Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMs
This work addresses the challenge of improving coordination and communication in multi-agent systems for researchers and practitioners in AI, but it appears incremental as it builds on existing LLM and multi-agent decision-making methods.
The authors tackled the problem of enhancing multi-agent decision-making by integrating large language models (LLMs) with multi-agent algorithms, proposing a systematic framework for multi-agentic LLMs that includes prompt engineering, memory architectures, multi-modal processing, and fine-tuning, and evaluated it through ablation studies on game settings with social dilemmas and game-theoretic aspects.
Language is a ubiquitous tool that is foundational to reasoning and collaboration, ranging from everyday interactions to sophisticated problem-solving tasks. The establishment of a common language can serve as a powerful asset in ensuring clear communication and understanding amongst agents, facilitating desired coordination and strategies. In this work, we extend the capabilities of large language models (LLMs) by integrating them with advancements in multi-agent decision-making algorithms. We propose a systematic framework for the design of multi-agentic large language models (LLMs), focusing on key integration practices. These include advanced prompt engineering techniques, the development of effective memory architectures, multi-modal information processing, and alignment strategies through fine-tuning algorithms. We evaluate these design choices through extensive ablation studies on classic game settings with significant underlying social dilemmas and game-theoretic considerations.