Task-Oriented Dialogue Systems

Ask about this topic

Overview

Task-oriented dialogue systems help people complete goals—such as booking, getting support, or filling forms—by tracking what is known and deciding what to ask or do next. Common approaches include modular intent and slot filling with dialogue state tracking and policy selection, as well as end-to-end language models that use schemas, tools, databases, or structured controllers. Work is evaluated on benchmarks such as MultiWOZ, Schema-Guided Dialogue, and SIMMC, alongside spoken, multilingual, and real-world service settings; newer methods also use simulators and synthetic dialogues for training and testing. A central challenge is making systems reliable over long interactions: they must preserve constraints, handle missing or conflicting information, avoid hallucinations, and adapt to users whose behavior may differ from that of simulated users.

Latest papers

CardsList

59 papers11 papers in the last four weeks, up 57% on the four weeks before. 0.1% of all new papers.

  1. Decoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation

    Oct 23, 2026Qiyuan Li, Xiaomei Guo, Chao Gao +4Synthetic Clinical Data GenerationText Generation

    School of Computer Science and Technology, Wuhan University of Science and Technology, China · Department of Cardiology, Tongji Hospital, Huazhong University of Science and Technology, China · Department of Computer Science, Vrije Universiteit Amsterdam, Netherlands +1

  2. Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues

    Oct 23, 2026Juan Li, Fangshu Chang, Xinyi Jiang +2User SimulationSynthetic Data Generation for LLM Agents

    Bairong Inc.

  3. ARGUS: An Agenda-Driven Framework for Reliable User Simulation

    Oct 15, 2026Hang Zheng, Nan Jiang, Zichen Zhu +6Task-Oriented Dialogue SystemsUser Simulation

    X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence SJTU AI Institute, Shanghai Jiao Tong University, Shanghai, China · Jiangsu Key Lab of Language Computing, Suzhou, China · AISpeech Co., Ltd., Suzhou, China +1

  4. Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive Dialogue

    Oct 15, 2026Zanwu Liu, Dan Zhang, Xiaodi Wang +6Conversational AgentsProactive Agents

    School of Artificial Intelligence, Beihang University, Beijing, China · Dongchezu Technology Co., Ltd., Beijing, China

  5. A Benchmark for Bangla Task-Oriented Dialogue Understanding

    Oct 13, 2026Afrina Alam Lamia, Sumiaya Sharif, Prottoy Modak +2State TrackingTask-Oriented Dialogue Systems

    East West University, Dhaka, Bangladesh

  6. MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents

    Oct 8, 2026Arkajyoti Chakraborty, Adam Zernik, Ishika Kulkarni +6Task-Oriented Dialogue SystemsAdversarial Robustness of Language Models

    University of California, Santa Cruz · Uniphore

  7. Conversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Training

    Oct 7, 2026Nafiseh Ghoroghchian, Luis Scoccola, Tina Sedaghat +4Task-Oriented Dialogue SystemsText-to-SQL

    Layer 6 AI

  8. Richard: Voice-First Mobile Interaction for Persistent Tasks

    Sep 30, 2026Xinyang ChenSpoken Dialogue SystemsConversational Agents

  9. ThuRunel: Dynamic Decoupling for Structured Advisory Dialogue

    Sep 28, 2026Yuyan ChenConversational AgentsHuman-AI Decision Making

    ModelsLive Inc.

  10. Proactive Dialogue Policy Optimization via Cognitive-State Transition

    Sep 28, 2026Minghui Ma, Mengqi Chen, Bin Guo +1Policy OptimizationConversational Agents

    Northwestern Polytechnical University

  11. SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents

    Sep 28, 2026Wenyi Yu, Siyin Wang, Terumi Chiba +5LLM Agent OrchestrationTool-Using Language Agents

    Tsinghua University · ByteDance

  12. Lost with a Map: Conversational State and Behavioral Reliability in Language Models

    Sep 27, 2026Atahan Dokme, Larry HeckSpoken Dialogue SystemsLLM Reliability

    Georgia Institute of Technology

  13. Large-Scale User Behavior Analysis in Multimodal AI-Assisted Manual Task Execution

    Sep 7, 2026Rafael Ferreira, Diogo Tavares, Diogo Glória-Silva +2Human-AI InteractionUser Modeling

    NOVA University of Lisbon, Portugal · NOVA LINCS, Portugal

  14. An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orchestration

    Sep 7, 2026Ramon Gonzalez, Antonio DiazRetrieval-Augmented GenerationSpoken Dialogue Systems

    Mentomy AI

  15. IRWOZ 2.0: A Large Language Model-driven Dialogue Dataset for Industrial Robot Conversations

    Sep 3, 2026Chen Li, Dimitrios ChrysostomouSpoken Dialogue SystemsSynthetic Data Generation for Robotics

    Department of Materials and Production, Aalborg University, Fibigerstraede 16, Aalborg, 9220, Denmark.

  16. PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation

    Sep 2, 2026Smitha Muthya Sudheendra, Jaideep SrivastavaText GenerationControllable Text Generation

    University of Minnesota, Twin Cities

  17. SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue Agents

    Aug 31, 2026Rayan Khoury, Shih-Yao Lin, Pratyush MishraLLM-as-a-JudgeMulti-Turn Dialogue Evaluation

    Microsoft

  18. Learning to Reason and Use Tools through Unsupervised Fine-Tuning in Task-Oriented Dialog Systems

    Aug 31, 2026Markel Ferro, Oier Lopez de LacalleSelf-Training for Language ModelsLLM Fine-Tuning

    HiTZ Center - Ixa, University of the Basque Country UPV/EHU

  19. DeepSAGE: Stage-Aware Reinforcement Learning for Structured CBT Counseling Dialogue

    Aug 23, 2026Qi Zhang, Heajun An, Prakriti Dumaru +4LLM AgentsRL for LLM Agents

    Virginia Tech · International Computer Science Institute · University of California, Davis

  20. Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does

    Aug 20, 2026Xinyi Liu, Hooshang Nayyeri, Dilek Hakkani-Tur +5Task-Oriented Dialogue SystemsVoice Agent Evaluation

    Amazon · University of Illinois Urbana-Champaign · University College London

  21. Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents

    Aug 16, 2026Meiling Tao, Yiling Tao, Peng WangState TrackingLLM Context Management

    University of Electronic Science and Technology of China · Shenzhen International Graduate School, Tsinghua University

  22. Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations

    Aug 12, 2026Lior Baruch, Moshe Butman, Kfir Bar +1Task-Oriented Dialogue Systems

    School of Computer Science Reichman University, Herzliya, Israel · Faculty of Computer Science The College of Management Academic Studies, Rishon LeZion, Israel

  23. Benchmarking the Benchmarks: Evaluating Benchmarks for Conversational Agents

    Aug 6, 2026Noam Koren, Roy Bar-Haim, Abigail GoldsteenAI Agent BenchmarksTask-Oriented Dialogue Systems

    IBM Research

  24. FormBharo: Designing and Evaluating a Voice Agent for Conversational Form Filling in Rural India

    Aug 6, 2026Aman Dalmia, Sanskriti Midha, Jigar DoshiVoice Agent EvaluationHealthcare

    Artpark, Indian Institute of Science, Bengaluru, Karnataka, India

  25. Everyone is unique: Towards Behaviorally Heterogeneous Negotiation Dialogue Systems for Debt Collection

    Jul 28, 2026Yuhang Yang, Kai Tang, Chao Ye +4Automated NegotiationLLM Agent Evaluation

    1State Key Laboratory of Blockchain and Data Security, Zhejiang University · 2Ant Group

  26. Low-Latency Turn-Taking via Context-Aware Preface Generation in a Real-World Dialogue Robot

    Jul 25, 2026Yuki Okafuji, Koji Inoue, Yoshiki OhiraSpoken Dialogue SystemsTask-Oriented Dialogue Systems

    CyberAgent Tokyo, Japan · The University of Osaka Osaka, Japan · Graduate School of Informatics Kyoto University Kyoto, Japan

  27. Candidate Attended Dialogue State Tracking Using BERT

    Jul 17, 2026Junyuan Zheng, Onkar Salvi, John ChanZero-Shot LearningSpoken Dialogue Systems

    OneConnect US Research Institute, New York, NY, 10019

  28. Towards Detecting Inconsistencies in End-to-end Generated TODs

    Jul 10, 2026Tiziano Labruna, Giovanni Bonetta, Bernardo MagniniLLM Hallucination DetectionConversational Agents

    Fondazione Bruno Kessler Povo, Trento, Italy

  29. TRACER: Early Failure Detection for Task-Oriented Dialogue

    Jul 4, 2026Erfan Nourbakhsh, Rocky Slavin, Ke Yang +1Spoken Dialogue SystemsFault Detection

    The University of Texas at San Antonio

  30. When the Database Fails: Prompting LLM Dialogue Agents for Safe Recovery in Task-Oriented Dialogue

    Jun 30, 2026Mohammad Alijanpour Shalmani, Alale Rezvani Boroujeni, Jiann Shiun YuanAI Agent ReliabilityLLM Hallucination Mitigation

    College of Engineering and Computer Science, University of Central Florida, Orlando, Florida · Department of Marketing, University of Central Florida, Orlando, Florida