Conversational Agents

Follow this topic Ask about this topic

Latest papers 219

37 papers in the last four weeks, up 32% on the four weeks before. 0.2% of all new papers.

All topics

Unlocking Proactivity in Task-Oriented Dialogue
May 21, 2026Azure Zhang, Ning Gao, Yuqin Dai +7LLM Post-Training Conversational Agents
1Keeta AI, Meituan · 2Independent Researcher · 3CUHK +1
From Lexicon to AI: A Structured-Data Pipeline for Specialized Conversational Systems in Low-Resource Languages
May 21, 2026Siddhant Hitesh Mantri, Dhara Gorasiya, Malhar Kulkarni +1Knowledge Augmentation for Language Models Synthetic Data Generation for Language Models
NMIMS, Mumbai · CFILT, IIT Bombay
Designing Conversations with the Dead: How People Engage with Generative Ghosts
May 20, 2026Jack Manning, Daniel Sullivan, Dylan Thomas Doyle +2Human-AI Interaction Human-Centered AI
University of Colorado Boulder, USA
LoCar: Localization-Aware Evaluation of In-Vehicle Assistants through Fine-Grained Sociolinguistic Control
May 20, 2026Seogyeong Jeong, Kiwoong Park, Seyoung Song +4LLM Evaluation Language Modeling
KAIST · BMW Group
ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions
May 19, 2026Chuanyang Jin, Binze Li, Haopeng Xie +6LLM Personalization Human-AI Interaction
Johns Hopkins University · Massachusetts Institute of Technology · Google Research
DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition
May 18, 2026Le Zhang, Shengming Zhang, Rui Zha +3Spoken Dialogue Systems LLM Agent Training
Baidu Inc., Beijing, China
PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures
May 15, 2026Yunan Lu, Luigi Liu, Omar Yahia +2AI Agent Reliability Adversarial Prompt Generation
Columbia University · University of California San Diego · Walmart
LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots
May 15, 2026Haoran Sun, Xinrui Song, Xinyu Zhang +7Retrieval-Augmented Generation Mechanism Design
Peking University · Shandong University · Alibaba Group
Conversations in Space: Non-Linear LLM Interaction in Everyday Use
May 15, 2026Rifat Mehreen Amin, Alperen Adatepe, Daniela Fernandes +2Human-AI Interaction Conversational Agents
LMU Munich · Munich, Germany · Aalto University +3
Adesua: Development and Feasibility Study of an AI WhatsApp Bot for Science Learning in West Africa
May 14, 2026George Boateng, Evans Atompoya, Philemon Badu +4Educational Technology AI in Education
ETH Zurich, Switzerland · Kwame AI Inc., U.S. · Charité - Universitätsmedizin Berlin, Germany
Understanding How International Students in the U.S. Are Using Conversational AI to Support Cross-Cultural Adaptation
May 14, 2026Laleh Nourian, Anisa Callis, Stephanie Patterson +3Educational Technology Human-AI Interaction
Rochester Institute of Technology, Rochester, NY, USA · School of Information, Rochester Institute of Technology, Rochester, NY, USA
From Sycophantic Consensus to Pluralistic Repair: Why AI Alignment Must Surface Disagreement
May 14, 2026Varad Vishwarupe, Nigel Shadbolt, Marina JirotkaLLM Sycophancy LLM Alignment
Department of Computer Science, University of Oxford · Institute for Ethics in AI, University of Oxford · Responsible Technology Institute, University of Oxford
MindGap: A Conversational AI Framework for Upstream Neuroplastic Intervention in Post-Traumatic Stress Disorder
May 14, 2026Eranga Bandara, Ross Gore, Asanga Gunaratna +16Mental Health Conversational Agents
Old Dominion University, Norfolk, VA, USA · AI Motion Labs, Melbourne, Australia · Department of Psychiatry and Neurobehavioral Sciences, University of Virginia School of Medicine, Charlottesville, VA, USA +5
Ottilie: A Socially Intelligent Virtual Host for Sales-Driven Live Commerce
May 14, 2026Yuyan ChenE-Commerce Conversational Agents
Cornell University
BOOKMARKS: Efficient Active Storyline Memory for Role-playing
May 13, 2026Letian Peng, Ziche Liu, Yiming Huang +4LLM Agent Memory Conversational Agents
University of California, San Diego
Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents
May 13, 2026Xubo Lin, Zezhi Deng, Shihao Wang +2Hierarchical RL Conversational Agents
Georgetown University · Singapore Management University
Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent
May 13, 2026Hao Wang, Ligong Han, Kai Xu +1Requirements Engineering Software Engineering Agents
Red Hat AI Innovation · MIT-IBM Watson AI Lab · IBM Core AI
Enhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword Bridging
May 12, 2026Maodong Li, Yancui Li, Fang KongConversational Agents
School of Computer Science and Technology, Soochow University, China · School of Computer and Information Engineering, Henan Normal University, China · Jiangsu Key Lab of Language Computing, Suzhou 215123, China
New AI-Driven Tools for Enhancing Campus Well-being: A Prevention and Intervention Approach
May 11, 2026Jinwen TangReinforcement Learning Depression Detection
University of Missouri-Columbia[cs.AI]
An Annotation Scheme and Classifier for Personal Facts in Dialogue
May 11, 2026Konstantin ZaitsevLLM Personalization Text Classification
Building Korean linguistic resource for NLU data generation of banking app CS dialog system
May 11, 2026Jeongwoo Yoon, On-yu Park, Changhoe Hwang +3Synthetic Data Generation Intent Classification
DICORA, Hankuk University of Foreign Studies · Université Gustave Eiffel
Towards Conversational Medical AI with Eyes, Ears and a Voice
May 10, 2026Meet Shah, Jason Gusdorf, Anil Palepu +50Audio-Visual Understanding Healthcare
ProactBench: Beyond What The User Asked For
May 9, 2026Sepehr Harfi, Ahmad Salimi, Dongming Shen +1LLM Agent Evaluation Proactive Assistance
Boson AI Toronto, ON, Canada · Boson AI Santa Clara, CA, USA
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents
May 9, 2026Minzheng Wang, Run Luo, Yanbo Wang +6Reinforcement Learning Self-Play RL
MAIS, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · National University of Singapore +1
AI-Care: A Conversational Agentic System for Task Coordination in Alzheimer's Disease Care
May 8, 2026Preyash Yadav, Michelle Cohn, Priyanka Koppolu +5Alzheimer's Disease Tool-Using Agents
Department of Computer Science University of California, Davis Davis, USA · Department of Linguistics University of California, Davis Davis, USA · Department of Neurology University of California, Davis Sacramento, USA +1
Playing games with knowledge: AI-Induced delusions need game theoretic interventions
May 8, 2026Will Beaumaster, Paul SchraterLLM Sycophancy Mechanism Design
University of Minnesota
What if AI systems weren't chatbots?
May 8, 2026Sourojit Ghosh, Pranav Narayanan Venkit, Sanjana Gautam +1Human-AI Interaction AI Governance
University of Washington Seattle, USA · Salesforce Research, USA · Microsoft, USA +2
MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes
May 7, 2026Maximillian Chen, Xuanming Zhang, Michael Peng +3Tool-Augmented Language Model Agents Multimodal Large Language Models
Columbia University · Seoul National University
When2Speak: A Dataset for Temporal Participation and Turn-Taking in Multi-Party Conversations for Large Language Models
May 7, 2026Vihaan Nama, Shreya Mendi, Zian Ye +1Synthetic Data Generation Synthetic Data Generation for Language Models
Pratt School of Engineering Duke University
Dynamic In-Group Persona Generation for Enhancing Human-AI Rapport
May 5, 2026Yoonseok Oh, Inseo Jung, Jinkyu Kim +3Human-AI Interaction Persona Prompting
Korea University · Kakao Mobility · University of California, Berkeley

May 21, 2026J/K move · Enter open · S save

Unlocking Proactivity in Task-Oriented Dialogue

Azure Zhang, Ning Gao, Yuqin Dai, Ruiyuan Wu+6

1Keeta AI, Meituan · 2Independent Researcher · 3CUHK+1

LLM Post-Training Conversational Agents User Simulation Task-Oriented Dialogue Systems Text Generation

Open paper AskPDF arXiv

Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that actively probes the user's concerns and steers the conversation toward acceptance within a bounded number of turns. Yet post-trained LLMs are inherently conservative, and reward-shaping RL (e.g., GRPO) struggles since it only re-weights what an already passive policy samples. We show that conditioning on the user's latent concerns unlocks proactive capability that no amount of sampling can undermine, establishing these concerns as a pivotal training-time signal. To operationalize this finding, we build the \textbf{Cognitive User Simulator}, which models each user as a stratified persona comprising observable external traits and hidden internal concerns. The simulator produces faithful and diverse interactions, while emitting per-turn state dynamics that track persuasion progress. We then introduce \textbf{Simulator-Induced Asymmetric-View Policy Optimization}, which converts the modeled concerns and the simulation state transition into complementary training objectives: (1) \emph{Asymmetric On-Policy Self-Distillation} that transfers concern-aware behavior from a privileged view of the same policy into its deployable, conversation-only view; and (2) \emph{State-Transition Policy Refinement} ...