Neural Orchestration for Multi-Agent Systems: A Deep Learning Framework for Optimal Agent Selection in Multi-Domain Task Environments
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911602198970368 |
|---|---|
| author | Agrawal, Kushagra Nargund, Nisharg |
| author_facet | Agrawal, Kushagra Nargund, Nisharg |
| contents | Multi-agent systems (MAS) are foundational in simulating complex real-world scenarios involving autonomous, interacting entities. However, traditional MAS architectures often suffer from rigid coordination mechanisms and difficulty adapting to dynamic tasks. We propose MetaOrch, a neural orchestration framework for optimal agent selection in multi-domain task environments. Our system implements a supervised learning approach that models task context, agent histories, and expected response quality to select the most appropriate agent for each task. A novel fuzzy evaluation module scores agent responses along completeness, relevance, and confidence dimensions, generating soft supervision labels for training the orchestrator. Unlike previous methods that hard-code agent-task mappings, MetaOrch dynamically predicts the most suitable agent while estimating selection confidence. Experiments in simulated environments with heterogeneous agents demonstrate that our approach achieves 86.3% selection accuracy, significantly outperforming baseline strategies including random selection and round-robin scheduling. The modular architecture emphasizes extensibility, allowing agents to be registered, updated, and queried independently. Results suggest that neural orchestration offers a powerful approach to enhancing the autonomy, interpretability, and adaptability of multi-agent systems across diverse task domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02861 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural Orchestration for Multi-Agent Systems: A Deep Learning Framework for Optimal Agent Selection in Multi-Domain Task Environments Agrawal, Kushagra Nargund, Nisharg Multiagent Systems Artificial Intelligence Neural and Evolutionary Computing Multi-agent systems (MAS) are foundational in simulating complex real-world scenarios involving autonomous, interacting entities. However, traditional MAS architectures often suffer from rigid coordination mechanisms and difficulty adapting to dynamic tasks. We propose MetaOrch, a neural orchestration framework for optimal agent selection in multi-domain task environments. Our system implements a supervised learning approach that models task context, agent histories, and expected response quality to select the most appropriate agent for each task. A novel fuzzy evaluation module scores agent responses along completeness, relevance, and confidence dimensions, generating soft supervision labels for training the orchestrator. Unlike previous methods that hard-code agent-task mappings, MetaOrch dynamically predicts the most suitable agent while estimating selection confidence. Experiments in simulated environments with heterogeneous agents demonstrate that our approach achieves 86.3% selection accuracy, significantly outperforming baseline strategies including random selection and round-robin scheduling. The modular architecture emphasizes extensibility, allowing agents to be registered, updated, and queried independently. Results suggest that neural orchestration offers a powerful approach to enhancing the autonomy, interpretability, and adaptability of multi-agent systems across diverse task domains. |
| title | Neural Orchestration for Multi-Agent Systems: A Deep Learning Framework for Optimal Agent Selection in Multi-Domain Task Environments |
| topic | Multiagent Systems Artificial Intelligence Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2505.02861 |