arXiv：cs.CL· Chun-Wah Hsu, 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, Yihong Dong·· 13 小时前
OpenCollab：可编程协作与可控运行时的多智能体编程框架
OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
AI 导读
OpenCollab 是一个支持可编程协作与可控运行时的多智能体编程框架，并提出 Adherence 指标量化声明组织是否被真实执行，实验中该指标随配置变化从 47.2% 到 97.2%。
正文
Authors:Chun-Wah Hsu, 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, Yihong Dong
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 OpenCollab (Duo) establishes new SOTA performance compared to the mainstream harnesses such as Mini-SWE-agent, OpenHands, 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.
| Comments: | work on process |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2609.38345 [cs.SE] |
| (or arXiv:2609.38345v2 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2609.38345 arXiv-issued DOI via DataCite |
Submission history
From: Yu Wu [view email]
[v1]
Tue, 29 Sep 2026 18:08:54 UTC (3,273 KB)
[v2]
Fri, 9 Oct 2026 08:37:59 UTC (3,294 KB)
来源：arXiv：cs.CL · arxiv.org