Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling 事件

Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling arXiv:2605.26969v1 Announce Type: new Abstract: User modeling aims to use language models (LMs) to mimic an individual's behavior from a corpus of past context-action pairs (e.g., conversation turns), enabling the simulation of users in settings like behavioral science, human-AI collaboration, and market research. Recent approaches augment these corpora with synthesized reasoning traces, typically generated by conditioning on bo