Micius-Flash, a 27-billion-parameter model for engineering with native multimodal input, deep reasoning and a 256K-token context window, is introduced and released as an open-source model to advance the development of agents for science and engineering.
Hong-Cheng Gao, Wei-Heng Li, Yi-Peng Wei et al.· 0 citations
Embodied agents are expected to accomplish real-world goals by deciding for themselves how and when to interact with their surroundings. For many such goals, changing the physical state of the world is the means rather than the end: the agent changes the state of a system through interaction, observes the feedback, and...
Hong-Cheng Gao, Ze Zheng, Alex Zhou et al.· 1 citation
Vision-language-action (VLA) and world-action (WAM) models map observations and instructions directly to robot actions. This directness ties a policy to training: minor layout or viewpoint changes cause failure, and instructions generalize poorly. The root cause lies in representation: task requirements, conditions, pr...
Hong-Cheng Gao, Jing-Jing Zhou, Ze Zheng et al.· arXiv.org· 7 citations
Frontier models can control robots, but reasoning through every reach, grasp, and retreat makes manipulation slow and token-intensive. We revisit code as policy with a different division of labor: models build executable tools, code handles multi-phase motions, and models decide what to do next. We introduce URAI (Univ...
S. Ge, Alex Zhou, Jian-Shu Zeng et al.· arXiv.org· 8 citations
EngiWorld provides the first rigorous foundation for measuring progress toward agents that operate professional engineering software end to end, and introduces an artifact-centric evaluation methodology built on a unified domain-verifier suite.
Hong-Cheng Gao, Hai-Long Qu, Yu-Ang Lei et al.· 0 citations
A one-round study provides initial evidence for PRD-guided self-evolution, motivating validation at larger scales and in industrial settings, and presents AgentOmnia, a framework coordinating task-space definition, data synthesis, post-training, evaluation, and improvement across To-Consumer (ToC), To-Business (ToB), a...
OmniaBench provides a broad and diagnostic benchmark for characterizing the capability boundaries of general agents across diverse scenarios with explicit state spaces, and introduces a ten-dimensional capability taxonomy and eight compositional atomic difficulty factors to support fine-grained evaluation and analysis.