Curious Agent","created":"2025-02-24","cited_by_count":31,"area":"agents"},{"id":"2405.04669","title":"Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics","created":"2024-05-07","cited_by_count":27,"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":"2402.11639","title":"In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness","created":"2024-02-18","cited_by_count":22,"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":"2502.13913","title":"How Do LLMs Perform Two-Hop Reasoning in Context?","created":"2025-02-19","cited_by_count":20,"area":"lr"},{"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":"2404.18444","title":"U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models","created":"2024-04-29","cited_by_count":17,"area":"diffusion"},{"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":"2410.11778","title":"On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures","created":"2024-10-15","cited_by_count":15,"area":null},{"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":"2502.04204","title":"Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence","created":"2025-02-06","cited_by_count":14,"area":"safety"},{"id":"2409.17335","title":"Non-asymptotic Convergence of Training Transformers for Next-token Prediction","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2410.16670","title":"CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing","created":"2024-10-22","cited_by_count":12,"area":"lr"},{"id":"2506.05295","title":"Sample Complexity and Representation Ability of Test-time Scaling Paradigms","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"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":"2505.19241","title":"ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment","created":"2025-05-25","cited_by_count":10,"area":"lr"},{"id":"2410.24108","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","created":"2024-10-31","cited_by_count":8,"area":"offlinerl"},{"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":"2505.13499","title":"Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency","created":"2025-05-16","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":"2405.16819","title":"Automatic Domain Adaptation by Transformers in In-Context Learning","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2501.18187","title":"On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning","created":"2025-01-30","cited_by_count":7,"area":null},{"id":"2501.18793","title":"OT-Transformer: A Continuous-time Transformer Architecture with Optimal Transport Regularization","created":"2025-01-30","cited_by_count":7,"area":null},{"id":"2504.04204","title":"Adaptive Elicitation of Latent Information Using Natural Language","created":"2025-04-05","cited_by_count":7,"area":null},{"id":"2601.15014","title":"Efficient and Minimax Optimal In-context Nonparametric Regression with Transformers","created":"2026-01-21","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":"2310.15719","title":"AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2405.17234","title":"Benchmarking General-Purpose In-Context Learning","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2410.12783","title":"Context-Scaling versus Task-Scaling in In-Context Learning","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2512.04558","title":"On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference","created":"2025-12-04","cited_by_count":6,"area":"lr"},{"id":"2601.15158","title":"Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data","created":"2026-01-21","cited_by_count":6,"area":"lr"},{"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":"2410.05448","title":"Task Diversity Shortens the ICL Plateau","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2410.23610","title":"Global Convergence in Training Large-Scale Transformers","created":"2024-10-31","cited_by_count":5,"area":null},{"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":"2507.15759","title":"Interaction as Intelligence: Deep Research With Human-AI Partnership","created":"2025-07-21","cited_by_count":5,"area":null},{"id":"2510.12624","title":"Learning-To-Measure: In-Context Active Feature Acquisition","created":"2025-10-14","cited_by_count":5,"area":null},{"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":"2510.23254","title":"Optimal In-context Adaptivity and Distributional Robustness of Transformers","created":"2025-10-27","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":"2409.12446","title":"Neural Networks Generalize on Low Complexity Data","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2412.00979","title":"Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance","created":"2024-12-01","cited_by_count":3,"area":"offlinerl"},{"id":"2505.11918","title":"Transformers as Unsupervised Learning Algorithms: A study on Gaussian Mixtures","created":"2025-05-17","cited_by_count":3,"area":null},{"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":"2509.18389","title":"Towards Provable Emergence of In-Context Reinforcement Learning","created":"2025-09-22","cited_by_count":3,"area":"deeprl"},{"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":"2405.15115","title":"Towards Better Understanding of In-Context Learning Ability from In-Context Uncertainty Quantification","created":"2024-05-24","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":"2508.16027","title":"Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning","created":"2025-08-22","cited_by_count":2,"area":"deeprl"},{"id":"2603.01335","title":"Provable and Practical In-Context Policy Optimization for Self-Improvement","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"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":"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":"2410.19931","title":"Provable optimal transport with transformers: The essence of depth and prompt engineering","created":"2024-10-25","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":"2506.01919","title":"Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2604.05157","title":"IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents","created":"2026-04-06","cited_by_count":1,"area":"agents"},{"id":"2604.12817","title":"Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory","created":"2026-04-14","cited_by_count":1,"area":"safety"},{"id":"2605.07959","title":"Convergent Stochastic Training of Multi-Headed Attention and Understanding LoRA","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2504.06983","title":"Free Random Projection for In-Context Reinforcement Learning","created":"2025-04-09","cited_by_count":0,"area":"deeprl"},{"id":"2508.13657","title":"In-Context Decision Making for Optimizing Complex AutoML Pipelines","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2510.00347","title":"In-Context Curiosity: Distilling Exploration for Decision-Pretrained Transformers on Bandit Tasks","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.09908","title":"Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2605.09727","title":"One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning","created":"2026-05-10","cited_by_count":0,"area":"deeprl"},{"id":"2605.25210","title":"Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning","created":"2026-05-24","cited_by_count":0,"area":"diffusion"},{"id":"2605.29028","title":"Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.18812","title":"Reinforcement Learning Foundation Models Should Already Be A Thing","created":"2026-06-17","cited_by_count":0,"area":"deeprl"},{"id":"2606.31184","title":"Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.23333","title":"Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2609.30391","title":"From Weak Data to Strong Policy: Q-Targets Enable Provable In-Context Reinforcement Learning","created":"2026-09-24","cited_by_count":0,"area":"deeprl"},{"id":"2609.37659","title":"Are In-Context Images Worth 10 Dimensions?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.20004","title":"Provable Transformer Context Compression for In-Context Reinforcement Learning","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}