titleApodex 1.1: Scaling Agentic Intelligence for Complex Work
authorsApodex Team, B. An, B. Li, B. Wang, B. Zhang, B. L. Wang, C. Feng, C. Wei, C. Xue, C. Zhang, D. Ng, D. Ye, E. Min, F. Chen, F. Liu, F. Yang, F. Ye, H. Xu, H. Yang, H. Ye, H. Zhang, H. Zhao, J. Li, J. Lin, J. Xia, K. Jin, K. Wang, K. Yang, L. Bing, L. Lei, L. Su, Le. Wang, Lu. Wang, N. Wang, Q. Ren, Q. Yang, R. Li, S. Bai, S. Du, S. Li, S. Lin, S. Nie, S. Wang, S. Zhang, S. Z. Wang, Ta. Q. Fang, Ti. Q. Fang, W. Fang, W. Li, W. Zhang, X. Chen, X. Li, X. Tang, X. Wang, X. Xu, X. Zhang, X. Q. Wang, X. Y. Wang, Y. Deng, Y. Gao, Y. Hu, Y. Li, Y. Sui, Y. Wang, Y. Xiao, Y. Zhang, Z. Chen, Z. Cheng, Z. Feng, Z. Liang, Z. Zhang
date2026-08-24
venuearXiv (preprint, not peer reviewed)
idarXiv:2608.23283
affiliationApodex
upvotes209 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
abstractGeneral-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information sources, and executable code, together with state maintenance, failure recovery, and verifiable delivery. We call this working capability: sustained, verifiable progress toward a real-world objective. Apodex 1.1 develops this capability along two complementary dimensions. Environment Scaling expands the diversity and verifiability of executable file, search, and code environments, while Agentic Coordination Scaling trains agents to decompose long-horizon tasks, delegate parallel work, integrate asynchronous results, and replan. A shared execution harness and AgentOS maintain task state and provenance across tools and agents, and training turns environment trajectories and coordination traces into reliable behavior. Across complex professional work, finance, scientific research, mathematics, coding, and search, Apodex 1.1 reaches the leading performance band despite using a substantially smaller model than many frontier systems. The 35B-parameter Apodex 1.1 Mini further retains strong working capability in a locally deployable form. These results ground agentic intelligence in useful, verifiable work completed over time and advance our goal of building a Heavy-Duty Solver for ambitious, long-running tasks.

cite

@misc{team2026apodex,
  title={Apodex 1.1: Scaling Agentic Intelligence for Complex Work},
  author={Apodex Team and B. An and B. Li and B. Wang and B. Zhang and B. L. Wang and C. Feng and C. Wei and C. Xue and C. Zhang and D. Ng and D. Ye and E. Min and F. Chen and F. Liu and F. Yang and F. Ye and H. Xu and H. Yang and H. Ye and H. Zhang and H. Zhao and J. Li and J. Lin and J. Xia and K. Jin and K. Wang and K. Yang and L. Bing and L. Lei and L. Su and Le. Wang and Lu. Wang and N. Wang and Q. Ren and Q. Yang and R. Li and S. Bai and S. Du and S. Li and S. Lin and S. Nie and S. Wang and S. Zhang and S. Z. Wang and Ta. Q. Fang and Ti. Q. Fang and W. Fang and W. Li and W. Zhang and X. Chen and X. Li and X. Tang and X. Wang and X. Xu and X. Zhang and X. Q. Wang and X. Y. Wang and Y. Deng and Y. Gao and Y. Hu and Y. Li and Y. Sui and Y. Wang and Y. Xiao and Y. Zhang and Z. Chen and Z. Cheng and Z. Feng and Z. Liang and Z. Zhang},
  year={2026},
  eprint={2608.23283},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2608.23283}
}