Multi-Turn Interactions

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 44

All topics

You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue
Oct 5, 2026Junle Chen, Wei Chen, Zhengjun Huang +5Multi-Turn Interactions Instruction-Tuned Models
HKUST · Tencent
CLIMB: A Clinical Multimorbidity Benchmark for Diagnosing Co-occurring Conditions through Multiturn Conversations
Sep 28, 2026Yusuf Kesmen, Aniruddha Mukherjee, Yena Chang +7Multimorbidity Clinical Decision Support
EPFL · Aarhus University
The Marathon of Scientific Reasoning: Robustness of Scientific Agents to Perturbations in Multi-Turn Interactions
Sep 28, 2026Xiaoting Lyu, Xinbo Ma, Yufei Han +5Scientific Discovery Scientific Agents
Xi’an Jiaotong University, China · Inria, France · Agency for Science, Technology and Research (A*STAR), Singapore +1
TRACER: Trajectory-Aligned Learning for Multi-Turn User Simulation
Sep 23, 2026Geng Chen, Ruotong Pan, Zhirui Yang +9User Simulation Multi-Turn Interactions
Peking University · Kuaishou Technology · Xi’an Jiaotong University +3
Critical-State RL: Diagnosing Trainable States for Multi-Turn Tool Use
Sep 21, 2026Zixiang Chen, Wenting Zhao, Zhepeng Cen +9Critic-Free Reinforcement Learning Offline Reinforcement Learning
Salesforce AI Research
DyMT-ESB: Dynamic Multi-Turn Evaluation of Social Bias in User-LLM Interactions
Sep 16, 2026Rem Hida, Masahiro Kaneko, Daisuke Oba +2Large Language Model Bias Multi-Turn Interactions
Institute of Science Tokyo · MBZUAI · Third Intelligence +1
$S^3$ -Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants
Sep 9, 2026Heyang Liu, Jiayi Huang, Wenyang Xiao +8Speech Language Models Full-Duplex Voice Agents
Shanghai Jiao Tong University · Ant Group · Tongji University
Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling
Sep 1, 2026Kangjia Zhao, Jiajun Li, Haozhan Shen +8Multi-Turn Interactions Diagnostic Framework
Zhejiang University · Shanghai Jiao Tong University · National University of Singapore +3
Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn Reasoning
Aug 31, 2026Jie Liang, Zhengxin Yu, Hamid Nasiri +1Reasoning Trajectory Multi-Turn Interactions
School of Computing and Communications, Lancaster University, UK · School of Computing and Engineering, University of Huddersfield, UK
EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants
Aug 29, 2026Yue Peng, Lanke Xia, Zihan Wang +3Generative User Interface Multi-Turn Interactions
New York University Shanghai
HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning
Aug 22, 2026Yucan Guo, Xiaohan Wang, Miao Su +8Multi-Turn Interactions Credit Assignment
State Key Laboratory of AI Safety · Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences +1
Hy-MultiTurn: A Six-Dimensional Benchmark for Deep Multi-Turn Dialogue Understanding
Jul 31, 2026Eileen Ye, Jiawen Tao, Yaoming Li +7Multi-Turn Interactions Dialogue
Hunyuan Team, Tencent · Peking University
Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions
Jul 29, 2026Shi Lin, Peng Qian, Dinghao Liu +5Large Language Model Safety Multi-Turn Interactions
1Zhejiang Gongshang University · 2Shandong University · 3Hainan University +1
OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars
Jul 25, 2026Quanyue Song, Yishan He, Yanbo Ding +4Audio-Video Generation Audio-Visual Consistency
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, China · China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd., China · Shenzhen Key Laboratory of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
LLMs Get Lost in Evolving User Intent
Jul 22, 2026Jihoon Tack, Philippe Laban, Jennifer NevilleMulti-Turn Interactions Conversational Context
Microsoft Research
Clarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration
Jul 17, 2026Xiaoye Zhu, Weixin Li, Junan Huo +53D Generation Multi-Turn Interactions
South China University of Technology Guangzhou, Guangdong, China
Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions
Jul 16, 2026Yijiang Li, Huiqi Zou, Bingyang Wang +1Large Language Model Evaluation Large Language Model Hallucination
UC San Diego · Northeastern University · Georgia Institute of Technology +1
MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
Jul 14, 2026Xixuan Hao, Zeyu Zhang, Zehao Lin +6Conversational Memory Nativemem
MemTensor (Shanghai) Technology Co., Ltd. · The Hong Kong University of Science and Technology (Guangzhou) · Renmin University of China
Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web Services
Jun 18, 2026Mugeng Liu, Shuoqi Li, Yixuan Zhang +1Tool Invocation Agentic Workflows
School of Computer Science, Peking University, Beijing, China · School of Software & Microelectronics, Peking University, Beijing, China · Institute for Artificial Intelligence, Peking University, Beijing, China
AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts
Jun 18, 2026Yanyu Yao, Shangze Li, Zhi Zheng +4Peak Memory Large Language Model Agents
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China · Anhui University, Hefei, China
Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models
Jun 9, 2026Atsumoto Ohashi, Neil Zeghidour, Alexandre Défossez +1Full-Duplex Speech Models Multi-Turn Interactions
Kyutai, Paris, France · Gradium, Paris, France
Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs
Jun 9, 2026Saeid Jamshidi, Amin Nikanjam, Arghavan Moradi Dakhel +2Model Context Protocol Multi-Turn Interactions
SWAT Laboratory, Polytechnique Montréal, Montréal, QC, Canada · Huawei Distributed Scheduling and Data Engine Lab, Montr´eal, QC, Canada
IMUG-Bench: Benchmarking Unified Multimodal Models on Interleaved Understanding and Generation
Jun 8, 2026Lingyi Meng, Zecong Tang, Haoran Li +12Multi-Turn Interactions Multimodal Model
Zhejiang University · Institute of Automation, Chinese Academy of Sciences · The University of Hong Kong +1
Evidence-Based Intelligent Diagnostic and Therapeutic Visualization System with Large Language Models: Multi-Turn Interaction and Multimodal Treatment Plan Generation
Jun 5, 2026Yunhan Wang, Yuda Wang, Zhiying Tu +5Knowledge Graphs Multi-Turn Interactions
Harbin Institute of Technology, Weihai, Weihai, Shandong, China · Shandong Key Laboratory of Digital Service Computing Technology and Systems, China · Weihai Municipal Hospital, Weihai, Shandong, China +3
CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Model
Jun 4, 2026Zeyang Yue, Chenfei Yan, Feifei Zhao +5Large Language Model Safety Emotional Manipulation
School of Artificial Intelligence, Beihang University · 2BrainCog AI Lab, CASIA · School of Artificial Intelligence, UCAS +4
THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models
Jun 1, 2026Zhiqing Ma, Zhonghao Xu, Dong Yu +3Large Language Model Jailbreaks Jailbreak Attacks
1Beijing Language and Culture University · †Corresponding authors
MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for Medical AI Safety
May 30, 2026Anushka Sheoran, Yiduo HaoArtificial Intelligence Safety Multi-Turn Interactions
University of Pennsylvania
Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games
May 26, 2026Mingyuan Fan, Weiguang Han, Daixin Wang +3Multi-Turn Interactions Metacognition
East China Normal University · Ant Group
Clarification Is Not Enough: Post-Clarification Answering Remains the Bottleneck in Multi-Turn QA
May 24, 2026Jinyan Su, Jennifer HealeyClarification Multi-Turn Interactions
1Cornell University · 2Adobe Research
Towards Multi-Turn Dialog Systems for Industrial Asset Operations and Maintenance
May 24, 2026Chengrui Li, Rujing Li, Yitong Bai +1Multi-Turn Interactions Reuse
Columbia University
EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions
May 22, 2026Haiyang Shen, Xuanzhong Chen, Wendong Xu +3Coding Agents Multi-Turn Interactions
1UniPat AI · 2Peking University · 3Tsinghua University +1
Emotion-Attended Stateful Memory (EASM):The Architecture for Hyper-Personalization at Scale
May 14, 2026Vineet Kotecha, Vansh GuptaLarge Language Model Personalization Persistent State
divAIne Research
When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
May 13, 2026Vardhan Dongre, Joseph Hsieh, Viet Dac Lai +3Large Language Models Fail Multi-Turn Interactions
University of Illinois Urbana-Champaign · Adobe Research
Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking
May 9, 2026Zhida He, Xiaoyu Wen, Han Qi +7Jailbreak Attacks Jailbreaks
Shanghai AI Laboratory · Fudan University · Shanghai Jiao Tong University
How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation
May 7, 2026Shai Feldman, Yaniv RomanoLarge Language Model Jailbreaks Jailbreak Attacks
Department of Computer Science Technion, Israel · Departments of Electrical & Computer Engineering. and Computer Science Technion, Israel
BALAR : A Bayesian Agentic Loop for Active Reasoning
May 6, 2026Aymen Echarghaoui, Dongxia Wu, Emily B. FoxLLM Reasoning Strategies Multi-Turn Interactions
Department of Statistics, Stanford University · Department of Computer Science, Stanford University
Evaluating Temporal Consistency in Multi-Turn Language Models
Apr 24, 2026Yash Kumar Atri, Steven L. Johnson, Tom HartvigsenMulti-Turn Interactions Temporal Reasoning
University of Virginia
DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents
Apr 21, 2026Shengqin Wang, Wentao Yan, Huichi Zhou +4Multimodal Search Agents Multimodal Agents
East China Normal University · University College London · Huawei Noah’s Ark Lab +2
SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference
Feb 24, 2026Cuong Chi Le, Minh V. T Pham, Tung Vu Duy +4Llm-Driven Code Synthesis Self-Speculative
The University of Texas at Dallas · FPT Software AI Center · VinUniversity +1
Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
Dec 8, 2025Sijia Li, Yuchen Huang, Zifan Liu +6Episodic Memory Multi-Turn Reinforcement Learning
Hong Kong University of Science and Technology · Microsoft Research Asia · Work done during internship at Microsoft.
GMTRouter: Personalized LLM Router over Multi-turn User Interactions
Oct 29, 2025Yihang Sun, Encheng Xie, Tao Feng +1Large Language Model Routing Large Language Model Personalization
University of Illinois Urbana-Champaign
Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks
Oct 16, 2025Trilok Padhi, Pinxian Lu, Abdulkadir Erol +5Attacker Large Language Model Multi-Turn Interactions
1Georgia State University · 2Georgia Institute of Technology · University of California, Berkeley
Post-training for Efficient Communication via Convention Formation
Aug 8, 2025Yilun Hua, Evan Wang, Yoav ArtziPost-Training Multi-Turn Interactions
Department of Computer Science and Cornell Tech Cornell University
Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
Jul 7, 2025Yuanzhe Hu, Yu Wang, Julian McAuleyAgentic Memory Large Language Model Agents
University of California, San Diego

Oct 5, 2026, cs.AIJ/K move · Enter open · S save

You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue

Junle Chen, Wei Chen, Zhengjun Huang, Zhoujin Tian+4

HKUST · Tencent

Multi-Turn Interactions Instruction-Tuned Models

Open paper AskPDF arXiv

When a large language model handles a multi-turn task and a user proposes a change but ultimately rejects it, the model should continue as if nothing changed. We find a surprising failure: merely mentioning a rejected change can derail task execution, even when the user's final intent remains unchanged. To systematically study language model behavior under evolving user intent, we introduce Intent-Eval, a controlled benchmark spanning tool actions, code, databases, and mathematics. Across diverse tasks, models are vulnerable to both rejected proposals and superseded requirements, consistent with mentioned-as-in-effect confusion: conversational content is treated as active requirements even after it has been rejected or replaced. Accuracy degradation can deepen or persist as interaction continues, highlighting the need to distinguish what has been mentioned from what remains in effect. Building on this insight, we propose Intent-OPSD, a decision-conditioned on-policy self-distillation framework with Teacher and Student initialized from the same model. The frozen Teacher provides active-intent supervision from the complete task matching the user's decision, training the Student on the full dialogue to follow active requirements reflecting user intent.

Momentum

Related topics

Latest papers 44