COOP2 Observable cooperation in LLM multi-agent systems
Code for connecting the cognitive activity of LLM agents to grounded environment actions and cooperative task progress.
I am constantly inspired by open-source projects and grateful for the openness behind them. Many of my projects began with ideas and tools shared by others. Hope something here can also help!
More is coming.
Code for connecting the cognitive activity of LLM agents to grounded environment actions and cooperative task progress.
DIG records emergent multi-agent execution as a time-evolving graph of agent activations and events. It is agnostic to the language model, environment, and number of agents.
Extends the Minecraft-inspired Crafter environment for studying multiple LLM agents that plan, remember, share resources, and work toward a collective objective.
Code for simulating heterogeneous human feedback and training HVAC controllers around collective comfort and energy use.