We hope to build an system that is lightweight, customizable, and that is caplable ofsocial-reasoning and expecting what the other agent should be doing through the lens of advesarial collaboration. We built a generalize agent model for every single agent in this environment and hopefully moving a step closer to level-one agent. Cover page image in courtesy of Sicun Gao from UCSD CSE.
Image in courtesy of Zhiting Hu from UCSD HDSI: Level-1 Agent Concept.
Check out our unpublished manuscript of RPLH: A Lightweight Agent-Based System For Multi-Collaboration Under Adversarial Settings.
System Documentation GitHub Repository