Intel / article

Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

Source: arxiv.org
Author: Wenhui Chen, Shiwen Cheng, Hao Dong, Chenda Duan, Ruixiang Feng, Zhong Guan, Boqiang Guo, Xueyuan Han, Haojie Hao, Liangmeng Huang, Zhelong Huang, Xinke Kong, Hongyu Li, Jiazheng Li, Junbo Li, Qingchuan Li, Yukun Lian, Chang Liu, Tianyu Liu, Zicheng Liu, Shuyi Ouyang, Yijun Pan, Kunyu Shi, Xiaojun Tang, Bingquan Wang, Kesu Wang, Yuchen Wang, Sibo Wei, Sicong Xie, Xiaoying Xing, Yi Xu, Zhijun Xu, Hongwei Xue, Qingcheng Zeng, Di Zhang, Guannan Zhang, Haochen Zhang, Tianlong Zhang, Tianyu Zhao, Tianyu Zhao, Yanjun Zheng, Jialong Zhu, Zijian Zou
Date: Published Sep 14, 2026

Context

Occamy-1.0 targets the repeated execution work behind an assistant that searches, edits files and uses software tools. Its developers further trained Qwen3.6-35B-A3B to follow tool requirements, track changing task state and recover from failures. They trained separate versions for extended workflows and shorter tasks, merged them, then continued training on complete workflows. The paper describes specialization aimed at carrying work through to completion.

The authors report stronger results than the starting model on several of their benchmarks, with only a modest change in estimated per-task cost. Their comparison prices measured text usage under a common pricing protocol. It supports a claim about execution efficiency; it does not measure the full expense of deploying and operating the model.

Terms in this piece · Glossary

inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.

Read the source arxiv.org