{"total":21,"rows":[{"id":"2311.16789","title":"A Survey of the Evolution of Language Model-Based Dialogue Systems: Data, Task and Models","created":"2023-11-28","cited_by_count":23,"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":"2310.08372","title":"Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment","created":"2023-10-12","cited_by_count":19,"area":null},{"id":"2311.09008","title":"End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions","created":"2023-11-15","cited_by_count":17,"area":null},{"id":"2401.04883","title":"Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations","created":"2024-01-10","cited_by_count":14,"area":null},{"id":"2312.10053","title":"Towards Goal-oriented Intelligent Tutoring Systems in Online Education","created":"2023-12-03","cited_by_count":7,"area":null},{"id":"2408.02417","title":"Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation","created":"2024-08-05","cited_by_count":5,"area":null},{"id":"2312.04668","title":"TOD-Flow: Modeling the Structure of Task-Oriented Dialogues","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2505.17795","title":"DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors","created":"2025-05-23","cited_by_count":4,"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":"2401.02417","title":"Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition","created":"2024-01-04","cited_by_count":1,"area":null},{"id":"2606.09293","title":"One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2307.06721","title":"Why Guided Dialog Policy Learning performs well? Understanding the role of adversarial learning and its alternative","created":"2023-07-13","cited_by_count":0,"area":null},{"id":"2309.00230","title":"JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning","created":"2023-09-01","cited_by_count":0,"area":null},{"id":"2309.02240","title":"Dialog Action-Aware Transformer for Dialog Policy Learning","created":"2023-09-05","cited_by_count":0,"area":null},{"id":"2312.11027","title":"Learning Top-k Subtask Planning Tree based on Discriminative Representation Pre-training for Decision Making","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2501.08067","title":"Optimal Policy Adaptation under Covariate Shift","created":"2025-01-14","cited_by_count":0,"area":null},{"id":"2509.19695","title":"DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual-Systems","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2601.02871","title":"SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.06877","title":"Personality-Aware Reinforcement Learning for Persuasive Dialogue with LLM-Driven Simulation","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2604.13817","title":"RPS: Information Elicitation with Reinforcement Prompt Selection","created":"2026-04-15","cited_by_count":0,"area":null}],"next_cursor":null}