Nexus: A Lightweight and Scalable Multi-Agent Framework for Complex Tasks Automation
Humza Sami, Mubashir ul Islam, Samy Charas, Asav Gandhi,, Pierre-Emmanuel Gaillardon, Valerio Tenace

TL;DR
Nexus is a lightweight, open-source Python framework that enables scalable, multi-agent systems leveraging large language models, demonstrating state-of-the-art performance in coding, reasoning, and optimization tasks.
Contribution
The paper introduces Nexus, a novel flexible multi-agent framework that enhances scalability and domain adaptability for LLM-based systems with innovative architecture and workflow design.
Findings
Achieves 99% pass rate on HumanEval coding tasks
Attains 100% accuracy on VerilogEval-Human
Provides 30% power savings in optimization tasks
Abstract
Recent advancements in Large Language Models (LLMs) have substantially evolved Multi-Agent Systems (MASs) capabilities, enabling systems that not only automate tasks but also leverage near-human reasoning capabilities. To achieve this, LLM-based MASs need to be built around two critical principles: (i) a robust architecture that fully exploits LLM potential for specific tasks -- or related task sets -- and () an effective methodology for equipping LLMs with the necessary capabilities to perform tasks and manage information efficiently. It goes without saying that a priori architectural designs can limit the scalability and domain adaptability of a given MAS. To address these challenges, in this paper we introduce Nexus: a lightweight Python framework designed to easily build and manage LLM-based MASs. Nexus introduces the following innovations: (i) a flexible multi-supervisor…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Multimodal Machine Learning Applications · Natural Language Processing Techniques
MethodsMixing Adam and SGD
