跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 18 天前AI 評分46

Micius-Flash:面向工程的輕量級智能體智能

Micius-Flash: Lightweight Agentic Intelligence for Engineering

AI 導讀

Micius-Flash 是一款面向工程的 27B 參數多模態推理模型,採用知識樹數據流程及多教師在線策略蒸餾訓練,支援 256K-token 上下文。在超過 20 個數據集、約 15K 筆記錄上,其硬件程式碼基準平均得分為 64.2%,較同規模基線高 15.0 個百分點;半導體智能體基準得分為 62.4%,高 17.2 個百分點。

正文

Published on Nov 4

·

Submitted by

Yu Lei

on Nov 11

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Micius-Flash is a 27B-parameter multimodal reasoning model trained with a knowledge-tree data pipeline and multi-teacher on-policy distillation, achieving strong hardware and semiconductor agent benchmark results and supporting tool-integrated engineering workflows.

We introduce Micius-Flash, a 27-billion-parameter model for engineering with native multimodal input, deep reasoning and a 256K-token context window. We design the Micius data pipeline as a knowledge-tree-driven data flywheel comprising three stages: knowledge tree construction and expansion, data synthesis, and quality validation with hard-example augmentation. From this data, we train expert models for semiconductor knowledge and reasoning, hardware coding, and semiconductor multimodal understanding, along with agentic experts. Subsequently, we employ Multi-Teacher On-Policy Distillation (MOPD) to supervise training on sequences generated by Micius itself, thereby integrating the capabilities of these expert models into a unified model. On more than 20 datasets with about 15K records, Micius-Flash averages 64.2% on hardware code benchmarks, 15.0 points above a same-size baseline. It scores 62.4% on a semiconductor-specific agent benchmark, exceeding the same-size baseline by 17.2 points. We further develop Micius Harness for industrial applications, connecting the model to specialized tools, including EDA tools and KiCad, as well as execution environments. Case studies in PCB design, chip design workflow automation, and software development demonstrate the model's ability to use tool execution feedback for multi-step planning, code debugging, and iterative verification. We release Micius as an open-source model to advance the development of agents for science and engineering.

View arXiv page View PDF Project page Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.10015 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.10015 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.10015 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co