Multi-agent LLM coordination in a Pokémon 2v2 environment
- Most multi-agent research is about workflows, where agents pass tasks down a pipeline (Hong et al., 2024; Qian et al., 2024).
- To test this, I built a multi-agent environment on Pokémon Showdown's 2v2 format to evaluate these abilities.
Unverified
- Most multi-agent research is about workflows, where agents pass tasks down a pipeline (Hong et al., 2024; Qian et al., 2024).
- To test this, I built a multi-agent environment on Pokémon Showdown's 2v2 format to evaluate these abilities.
Sources: Olivergrabner