Xiao-Qing Zhang

This work presents ZGCM-1, a fully open 7B dense foundation model trained from scratch with extreme data, system, and algorithmic efficiency, and establishes an AI-native R&D workflow where agent swarms autonomously manage cluster operations, data curation, and rapid diagnostic evaluation.

HiGram cuts through irrelevant memory noise, boosting answer quality and efficiency in long-term reasoning tasks by leveraging a hierarchical structure and path-level localization.

OrchBench reveals that preserving task-critical information is more crucial than simply increasing agent numbers, challenging conventional wisdom in multi-agent system design.