A long-standing goal of the research community is to develop highly interactive LLM-based dialogue agents. Recent research focuses on optimizing policies based on fixed offline logs (Static Context RL) or using a prompt-based simulator (Interactive RL). In this work, we theoretically show that both paradigms are fundamentally limited by context distribution shift--a mismatch between dialogue histories observed during training and those encountered in real conversations. This shift compounds quadratically over turns and severely degrades dialogue quality. Specifically, we attribute this shift to two distinct sources: (i) policy-induced shift, arising from training on static histories rather than self-generated trajectories; and (ii) simulator-induced shift, stemming from discrepancies between simulated and real human behaviors. To address these challenges, we propose Calibrated Interactive RL, a unified framework that couples interactive RL with simulator alignment. By aligning the simulator with human interaction patterns, our approach reduces the sim-to-real gap and mitigates compounding distribution shifts. Experiments across multiple dialogue tasks confirm our theoretical analysis: (i) Interactive RL significantly outperforms the Static Context baseline by mitigating policy distribution shift; and (ii) calibrating simulators with our alignment method further bridges the sim-to-real gap, yielding state-of-the-art downstream performance.
KokoroChat: A Japanese Psychological Counseling Dialogue Dataset Collected via Role-Playing by Trained Counselors
The University of Electro-Communications（电通通讯大学）；Rapport Technologies, Inc.（Rapport技术公司）；iDEAR Human Support Service（iDEAR人类支持服务）；Japanese Organization of Mental Health and Educational Agencies（日本心理健康与教育机构联合会）
HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
MAIS&NLPR, Institute of Automation, Chinese Academy of Sciences（自动化研究所人工智能与自然语言处理实验室，中国科学院）；School of Artificial Intelligence, UCAS（中国科学院大学人工智能学院）；Meituan（美团）
PsychēChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling
East China University of Science and Technology（东华大学）；Shanghai Changning Mental Health Center, Affiliated Mental Health Center of East China Normal University（上海昌宁心理健康中心，华东师范大学附属心理健康中心）
Mitigating the Negative Impact of Over-association for Conversational Query Production
School of Information, Xiamen University（厦门大学信息学院）；Xiamen Key Laboratory of Intelligent Storage and Computing（厦门智能存储与计算重点实验室）；Tencent AI Lab（腾讯AI实验室）；College of Computer and Control Engineering, Minjiang University（闽江学院计算机与控制工程学院）
Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
Xi’an Jiaotong University（西安交通大学）；National Engineering Laboratory for Big Data Analytics（国家大数据分析工程实验室）；Nanyang Technological University（南洋理工大学）；Lenovo Research（联想研究院）；University of Massachusetts Boston（马萨诸塞大学波士顿分校）；Zhejiang University of Technology（浙江工业大学）
C$^2$GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高陵人工智能学院）；Tsinghua University（清华大学）；Beijing Key Laboratory of Research on Large Models（北京大模型研究关键实验室）；Engineering Research Center of Next-Generation Intelligent Search（下一代智能搜索工程研究中心）
Robustness Risk of Conversational Retrieval: Identifying and Mitigating Noise Sensitivity in Qwen3-Embedding Model
Beijing University of Posts and Telecommunications（北京邮电大学）；SenseTime（商汤科技）；Beijing Key Laboratory of Network System and Network Culture（网络系统与网络文化北京市重点实验室）
FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；ELLIS Institute Tübingen（ELLIS图宾根研究所）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Tübingen AI Center（图宾根人工智能中心）
MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
Hong Kong University of Science（香港科学大学）；MMLab, Chinese University of Hong Kong, Hong Kong SAR（香港中文大学MMLab, 香港特别行政区）；The University of Hong Kong, Hong Kong SAR（香港大学, 香港特别行政区）
