{"list":"other","total":88,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429},{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417},{"id":"2507.17746","title":"Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains","created":"2025-07-23","cited_by_count":366},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"2404.18796","title":"Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models","created":"2024-04-29","cited_by_count":326},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"1710.06542","title":"Asymmetric Actor Critic for Image-Based Robot Learning","created":"2017-10-18","cited_by_count":238},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"2406.04770","title":"WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild","created":"2024-06-07","cited_by_count":218},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"2402.10811","title":"Quantifying the Persona Effect in LLM Simulations","created":"2024-02-16","cited_by_count":169},{"id":"1803.00101","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","created":"2018-02-28","cited_by_count":156},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144},{"id":"2406.02900","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","created":"2024-06-05","cited_by_count":143},{"id":"2507.18624","title":"Checklists Are Better Than Reward Models For Aligning Language Models","created":"2025-07-24","cited_by_count":128},{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124},{"id":"2508.12790","title":"Reinforcement Learning with Rubric Anchors","created":"2025-08-18","cited_by_count":113},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109},{"id":"2403.19154","title":"STaR-GATE: Teaching Language Models to Ask Clarifying Questions","created":"2024-03-28","cited_by_count":104},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80},{"id":"2410.13788","title":"Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions","created":"2024-10-17","cited_by_count":76},{"id":"2411.15100","title":"XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models","created":"2024-11-22","cited_by_count":75},{"id":"2407.17387","title":"PERSONA: A Reproducible Testbed for Pluralistic Alignment","created":"2024-07-24","cited_by_count":73},{"id":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70},{"id":"2405.14655","title":"Multi-turn Reinforcement Learning from Preference Human Feedback","created":"2024-05-23","cited_by_count":67},{"id":"2406.14868","title":"Direct Multi-Turn Preference Optimization for Language Agents","created":"2024-06-21","cited_by_count":64},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58},{"id":"2510.06552","title":"Flipping the Dialogue: Training and Evaluating User Language Models","created":"2025-10-08","cited_by_count":58},{"id":"2603.11245","title":"Mind the Sim2Real Gap in User Simulation for Agentic Tasks","created":"2026-03-11","cited_by_count":54},{"id":"2510.05444","title":"SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?","created":"2025-10-06","cited_by_count":50},{"id":"2403.09738","title":"Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation","created":"2024-03-13","cited_by_count":48},{"id":"2411.02306","title":"On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback","created":"2024-11-04","cited_by_count":47},{"id":"2511.02208","title":"Training Proactive and Personalized LLM Agents","created":"2025-11-04","cited_by_count":46},{"id":"2502.18968","title":"Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles","created":"2025-02-26","cited_by_count":41},{"id":"2412.16984","title":"LLM-Powered User Simulator for Recommender System","created":"2024-12-22","cited_by_count":39},{"id":"1908.10719","title":"Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog","created":"2019-08-28","cited_by_count":37},{"id":"2603.03303","title":"HumanLM: Simulating Users with State Alignment Beats Response Imitation","created":"2026-02-07","cited_by_count":37},{"id":"2504.07114","title":"ChatBench: From Static Benchmarks to Human-AI Evaluation","created":"2025-03-22","cited_by_count":34},{"id":"2505.13360","title":"What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts","created":"2025-05-19","cited_by_count":32},{"id":"2509.19736","title":"UserRL: Training Interactive User-Centric Agent via Reinforcement Learning","created":"2025-09-24","cited_by_count":32},{"id":"2410.04612","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","created":"2024-10-06","cited_by_count":30},{"id":"2308.11534","title":"PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator","created":"2023-08-21","cited_by_count":29},{"id":"2405.13028","title":"DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues","created":"2024-05-16","cited_by_count":24},{"id":"2406.01633","title":"On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots","created":"2024-06-01","cited_by_count":24},{"id":"2409.03753","title":"WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild","created":"2024-09-05","cited_by_count":20},{"id":"2306.00774","title":"In-Context Learning User Simulators for Task-Oriented Dialog Systems","created":"2023-06-01","cited_by_count":19},{"id":"2309.13233","title":"User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue","created":"2023-09-23","cited_by_count":19},{"id":"2408.13545","title":"IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering","created":"2024-08-24","cited_by_count":19},{"id":"2509.23124","title":"Non-Collaborative User Simulators for Tool Agents","created":"2025-09-27","cited_by_count":18},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18},{"id":"2505.15607","title":"From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning","created":"2025-05-21","cited_by_count":17},{"id":"2409.08330","title":"Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue","created":"2024-09-12","cited_by_count":16},{"id":"2407.03974","title":"LLM Roleplay: Simulating Human-Chatbot Interaction","created":"2024-07-04","cited_by_count":15},{"id":"2602.16938","title":"ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders","created":"2026-02-18","cited_by_count":12},{"id":"2504.07091","title":"AssistanceZero: Scalably Solving Assistance Games","created":"2025-04-09","cited_by_count":10},{"id":"2509.17619","title":"Human vs. Agent in Task-Oriented Conversations","created":"2025-09-22","cited_by_count":9},{"id":"2601.04436","title":"Learning to Simulate Human Dialogue","created":"2026-01-07","cited_by_count":9},{"id":"2601.16355","title":"Identity, Cooperation and Framing Effects within Groups of Real and Simulated Humans","created":"2026-01-22","cited_by_count":5},{"id":"2501.05032","title":"Enhancing Human-Like Responses in Large Language Models","created":"2025-01-09","cited_by_count":4},{"id":"2306.00858","title":"Adversarial learning of neural user simulators for dialogue policy optimisation","created":"2023-06-01","cited_by_count":2}],"next_cursor":null}