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

TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents
Aug 24, 2026Wenhao Wu, Menghao Zhang, Xin Wang +3Tool-Augmented Language Model Agents LLM Agent Orchestration
Xiaomi Inc. · Nanjing University · Tsinghua University
Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiency
Aug 23, 2026Zhihong Cao, Chen HuangConversational Agents
School of Computing and Data Science, The University of Hong Kong · Institute of Data Science, National University of Singapore · College of Computer Science, Sichuan University
ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents
Aug 22, 2026Xiaoyu Wang, Qingqing Gu, Yue Zhao +5RL for Language Models Hierarchical RL
1Geely AI Lab · 2Beijing Institute of Technology · 3Peking University
AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations
Aug 22, 2026Rachel Poonsiriwong, Chayapatr, Archiwaranguprok +4AI Agent Monitoring Human Oversight of AI
Pub · MIT Media Lab Cambridge, MA, USA · KASIKORN Labs Nonthaburi, Thailand
Generating Diverse Personas for User Simulators to Test Interview Dialogue Systems
Aug 20, 2026Mikio Nakano, Kazunori Komatani, Hironori TakeuchiUser Simulation Persona-Conditioned Generation
C4A Research Institute, Inc., Setagaya, Tokyo, Japan · SANKEN, University of Osaka, Ibaraki, Osaka, Japan · Musashi University, Nerima, Tokyo, Japan
Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does
Aug 20, 2026Xinyi Liu, Hooshang Nayyeri, Dilek Hakkani-Tur +5Voice Agent Evaluation Conversational Agents
Amazon · University of Illinois Urbana-Champaign · University College London
Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges
Aug 18, 2026Syeda Faiza Ahmed Sara, Zien Sheikh Ali, Hunzalah Hassan Bhatti +2Conversational Agents Multimodal Agents
Qatar Computing Research Institute, HBKU, Qatar
Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Context
Aug 18, 2026Yiwen Zhao, Zhihao Wen, Yuchen Mao +5RL for LLM Agents Conversational Agents
Fudan University · Ant International, Ant Group
AdsWorldEngine: A Self-Evolving Conversational Advertising Agent through Orchestrator and Tool Coevolution
Aug 13, 2026Simiao Zuo, Chenhui Xu, Yimeng Jia +3Online Advertising Tool-Using Agents
Microsoft Redmond, WA, USA
Toward Meaningful Transparency for AI Chatbots: Disclosing Persuasive Intent Reduces Persuasion
Aug 12, 2026Adrian Rauchfleisch, Andreas JungherrHuman-AI Interaction AI Governance
1National Taiwan University · University of Bamberg
The Signal Rail: A Deterministic Motion Grammar for Communicating Conversational Agent State in Terminal Interfaces
Aug 11, 2026Matteo GrellaConversational Agents
Crisis24
Longitudinal Evidence That General-Purpose Chatbots Actively Foster Relational Engagement
Aug 11, 2026Lisa Mühl, Jessica M. SzczukaHuman-AI Interaction Conversational Agents
INTITEC Research Group, Social Psychology: Media and Communication, University of Duisburg-Essen, Duisburg, Germany · Research Center Trustworthy Data Science and Security, University Duisburg-Essen, Duisburg, Germany · Centre for Justice, Queensland University of Technology, Australia
Reducing belief in conspiracy theories as they unfold using large language models
Aug 6, 2026Thomas H. Costello, Nathaniel Rabb, Michael Nicholas Stagnaro +2Belief Revision Conversational Agents
Department of Social and Decision Sciences, Carnegie Mellon University, Pittsburgh, PA 15213 · Sloan School of Management, Massachusetts Institute of Technology, Cambridge, MA 02142, USA · Department of Psychology, Cornell University, Ithaca, NY 14853, USA +2
ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment
Aug 6, 2026Abdulkadir Külçe, Alihan Esen, Çağla Fikir +4Conversational Agents LLM Agent Safety
Dept. of Artificial Intelligence and Data Engineering, Istanbul Technical University, Istanbul, Turkey · Dept. of Computer Engineering, Istanbul Technical University, Istanbul, Turkey
FormBharo: Designing and Evaluating a Voice Agent for Conversational Form Filling in Rural India
Aug 6, 2026Aman Dalmia, Sanskriti Midha, Jigar DoshiVoice Agent Evaluation Healthcare
Artpark, Indian Institute of Science, Bengaluru, Karnataka, India
EmpaAva: An Open-source Agentic 3D-Avatar Empathetic Live Chatbot
Aug 5, 2026Jie Yang, Wenhao Xu, Shuhui Lin +1Conversational Agents Multimodal Agents
National University of Singapore · Tsinghua University · University of Oxford
Dr. AGENTONOMICS: A Didactic Experiment of AGENTONOMICS
Aug 4, 2026Fengjunjie Pan, Alois KnollLLM Agent Orchestration AI Agent Governance
Chair of Robotics, Artificial Intelligence and Real-Time Systems · TUM School of Computation, Information and Technology · Technical University of Munich
Homebot: A Personal AI Agent for Conversational Home Assistance and Automation
Aug 3, 2026Shengyuan Ye, Yixin Zhang, Han Liang +3Tool-Augmented Language Model Agents Tool-Using Agents
Power Dispatching and Controlling Center, Guangdong Power Grid Co., Ltd., Guangzhou, China · School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China · Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China
PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents
Aug 3, 2026Wonjun Choi, Yerim Kim, Yukyung Lee +1Agent Memory LLM Personalization
Korea University, Seoul, Korea · Boston University, Boston, USA
Sweet Little Lies: Strategic Deception in AI Emotional Support Chatbots
Aug 2, 2026Aseem Pahuja, Zhiling Guo, Tahir Abbas SyedEmotional Support Conversation Deception in Language Models
Alliance Manchester Business School, The University of Manchester, UK · G. Brint Ryan College of Business, University of North Texas, USA
Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO
Jul 30, 2026Xilin Jiang, Riki Shimizu, Sukru Samet Dindar +3Spoken Dialogue Systems Speech Language Models
Columbia University · University of Washington · University of Illinois Urbana-Champaign
VAmoS Bench: Voice Agent Simulation Bench
Jul 29, 2026Joshua Meyer, Sahar Shayegan, Ritiz Tambi +5Voice Agent Evaluation Customer Support Automation
Veris AI
Latent-IM: Latent Interaction Management for Speech LLMs
Jul 29, 2026Adar Avsian, Atahan Dokme, Tony Woo +1Language Model Steering Speech Language Models
Georgia Institute of Technology
Cognivia: A Cognitive Behavioral Therapy Copilot for Evidence-Based Mental Healthcare
Jul 28, 2026Qi Chen, Siria Xiyueyao Luo, Jian Wang +3Mental Health Counseling Conversational Agents
Sichuan University Sichuan, China · Southwest Petroleum University Sichuan, China · University of Groningen Netherland +3
Psychological Influences of Conversational AI: Research and Design Directions for Reducing Harm and Promoting Well-Being
Jul 27, 2026Jina Suh, Mihaela Vorvoreanu, Forough Poursabzi-Sangdeh +5Human-AI Interaction Human-Centered AI
Microsoft, USA · University of Washington · City University of New York, USA +1
Towards Reducing Foreign Language Anxiety Using Level-Appropriate Embodied Conversational Agents
Jul 24, 2026Krishan Rajaratnam, Wenbin Gan, Yuan SunMulti-Agent LLM Systems Conversational Agents
University of Oxford (UNITED KINGDOM) · National Institute of Information and Communications Technology (JAPAN) · National Institute of Informatics (JAPAN)
Safeguards for Speech2Speech LLM-Assistants: A Case Study in Automotive Applications
Jul 23, 2026Gregor Endler, Sebastian Kraus, Lukas StappenLanguage Model Safety Evaluation LLM Guardrails
codemanufaktur GmbH, Germany · BMW Group, Germany
LLMs Get Lost in Evolving User Intent
Jul 22, 2026Jihoon Tack, Philippe Laban, Jennifer NevilleLLM Agent Evaluation AI Agent Benchmarks
Microsoft Research
AdaHome: An Adaptive Smart Home Assistant using Local Small Language Models
Jul 20, 2026Eu Jin Lim, Zhaoxing Li, Sebastian SteinAdaptive Inference On-Device Language Model Inference
University of Southampton Southampton, United Kingdom
Toward Anthropomorphic Dialogue: A Closed-Loop Framework for Human-Like Chat Generation, Evaluation, and Preference Alignment
Jul 19, 2026Wentao Liu, Siyu Song, Xi Chen +4LLM Alignment Large Language Model-Based Role-Play Simulation
1Shanghai Institute of Innovation · 2East China Normal University · University of Science and Technology of China +3

Aug 24, 2026J/K move · Enter open · S save

TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents

Wenhao Wu, Menghao Zhang, Xin Wang, Zhi Wang+2

Xiaomi Inc. · Nanjing University · Tsinghua University

Tool-Augmented Language Model Agents LLM Agent Orchestration LLM Agent Self-Improvement LLM Agent Skill Learning AI Agent Benchmarks Conversational Agents+1

Open paper AskPDF arXiv

Reliable deployment of LLM agents in user-facing products depends not on raw task-solving ability but on consistency and limit-awareness: behaving the same way across repeated trials, and recognizing when a request cannot, or cannot yet, be safely fulfilled. CAR-bench exposes this reliability gap in the domain of in-car assistants: an LLM-simulated user issues incomplete or ambiguous requests, requiring the agent to resolve uncertainty through multi-turn dialogue and tool use while strictly adhering to domain policies. Even frontier models show a substantial gap between what they can solve at least once (Pass@3) and what they solve consistently across trials (Pass^k). We bridge this gap with TRACE (TRAjectory-Contrastive Evolution), which iteratively improves a skill-based agent's behavioral knowledge without modifying model weights. This knowledge is organized as a Skill Bank of modular, retrievable skills, each encoding a self-contained set of tool-use rules and behavioral guidelines. TRACE evolves this bank through an agentic self-evolution loop: after each evaluation round, it groups trajectories by the skills invoked and refines each skill by contrasting successful and failed behaviors. The updated bank then guides subsequent rounds, while during deployment the Actor performs state-conditioned skill orchestration at every turn. On GPT-5.5, TRACE improves consistency (Pass^3) by 34.6 points, from 59.9% to 94.5%, while shrinking the gap between potential and reliable performance to just 4.0 points. On the official hidden set, TRACE achieved first place using GPT-5.6-Sol, attaining a Pass^3 score of 70%-a 40% relative improvement over the baseline. These results show that TRACE converts high model potential into stable, consistent performance gain. Project homepage: https://darwin-agent.github.io/Car-bench-TRACE.