Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.05007 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910194599985152 |
|---|---|
| author | Cui, Zhiqing Xie, Haotong Yuan, Jiahao Yang, Cheng Wang, Hanqing Wu, Yuxin Wu, Yifan Zhong, Siru Yu, Tao Guo, Yifu Zhang, Siyu Yu, Xinlei Ren, Qibing Naseem, Usman |
| author_facet | Cui, Zhiqing Xie, Haotong Yuan, Jiahao Yang, Cheng Wang, Hanqing Wu, Yuxin Wu, Yifan Zhong, Siru Yu, Tao Guo, Yifu Zhang, Siyu Yu, Xinlei Ren, Qibing Naseem, Usman |
| contents | Large language model (LLM) multi-agent systems typically rely on rigid orchestration, committing either to flat per-query routing or to hand-engineered task decomposition, so decomposition depth, worker choice, and inference budget are not jointly optimized under one objective. We introduce Uno-Orchestra, a unified orchestration policy that selectively decomposes a task and dispatches each subtask to an admissible (model, primitive) pair, with both decisions learned together from curated RL trajectories grounded in real worker interactions. Against 22 baselines on a 13-benchmark suite spanning math, code, knowledge, long-context, and agentic tool-use, Uno-Orchestra reaches 77.0% macro pass@1, roughly 16% above the strongest workflow baseline, at roughly an order of magnitude lower per-query cost, advancing the accuracy-efficiency frontier of selective delegation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05007 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation Cui, Zhiqing Xie, Haotong Yuan, Jiahao Yang, Cheng Wang, Hanqing Wu, Yuxin Wu, Yifan Zhong, Siru Yu, Tao Guo, Yifu Zhang, Siyu Yu, Xinlei Ren, Qibing Naseem, Usman Artificial Intelligence Large language model (LLM) multi-agent systems typically rely on rigid orchestration, committing either to flat per-query routing or to hand-engineered task decomposition, so decomposition depth, worker choice, and inference budget are not jointly optimized under one objective. We introduce Uno-Orchestra, a unified orchestration policy that selectively decomposes a task and dispatches each subtask to an admissible (model, primitive) pair, with both decisions learned together from curated RL trajectories grounded in real worker interactions. Against 22 baselines on a 13-benchmark suite spanning math, code, knowledge, long-context, and agentic tool-use, Uno-Orchestra reaches 77.0% macro pass@1, roughly 16% above the strongest workflow baseline, at roughly an order of magnitude lower per-query cost, advancing the accuracy-efficiency frontier of selective delegation. |
| title | Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.05007 |