arXiv Machine Learning
Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 9
MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
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.
arXiv Computation and Language
Aug 24
ZenGen: Social Mind for LLMs
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.
arXiv Computation and Language
Oct 12
Training User Simulators with Latent Intrinsic Feedback
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.
arXiv AI
Oct 12
Collaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses
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.
arXiv AI
Aug 19
KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn
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.
arXiv AI
Jun 18
Improve Large Language Model Systems with User Logs
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.