MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts

• URL: http://arxiv.org/abs/2608.09251v1
• Date: Mon, 10 Aug 2026 08:11:24 GMT
• Title: MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts
• Abstract summary: We introduce a Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts (MoRSE)<n>MoRSE distinguishes agents with (role, subtask)-conditional specialization at both the task structure and parameter levels.<n>To address the diverse role and subtask parameter adaptation demands, we propose a prototype-based semantic router for subtasks.
• Score: 23.501213747056624
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning [58.90602461025722]
  Multi-task instruct-tuning in large language models (LLMs) has been largely driven by multi-task instruct-tuning.<n>The training paradigm suffers from a key issue, named cross-task interference, due to conflicting gradients over shared parameters among different tasks.<n>We propose BADIT that decomposes LLM parameters into high-singular-value LoRA experts representing basic abilities.<n>We conduct extensive experiments on the SuperNI benchmark with 6 LLMs, and empirical results demonstrate that BADIT can outperform SOTA methods and mitigate the degree of cross-task interference.
  arXiv  Detail & Related papers  (2026-05-07T05:08:58Z)
• Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts [22.323342919724492]
  HERA is a hierarchical framework that jointly evolves multi-agent orchestration and role-specific agent prompts.<n> HERA achieves an average improvement of 38.69% over recent baselines.<n>Topological analyses reveal emergent self-organization, where sparse exploration yields compact, high-utility multi-agent networks.
  arXiv  Detail & Related papers  (2026-04-01T13:45:52Z)
• Designing Domain-Specific Agents via Hierarchical Task Abstraction Mechanism [61.01709143437043]
  We introduce a novel agent design framework centered on a Hierarchical Task Abstraction Mechanism (HTAM)<n>Specifically, HTAM moves beyond emulating social roles, instead structuring multi-agent systems into a logical hierarchy that mirrors the intrinsic task-dependency graph of a given domain.<n>We instantiate this framework as EarthAgent, a multi-agent system tailored for complex geospatial analysis.
  arXiv  Detail & Related papers  (2025-11-21T12:25:47Z)
• Separation and Collaboration: Two-Level Routing Grouped Mixture-of-Experts for Multi-Domain Continual Learning [7.361665112773847]
  We propose a Two-Level Grouped Mixture Routing-of-Experts (TRGE) method to mitigate catastrophic forgetting.<n> TRGE dynamically expands the pre-trained CLIP model, assigning specific expert group for each task.<n>We leverage Multimodal Large Language Models (MLLMs) which own powerful multimodal comprehension capabilities to generate task descriptions and recognize the correct task identifier.
  arXiv  Detail & Related papers  (2025-08-11T08:18:22Z)
• AgentOrchestra: Orchestrating Hierarchical Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocol [22.406849007798858]
  We propose the Tool-Environment-Agent Protocol to integrate environments, agents, and tools into an unified system.<n>We introduce AgentOrchestra, a hierarchical multi-agent framework with a central planning agent that decomposes complex objectives and coordinates specialized agents.
  arXiv  Detail & Related papers  (2025-06-14T13:45:37Z)
• Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration [63.90193684394165]
  We introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation.<n>During the experiential learning phase, we quantify the quality for each step in the task-solving workflow and store the resulting rewards.<n>During inference, agents retrieve high-reward, task-relevant experiences as few-shot examples to enhance the effectiveness of each reasoning step.
  arXiv  Detail & Related papers  (2025-05-29T07:24:37Z)
• ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation [96.86211867758652]
  Low-Rank Adaptation (LoRA) is widely adopted for downstream fine-tuning of foundation models.<n>We propose ThanoRA, a Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation framework.
  arXiv  Detail & Related papers  (2025-05-24T11:01:45Z)
• HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems [1.1930434318557155]
  We introduce HALO, a multi-agent collaboration framework based on a hierarchical reasoning architecture.<n>Specifically, we incorporate a high-level planning agent for task decomposition, mid-level role-design agents for subtask-specific agent instantiation, and low-level inference agents for subtask execution.<n>As the majority of users lack expertise in prompt engineering, we leverage an Adaptive Prompt Refinement module to transform raw queries into task-specific prompts.
  arXiv  Detail & Related papers  (2025-05-17T04:14:03Z)
• Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning [70.96345405979179]
  The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. variations in task content and complexity pose significant challenges in policy formulation. We introduce the Harmony Multi-Task Decision Transformer (HarmoDT), a novel solution designed to identify an optimal harmony subspace of parameters for each task.
  arXiv  Detail & Related papers  (2024-11-02T05:49:14Z)
• Agents meet OKR: An Object and Key Results Driven Agent System with Hierarchical Self-Collaboration and Self-Evaluation [25.308341461293857]
  OKR-Agent is designed to enhance the capabilities of Large Language Models (LLMs) in task-solving. Our framework includes two novel modules: hierarchical Objects and Key Results generation and multi-level evaluation.
  arXiv  Detail & Related papers  (2023-11-28T06:16:30Z)
• LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent Reinforcement Learning [122.47938710284784]
  We propose a novel framework for learning dynamic subtask assignment (LDSA) in cooperative MARL. To reasonably assign agents to different subtasks, we propose an ability-based subtask selection strategy. We show that LDSA learns reasonable and effective subtask assignment for better collaboration.
  arXiv  Detail & Related papers  (2022-05-05T10:46:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.