TL;DR
TRINITY introduces a lightweight, evolved coordinator that orchestrates multiple LLMs through role assignment, significantly improving performance across various tasks without weight-merging limitations.
Contribution
The paper presents a novel evolutionary strategy-optimized coordinator model that effectively manages diverse LLMs, enabling superior task performance and robustness.
Findings
Outperforms individual models and existing methods on coding, math, reasoning, and domain tasks.
Achieves state-of-the-art 86.2% on LiveCodeBench.
Coordinator's hidden states and high-dimensional optimization are key to performance.
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 B parameters) and a lightweight head (approximately 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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
