AI RESEARCH
TRINITY: An Evolved LLM Coordinator
arXiv CS.LG
•
ArXi:2512.04695v3 Announce Type: replace Combining diverse foundation models is promising, but weight-merging is limited by mismatched architectures and closed APIs. Trinity addresses this with a lightweight coordinator that orchestrates collaboration among large language models (LLMs). The coordinator, comprising a compact language model (approximately $0.6$B parameters) and a lightweight head (approximately $10$K parameters), is optimized with an evolutionary strategy for efficient and adaptive delegation.