Tag
A new AI research paper describes a tiny model that acts as a manager to route tasks to larger models, outperforming frontier models like ChatGPT, Gemini, and Claude on a hard coding benchmark by orchestrating a team of models instead of relying on a single one.
Sakana Fugu dynamically orchestrates a diverse pool of top models to tackle complex, multi-step tasks via a single API, leveraging their ICLR 2026 papers on learned orchestration to achieve frontier-level performance without single-vendor dependency.
Exa AILabs launches Exa Agent, a web research tool that orchestrates cost-effective models to perform tasks at less than half the cost of GPT-5.5 and Opus.
TRINITY is a lightweight 0.6B parameter coordinator that learns to orchestrate multiple LLMs by assigning them roles (Thinker, Worker, Verifier) using an evolutionary strategy. It outperforms individual models and existing coordination methods across coding, math, reasoning, and domain knowledge tasks.
Maestro is a reinforcement learning-driven framework that dynamically composes ensembles of frozen expert models and skills for multimodal tasks, achieving 70.1% average accuracy with a 4B orchestrator, surpassing GPT-5 and Gemini-2.5-Pro.
Rork introduces its AI Cloud service, enabling users to build AI applications using over 150 models including GPT and Kling without needing API keys.