Metraipolis › archive › dc_7cd455a5613a
MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts — arXiv:2608.09251
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09251
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:49:23.863Z
- SHA-256 of the archived text
b170ec4a4598cfa624eac5f6367a86a550da5b6f74993e30415f5f27b9b4d110- Stable URL of this page
https://metraipolis.com/documento/dc_7cd455a5613a
How to cite
MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts — arXiv:2608.09251 — arXiv (en), https://arxiv.org/abs/2608.09251 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cd455a5613a (Metraipolis archive dc_7cd455a5613a, sha256 b170ec4a4598cfa624eac5f6367a86a550da5b6f74993e30415f5f27b9b4d110)
BibTeX
@misc{dc7cd455a5613a,
title = {MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts — arXiv:2608.09251},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09251},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cd455a5613a; sha256 b170ec4a4598cfa624eac5f6367a86a550da5b6f74993e30415f5f27b9b4d110},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09251. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model-based multi-agent systems have recently shown strong potential for complex, long-horizon tasks. However, existing methods mainly rely on coarse prompt-level differentiation without parameter adaptation for diverse subtasks, resulting in insufficient inter-agent heterogeneity and limited specialized capability that bottleneck performance on tasks with complex requirements. To address this, we introduce a Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts (MoRSE) that distinguishes agents with (role, subtask)-conditional specialization at both the task structure and parameter levels. To make agents' responsibility explicit at the task structure level, we formulate a task-oriented multi-agent system that decomposes each task into a dependency-aware Directed Acyclic Graph of subtasks and assigns each agent a specific (role, subtask), introducing task-level specialization across collaborating agents. Additionally, to address the diverse role and subtask parameter adaptation demands, we propose a dynamic Mixture of (role, subtask) LoRA Experts module with a prototype-based semantic router for subtasks, augmenting agents with parameter-level specialization on a shared LLM substrate cost-effectively. Then, to co-optimize experts and router stably under sparse task rewards, we further propose a hierarchical group-relative policy optimization with two-layer credit assignment that isolates expert updates from the cross-route variance introduced by routing decisions, disentangling expert quality from routing quality. Experiments on code-generation benchmarks across three backbones demonstrate the effectiveness of our approach, with improvements in both whole-task and step-wise performance, and the gains from trained specialization generalize across held-out task categories and domains. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.09251 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T06:45:31.686Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).