Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents

By Yashar Talebirad, Amirhossein Nadiri. arXiv.org, 2023

462 citations recorded by the source corpus.

In this paper, we present a novel framework for enhancing the capabilities of large language models (LLMs) by leveraging the power of multi-agent systems. Our framework introduces a collaborative environment where multiple intelligent agent components, each with distinctive attributes and roles, work together to handle complex tasks more efficiently and effectively. We demonstrate the practicality and versatility of our framework through case studies in artificial general intelligence (AGI), specifically focusing on the Auto-GPT and BabyAGI models. We also examine the"Gorilla"model, which integrates external APIs into the LLM. Our framework addresses limitations and challenges such as looping issues, security risks, scalability, system evaluation, and ethical considerations. By modeling various domains such as courtroom simulations and software development scenarios, we showcase the potential applications and benefits of our proposed multi-agent system. Our framework provides an avenue for advancing the capabilities and performance of LLMs through collaboration and knowledge exchange among intelligent agents.

View Paper: https://www.semanticscholar.org/paper/ead6121fbc787d508dc6a6d7106f72bf0d647d03

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Maosong Sun
2. Zhiyuan Liu
3. Weize Chen
4. Cheng Yang
5. Yusheng Su
6. Grégoire Mialon
7. Thomas Scialom
8. Sirui Hong

Citations in the corpus

• MetaGPT: Meta Programming for Multi-Agent Collaborative Framework (2023, background): “Multi-agent Collaboration Prior works have explored using multiple LLMs in a collaborative setting to solve complex tasks [32, 29].”
• Communicative Agents for Software Development (2023, background): “[36] introduce multiple agents with unique attributes and roles to handle complex tasks in a black box environment.”
• Why Do Multi-Agent LLM Systems Fail? (2025, unknown): “The prompts of MAS agents should provide clear description of instructions, and the role of each agent should be clearly specified (see G.2 as an example) (He et al., 2024a; Talebirad & Nadiri, 2023).”
• Multi-Agent Collaboration Mechanisms: A Survey of LLMs (2025, unknown): “In contrast, [120] proposes a generic framework for enhancing LLM capabilities via MASs, showing how tools like Auto-GPT align with their framework.”
• GAIA: a benchmark for General AI Assistants (2023, methodology): “…multiple agent LLMs to debate and together reach better conclusions to answer user queries (Li et al., 2023a; Hong et al., 2023; Chan et al., 2023; Talebirad and Nadiri, 2023); (iii) using single agent LLMs augmented with specific tools, such as Blender Bot 3 (Shuster et al., 2022), BOLAA (Liu et…”
• AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025, unknown): “Large Image Models (LIMs) such as CLIP [88] and BLIP-2 [89] extend the agent’s capabilities into the visual domain.”