{"total":37,"rows":[{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135,"area":null},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45,"area":null},{"id":"2311.05584","title":"Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations","created":"2023-11-09","cited_by_count":38,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2410.07927","title":"Efficient Reinforcement Learning with Large Language Model Priors","created":"2024-10-10","cited_by_count":30,"area":null},{"id":"2306.11886","title":"SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling","created":"2023-06-20","cited_by_count":24,"area":null},{"id":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","cited_by_count":19,"area":null},{"id":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16,"area":null},{"id":"2310.10735","title":"Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2305.15695","title":"Asking Before Acting: Gather Information in Embodied Decision Making with Language Models","created":"2023-05-25","cited_by_count":12,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2505.18098","title":"Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL","created":"2025-05-23","cited_by_count":11,"area":null},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2410.03968","title":"Decoding Game: On Minimax Optimality of Heuristic Text Generation Strategies","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2410.05559","title":"Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2307.12425","title":"On the Effectiveness of Offline RL for Dialogue Response Generation","created":"2023-07-23","cited_by_count":6,"area":null},{"id":"2512.20773","title":"DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation","created":"2025-12-23","cited_by_count":5,"area":null},{"id":"2412.02626","title":"Time-Reversal Provides Unsupervised Feedback to LLMs","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2503.02368","title":"Evolutionary Guided Decoding: Iterative Value Refinement for LLMs","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2505.11081","title":"ShiQ: Bringing back Bellman to LLMs","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2411.02930","title":"Textual Aesthetics in Large Language Models","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2303.13465","title":"Deep RL with Hierarchical Action Exploration for Dialogue Generation","created":"2023-03-22","cited_by_count":1,"area":null},{"id":"2311.08300","title":"Workflow-Guided Response Generation for Task-Oriented Dialogue","created":"2023-11-14","cited_by_count":1,"area":null},{"id":"2504.02646","title":"Prompt Optimization with Logged Bandit Data","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2501.07324","title":"Foundation Models at Work: Fine-Tuning for Fairness in Algorithmic Hiring","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2605.14004","title":"Conditional Attribute Estimation with Autoregressive Sequence Models","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.24743","title":"Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2605.26403","title":"From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2609.07303","title":"Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.11956","title":"Performance, Efficiency and Collapse -- Advantages and Challenges in Offline Post-training of Code LLMs","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2610.12995","title":"What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}