{"total":52,"rows":[{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228,"area":"agents"},{"id":"2106.05555","title":"Shades of BLEU, Flavours of Success: The Case of MultiWOZ","created":"2021-06-10","cited_by_count":48,"area":null},{"id":"2102.05126","title":"AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models","created":"2021-02-09","cited_by_count":31,"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":"2405.13028","title":"DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues","created":"2024-05-16","cited_by_count":24,"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":"2208.10817","title":"GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers","created":"2022-08-23","cited_by_count":23,"area":null},{"id":"2211.17148","title":"ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format","created":"2022-11-30","cited_by_count":22,"area":null},{"id":"2109.04919","title":"EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems","created":"2021-09-10","cited_by_count":20,"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":"2306.00774","title":"In-Context Learning User Simulators for Task-Oriented Dialog Systems","created":"2023-06-01","cited_by_count":19,"area":null},{"id":"2309.13233","title":"User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue","created":"2023-09-23","cited_by_count":19,"area":null},{"id":"2306.17674","title":"X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents","created":"2023-06-30","cited_by_count":13,"area":null},{"id":"2204.05928","title":"Dynamic Dialogue Policy for Continual Reinforcement Learning","created":"2022-04-12","cited_by_count":12,"area":null},{"id":"2109.13620","title":"Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking","created":"2021-09-28","cited_by_count":11,"area":null},{"id":"2204.00763","title":"Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems","created":"2022-04-02","cited_by_count":9,"area":null},{"id":"2109.04349","title":"Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance","created":"2021-09-09","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":"2109.05460","title":"End-to-End Conversational Search for Online Shopping with Utterance Transfer","created":"2021-09-12","cited_by_count":7,"area":null},{"id":"2207.12551","title":"DialCrowd 2.0: A Quality-Focused Dialog System Crowdsourcing Toolkit","created":"2022-07-25","cited_by_count":6,"area":null},{"id":"2210.08692","title":"A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems","created":"2022-10-17","cited_by_count":6,"area":null},{"id":"2401.18040","title":"Enhancing End-to-End Multi-Task Dialogue Systems: A Study on Intrinsic Motivation Reinforcement Learning Algorithms for Improved Training and Adaptability","created":"2024-01-31","cited_by_count":6,"area":"alignment"},{"id":"2111.01398","title":"Integrating Pretrained Language Model for Dialogue Policy Learning","created":"2021-11-02","cited_by_count":5,"area":null},{"id":"2207.12185","title":"Post-processing Networks: Method for Optimizing Pipeline Task-oriented Dialogue Systems using Reinforcement Learning","created":"2022-07-25","cited_by_count":5,"area":null},{"id":"2208.10448","title":"Dialogue Term Extraction using Transfer Learning and Topological Data Analysis","created":"2022-08-22","cited_by_count":5,"area":null},{"id":"2505.05445","title":"clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2102.04506","title":"A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining","created":"2021-02-08","cited_by_count":3,"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":"2204.11481","title":"\"Think Before You Speak\": Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs","created":"2022-04-25","cited_by_count":3,"area":null},{"id":"2209.00876","title":"Dialogue Evaluation with Offline Reinforcement Learning","created":"2022-09-02","cited_by_count":3,"area":null},{"id":"2212.06828","title":"An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertainty","created":"2022-12-13","cited_by_count":3,"area":null},{"id":"2508.19163","title":"MATRIX: Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation","created":"2025-08-26","cited_by_count":3,"area":"agents"},{"id":"2105.02482","title":"A Unified Pre-training Framework for Conversational AI","created":"2021-05-06","cited_by_count":2,"area":null},{"id":"2108.01369","title":"How to Evaluate Your Dialogue Models: A Review of Approaches","created":"2021-08-03","cited_by_count":2,"area":null},{"id":"2209.07873","title":"Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning","created":"2022-09-16","cited_by_count":2,"area":null},{"id":"2210.05252","title":"Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2106.04835","title":"Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System","created":"2021-06-09","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":"2302.11199","title":"Few-Shot Structured Policy Learning for Multi-Domain and Multi-Task Dialogues","created":"2023-02-22","cited_by_count":1,"area":null},{"id":"2304.00884","title":"Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation","created":"2023-04-03","cited_by_count":1,"area":null},{"id":"2401.02208","title":"DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models","created":"2024-01-04","cited_by_count":1,"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":"2301.04582","title":"A Personalized Utterance Style (PUS) based Dialogue Strategy for Efficient Service Requirement Elicitation","created":"2023-01-07","cited_by_count":0,"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":"2311.08705","title":"Evaluating Robustness of Dialogue Summarization Models in the Presence of Naturally Occurring Variations","created":"2023-11-15","cited_by_count":0,"area":null},{"id":"2401.03905","title":"WEBDial, a Multi-domain, Multitask Statistical Dialogue Framework with RDF","created":"2024-01-08","cited_by_count":0,"area":null},{"id":"2602.14710","title":"Orcheo: A Modular Full-Stack Platform for Conversational Search","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.23345","title":"Bridging Reasoning and Action: Hybrid LLM-RL Framework for Efficient Cross-Domain Task-Oriented Dialogue","created":"2026-04-25","cited_by_count":0,"area":"lr"},{"id":"2607.06873","title":"Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"id":"2609.22607","title":"Pretrained Persona Mixture Models and Tandem Models for Human Simulation","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":null}