Abstract
The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. We explore the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents, and provides insight into their “cognitive” processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of a society of agents, providing a valuable resource for investigating conversational language models. In particular, we conduct comprehensive studies on instruction-following cooperation in multi-agent settings. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems.
Speaker
Guohao Li is a founder and CEO of Eigent.AI. He is an artificial intelligence researcher and an open-source contributor working on building intelligent agents that can perceive, learn, communicate, reason, and act. He is the core lead of the open source projects CAMEL-AI.org and DeepGCNs.org. Guohao Li was a postdoctoral researcher at University of Oxford with Prof. Philip Torr. He obtained his PhD degree in Computer Science at King Abdullah University of Science and Technology (KAUST) advised by Prof. Bernard Ghanem. During his Ph.D. studies, he was fortunate to work at Intel ISL with Dr. Vladlen Koltun and Dr. Matthias Müller as a research intern. He visited ETHz CVL as a visiting researcher. He also worked at Kumo AI and PyG.org with Prof. Jure Leskovec and Dr. Matthias Fey as a PhD intern. His primary research interests include Autonomous Agents, Graph Machine Learning, Computer Vision, and Embodied AI. He has published related papers in top-tier conferences and journals such as ICCV, CVPR, ICML, NeurIPS, RSS, 3DV, and TPAMI.
Video
Extra Details
Speaker Website / Paper Link / Paper Code/ Paper Project Page