{"total":16,"rows":[{"id":"2404.15155","title":"MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making","created":"2024-04-22","cited_by_count":163,"area":null},{"id":"2506.06303","title":"Reward Is Enough: LLMs Are In-Context Reinforcement Learners","created":"2025-05-21","cited_by_count":31,"area":null},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"area":null},{"id":"2406.07451","title":"A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models","created":"2024-06-11","cited_by_count":13,"area":null},{"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":"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":"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":"2502.05986","title":"Preventing Rogue Agents Improves Multi-Agent Collaboration","created":"2025-02-09","cited_by_count":3,"area":null},{"id":"2506.05855","title":"Optimized projection-free algorithms for online learning: construction and worst-case analysis","created":"2025-06-06","cited_by_count":3,"area":null},{"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":"2501.08925","title":"Disentangling Exploration of Large Language Models by Optimal Exploitation","created":"2025-01-15","cited_by_count":1,"area":null},{"id":"2601.12945","title":"A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Bandits","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2601.11905","title":"LIBRA: Language Model Informed Bandit Recourse Algorithm for Personalized Treatment Planning","created":"2026-01-17","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":"2610.07587","title":"Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.14790","title":"Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}