{"total":57,"rows":[{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2109.05794","title":"Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions","created":"2021-09-13","cited_by_count":63,"area":null},{"id":"2510.06552","title":"Flipping the Dialogue: Training and Evaluating User Language Models","created":"2025-10-08","cited_by_count":58,"area":null},{"id":"2603.11245","title":"Mind the Sim2Real Gap in User Simulation for Agentic Tasks","created":"2026-03-11","cited_by_count":54,"area":"agents"},{"id":"2404.06711","title":"MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education","created":"2024-04-10","cited_by_count":37,"area":null},{"id":"2107.11904","title":"Transferable Dialogue Systems and User Simulators","created":"2021-07-25","cited_by_count":36,"area":null},{"id":"2104.05565","title":"Survey on reinforcement learning for language processing","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2202.13675","title":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning","created":"2022-02-28","cited_by_count":30,"area":null},{"id":"2402.13374","title":"Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems","created":"2024-02-20","cited_by_count":25,"area":null},{"id":"2106.08838","title":"Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems","created":"2021-06-16","cited_by_count":23,"area":null},{"id":"2405.13003","title":"A Survey on Recent Advances in Conversational Data Generation","created":"2024-05-12","cited_by_count":23,"area":null},{"id":"1801.06176","title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning","created":"2018-01-18","cited_by_count":21,"area":"wm"},{"id":"2507.20152","title":"Goal Alignment in LLM-Based User Simulators for Conversational AI","created":"2025-07-27","cited_by_count":21,"area":null},{"id":"2305.08195","title":"Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing","created":"2023-05-14","cited_by_count":19,"area":null},{"id":"2207.14393","title":"LAD: Language Models as Data for Zero-Shot Dialog","created":"2022-07-28","cited_by_count":18,"area":null},{"id":"2105.14454","title":"NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation","created":"2021-05-30","cited_by_count":16,"area":null},{"id":"2210.14529","title":"Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with User Simulator","created":"2022-10-26","cited_by_count":15,"area":null},{"id":"2210.05664","title":"Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks","created":"2022-10-11","cited_by_count":14,"area":null},{"id":"1811.07550","title":"Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning","created":"2018-11-19","cited_by_count":12,"area":"wm"},{"id":"2404.18564","title":"Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning","created":"2024-04-29","cited_by_count":9,"area":"lr"},{"id":"2207.11762","title":"Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System","created":"2022-07-24","cited_by_count":8,"area":null},{"id":"2103.01287","title":"DEUS: A Data-driven Approach to Estimate User Satisfaction in Multi-turn Dialogues","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2602.03548","title":"SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue","created":"2026-02-03","cited_by_count":7,"area":"agents"},{"id":"2110.06905","title":"Teaching Models new APIs: Domain-Agnostic Simulators for Task Oriented Dialogue","created":"2021-10-13","cited_by_count":6,"area":null},{"id":"2506.12266","title":"The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs","created":"2025-06-13","cited_by_count":6,"area":"agents"},{"id":"2410.12891","title":"Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2302.09522","title":"Interactive Video Corpus Moment Retrieval using Reinforcement Learning","created":"2023-02-19","cited_by_count":4,"area":null},{"id":"2605.20506","title":"Reinforcing Human Behavior Simulation via Verbal Feedback","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2106.00891","title":"High-Quality Diversification for Task-Oriented Dialogue Systems","created":"2021-06-02","cited_by_count":3,"area":null},{"id":"2210.12942","title":"Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2608.12355","title":"Humans are Missing from AI Coding Agent Research","created":"2026-07-04","cited_by_count":3,"area":"agents"},{"id":"2105.10267","title":"Towards a Universal NLG for Dialogue Systems and Simulators with Future Bridging","created":"2021-05-21","cited_by_count":2,"area":null},{"id":"2303.00908","title":"Interactive Text Generation","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2402.00085","title":"Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning","created":"2024-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2504.18058","title":"Exploring Personality-Aware Interactions in Salesperson Dialogue Agents","created":"2025-04-25","cited_by_count":2,"area":null},{"id":"2506.03519","title":"An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals","created":"2025-06-04","cited_by_count":2,"area":"alignment"},{"id":"2604.13828","title":"MUSE: Multi-Domain Chinese User Simulation via Self-Evolving Profiles and Rubric-Guided Alignment","created":"2026-04-15","cited_by_count":2,"area":"alignment"},{"id":"2606.20708","title":"Simulated Customers Never Walk Away: Decision Fidelity of LLM User Simulators Measured Against Real Purchase Outcomes","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2102.02435","title":"Converse, Focus and Guess -- Towards Multi-Document Driven Dialogue","created":"2021-02-04","cited_by_count":1,"area":null},{"id":"2110.12412","title":"Improved Goal Oriented Dialogue via Utterance Generation and Look Ahead","created":"2021-10-24","cited_by_count":1,"area":null},{"id":"2211.11982","title":"BotSIM: An End-to-End Bot Simulation Framework for Commercial Task-Oriented Dialog Systems","created":"2022-11-22","cited_by_count":1,"area":null},{"id":"2305.03262","title":"Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization","created":"2023-05-05","cited_by_count":1,"area":null},{"id":"2305.03987","title":"Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization","created":"2023-05-06","cited_by_count":1,"area":"offlinerl"},{"id":"2308.01479","title":"Investigating Reinforcement Learning for Communication Strategies in a Task-Initiative Setting","created":"2023-08-03","cited_by_count":1,"area":null},{"id":"2401.05822","title":"Towards Goal-Oriented Agents for Evolving Problems Observed via Conversation","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2503.04675","title":"LLM-guided Plan and Retrieval: A Strategic Alignment for Interpretable User Satisfaction Estimation in Dialogue","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2507.18017","title":"Fashion-AlterEval: A Dataset for Improved Evaluation of Conversational Recommendation Systems with Alternative Relevant Items","created":"2025-07-24","cited_by_count":1,"area":null},{"id":"2602.22697","title":"Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue","created":"2026-02-26","cited_by_count":1,"area":"agents"},{"id":"2607.10428","title":"Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2609.01591","title":"StudentSim: Training LLM-based Student Simulators","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2109.13029","title":"Every time I fire a conversational designer, the performance of the dialog system goes down","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2211.15916","title":"BotSIM: An End-to-End Bot Simulation Toolkit for Commercial Task-Oriented Dialog Systems","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2305.16852","title":"Model-Based Simulation for Optimising Smart Reply","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2510.08621","title":"From Simulation to Strategy: Automating Personalized Interaction Planning for Conversational Agents","created":"2025-10-08","cited_by_count":0,"area":"agents"},{"id":"2604.02713","title":"Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2608.19549","title":"Generating Diverse Personas for User Simulators to Test Interview Dialogue Systems","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2610.13617","title":"Training User Simulators with Latent Intrinsic Feedback","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}