‹ back to 2026-08-25

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

arXiv cs.AI LLM Agents Apodex 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 2026-08-24

TL;DR - Apodex 1.1 targets sustained, verifiable completion of complex work by scaling both executable environments and coordination among agents. It reports leading-band performance across several professional and technical domains despite using a smaller model than many frontier systems.

Environment Scaling broadens executable file, search, and coding environments while emphasizing outcome verification.
Agentic Coordination Scaling trains long-horizon decomposition, parallel delegation, asynchronous result integration, and replanning.
A shared execution harness and AgentOS preserve task state and provenance across tools and agents.
The locally deployable 35B-parameter Apodex 1.1 Mini retains strong working capability.

view merged work →