MIMESIS is a user simulator designed to train interactive language agents by mimicking real user behavior. It is trained on human conversations with explicit reasoning supervision and incorporates 13 realistic behavioral patterns. Experiments show that agents trained with MIMESIS outperform those trained with GPT-5.5 across multiple unseen simulators, and the proposed Coached On-Policy Self-Distillation further improves agent performance by providing dense, token-level supervision.
By Hoang Phan, Dat Huynh, Andrey Zhmoginov, Qi Zeng, Wancen Mu, Yue Cao, Shengjie Bi, Yun He, Changdae Oh, Deren Lei
ZenGen is a comprehensive framework designed to develop socially intelligent large language models (LLMs). It introduces SoMBench, a psychology‑grounded benchmark with 3 primary and 17 secondary dimensions, and shows that current LLMs perform poorly on social cognition tasks. ZenGen combines supervised fine‑tuning, on‑policy distillation, and rubric‑based reinforcement learning to improve internalization, while Actio provides deployment‑time grounding with typed supports such as PRISM, Starling, SAGE, and gated RAG, yielding significant performance gains across benchmarks.
By ZenGen Team, Ao Xiang, Bi Jingping, Chen Jiahui, Chen Lehan, Chen Yilin, Cheng Xueqi, Fan Yixing, Gan Kairong, Gao Haowen, Gao Jinhua, Gao Shuxuan, Gong Chang, Guo Jiafeng, Guo Ruijie, Han Zhouyu, He Guangfu, He Yichun, Jiang Shuo, Jing Shaoling, Jing Ya, Lei Chenhao, Lei Yan, Li Anqi, Li Chengao, Li Haoyu, Li Shitian, Liang Xinjian, Liu Zhaoge, Lyu Xingyu, Nie Zhuwei, Pang Liang, Quan Zeping, Shan Shiguang, Shen Huawei, Tang Xinran, Tian Feng, Wang Qian, Wang Ruiping, Wang Xiaohong, Xia Zaiyu, Xiao Yi, Xu Jiayuan, Xu Kehan, Xu Qianqian, Xu Tianyu, Xu Yongjun, Yang Haoming, Yang Jun, Yao Di, Yu Xiaoming, Zhang Futong, Zhang Jie, Zhang Shixuan, Zhang Yuxuan, Zhao Xinyu, Zhao Zhuoran, Zhong Yunfei, Zhu Shengyu
The paper introduces user simulators that provide intrinsic feedback by incorporating latent evaluation states such as internal thoughts, reactions, and scalar ratings. These simulators, trained on real user–assistant interaction logs, outperform prompted baselines in realism and critiquing behaviors, and their turn‑level evaluations better align with human judgments. Additionally, the intrinsic feedback serves as an effective reward signal for multi‑turn reinforcement learning, reducing compute requirements by over 50% compared to setups using external judge LLMs.
By Tarek Naous, Craig Boutilier, Wei Xu, Ofer Meshi
The paper introduces Collaborative Theory of Mind (CToM), a framework that trains large language models to anticipate user responses and use those predictions to self‑revise before finalizing a reply. By combining a user‑response prediction objective with group‑relative policy optimization, CToM improves collaborative task performance across mathematical reasoning, coding, and writing tasks, raising accuracy from 74.1% to 79.6% on a math task and reducing the number of user replies needed. Ablation studies show that accurate user‑response predictions lead to more efficient interactions and better outcomes.
By Fanzhi Zeng, Anubrata Das, Maytal Saar-Tsechansky, Liu Leqi
KnowSim introduces an evaluation framework that uses a user simulator with explicit knowledge states to assess how well large language models calibrate information to users. The simulator represents knowledge as a graph of Information Units with prerequisite relationships and updates these states based on learning theory. KnowSim computes Knowledge Gain, Delivery Calibration, and Cognitive Overload metrics, and its rankings align with human judgments, outperforming baseline simulators and revealing model performance differences across user knowledge levels.
By Yoonjoo Lee, Hyoungwook Jin, Tae Soo Kim, Shaoyang Zhang, Philippe Laban, Q. Vera Liao
arXiv:2602. 06470v3 Announce Type: replace-cross Abstract: Scaling training data and model parameters has long driven progress in large language models (LLMs), but this paradigm is increasingly constrained by the scarcity of high-quality data and diminishing returns from rising computational costs.
By Changyue Wang, Weihang Su, Qingyao Ai, Xingzhao Yue, Rui Zhang, Xiaojia Chang, Yiqun Liu
arXiv:2610.14709v1 Announce Type: cross
Abstract: Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommen...
By Yang Xiao, Yusong Sun, Haoyi Wu, Wenyang Hui, Weiqiang Hang, Luqing Wang, Zejian Wang, Zirui Tu, Jingsheng Mao, Shaobo Hu, Yang Luo, Jiale Guo, Jin Zhang, Yudan Liu, Zhaokai Luo, Ren Huan, Yao Hu, Chengyue Jiang, Wenjie Li, Chuan Mu
The paper introduces UserRepGen-4B, a representation generator that creates natural-language user representations to condition user simulators for more faithful conversation simulation. By formulating a conversation reconstruction task and using hindsight distillation, the system learns to generate representations that improve simulation fidelity across 700 conversations from seven datasets. The improved representations also enhance diversity preservation and user distinction in unseen tasks.
By Shuhaib Mehri, Philippe Laban, Michel Galley, Dilek T\"ur, Jennifer Neville, Jianfeng Gao
arXiv:2608. 16168v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly use external memory systems to support personalization by drawing on long and evolving interaction histories, in which user preferences may be distributed across time, change with context, and conflict with earlier evidence.
By Heng Wang, Yifei Li, Lingling Zhang, Pengyu Li, Xinyu Che, Xinyu Zhang, Zesheng Yang
arXiv:2605.12682v2 Announce Type: replace
Abstract: Large language models (LLMs) are increasingly used as reasoning modules in many applications, yet they often struggle to produce human-aligned deci...
By Alina Hyk, Sandhya Saisubramanian
ToM2Vec introduces continuous theory-of-mind tokens that enable large language model agents to reason about multiple possible partner states in multi‑agent settings. By training these tokens to abstract partner thoughts, the model generates latent representations that condition agents’ thoughts and actions, improving performance across collaborative, competitive, and mixed‑motive environments. The approach demonstrates that latent reasoning outperforms text‑based reasoning and generalizes to unseen partner models, with tokens encoding partner beliefs, desires, and next actions.
By Nithin Sivakumaran, Ali Payani, Hyunji Lee, Mohit Bansal, Elias Stengel-Eskin
arXiv:2610.07062v1 Announce Type: cross
Abstract: Large language models are increasingly used to simulate how individuals respond to new situations, yet the behavioral reasoning behind these response...
By Yining Zhao, Bushi Liu, Haofei Yu, Zhengyang Qi, Shanyong Wang, Chuyue Li, Yuxiang Liu, Jiaxuan You