[2512.04695] TRINITY: An Evolved LLM Coordinator

Computer Science > Machine Learning arXiv:2512.04695 (cs) [Submitted on 4 Dec 2025 (v1), last revised 2 Mar 2026 (this version, v2)] Title:TRINITY: An Evolved LLM Coordinator Authors:Jinglue Xu, Qi Sun, Peter Schwendeman, Stefan Nielsen, Edoardo Cetin, Yujin Tang View a PDF of the paper titled TRINITY: An Evolved LLM Coordinator, by Jinglue Xu and 5 other authors View PDF HTML (experimental) Abstract: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. Trinity processes queries over multiple turns, where at each turn the coordinator assigns one of three roles (Thinker, Worker, or Verifier) to a selected LLM, effectively offloading complex skill acquisition from the coordinator itself. Experiments show that Trinity consistently outperforms individual models and existing methods across coding, math, reasoning, and domain knowledge tasks, and generalizes robustly to out-of-distribution tasks. On standard benchmarks, Trinity achieves state-of-the-art results, including a score of 86.2% on LiveCodeBench. Theoretical and empirical analyses identify two main factors b...