While Large Language Models (LLMs) have empowered AI research agents to perform isolated scientific tasks, automating complex, real-world workflows, such as LLM training, remains a significant challenge. In this paper, we introduce TREX, a multi-agent system that automates the entire LLM training life-cycle. By orchestrating collaboration between two core modules-the Researcher and the Executor-the system seamlessly performs requirement analysis, open-domain literature and data research, formulation of training strategies, preparation of data recipes, and model training and evaluation. The multi-round experimental process is modeled as a search tree, enabling the system to efficiently plan exploration paths, reuse historical results, and distill high-level insights from iterative trials. To evaluate the capability of automated LLM training, we construct FT-Bench, a benchmark comprising 10 tasks derived from real-world scenarios, ranging from optimizing fundamental model capabilities to enhancing performance on domain-specific tasks. Experimental results demonstrate that the TREX agent consistently optimizes model performance on target tasks.
@article{arxiv.2604.14116,
title = {TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration},
author = {Zerun Ma and Guoqiang Wang and Xinchen Xie and Yicheng Chen and He Du and Bowen Li and Yanan Sun and Wenran Liu and Kai Chen and Yining Li},
journal= {arXiv preprint arXiv:2604.14116},
year = {2026}
}