Abstract
Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically assume configured organizations are followed faithfully, whereas reality differs. This behavioral gap, combined with differences in underlying system components, prevents clear attribution of observed gains. To this end, we introduce OpenCollab, a multi-agent coding framework that provides a unified infrastructure for programmable collaboration and controllable runtime. Specifically, OpenCollab unifies organization design, enforces experimental control on a shared runtime, and tracks execution through fine-grained event streams. On this basis, we define Adherence to quantify whether the declared organization is actually realized. Our experiments reveal that agents collaborate very differently across configurations: changing any single dimension shifts Adherence, from 47.2% to as high as 97.2%. Furthermore, extensive agentic coding benchmarks show that a two-coder workflow built on OpenCollab establishes new SOTA performance compared to the mainstream harnesses such as Mini-SWE-agent, Codex CLI, and Claude Code, showing that a well-designed organization can outperform strong existing harnesses, while OpenCollab's single-agent configuration uses the fewest tokens across all evaluated suites. OpenCollab establishes a unified multi-agent infrastructure for easy programmable collaboration and controlled causal evaluation.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Hsu, C. W., Gong, K., Wu, Y., Chen, X., Liu, M., Li, J., Li, H., Liu, Z., Tang, N., Chi, J., Fan, Z., He, X., Yang, X., Jiang, X., & Dong, Y. (2026). OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime. https://omanscience.com/en/articles/opencollab-a-multi-agent-coding-framework-with-programmable-collaboration-and-controllable-runtime
MLA 9
Hsu, Chun-Wah, et al. "OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime." https://omanscience.com/en/articles/opencollab-a-multi-agent-coding-framework-with-programmable-collaboration-and-controllable-runtime.
Chicago (author–date)
Hsu, Chun-Wah, Kai Gong, Yu Wu, Xianhe Chen, Mengyang Liu, Jie Li, Hanyu Li, Zhixuan Liu, Naisheng Tang, Jiaying Chi, Ziheng Fan, Xuning He, Xiaokang Yang, Xue Jiang, and Yihong Dong. 2026. "OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime." https://omanscience.com/en/articles/opencollab-a-multi-agent-coding-framework-with-programmable-collaboration-and-controllable-runtime.
Harvard
Hsu, C. W., Gong, K., Wu, Y., Chen, X., Liu, M., Li, J., Li, H., Liu, Z., Tang, N., Chi, J., Fan, Z., He, X., Yang, X., Jiang, X. and Dong, Y. (2026) 'OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime', Available at: https://omanscience.com/en/articles/opencollab-a-multi-agent-coding-framework-with-programmable-collaboration-and-controllable-runtime.
Vancouver
Hsu CW, Gong K, Wu Y, Chen X, Liu M, Li J, et al. OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime. https://omanscience.com/en/articles/opencollab-a-multi-agent-coding-framework-with-programmable-collaboration-and-controllable-runtime
IEEE
C. W. Hsu, K. Gong, Y. Wu, X. Chen, M. Liu, J. Li, H. Li, Z. Liu, N. Tang, J. Chi, Z. Fan, X. He, X. Yang, X. Jiang, and Y. Dong, "OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime," https://omanscience.com/en/articles/opencollab-a-multi-agent-coding-framework-with-programmable-collaboration-and-controllable-runtime.