Saved in:
Bibliographic Details
Main Authors: Ma, Zerun, Wang, Guoqiang, Xie, Xinchen, Chen, Yicheng, Du, He, Li, Bowen, Sun, Yanan, Liu, Wenran, Chen, Kai, Li, Yining
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.14116
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915948277006336
author Ma, Zerun
Wang, Guoqiang
Xie, Xinchen
Chen, Yicheng
Du, He
Li, Bowen
Sun, Yanan
Liu, Wenran
Chen, Kai
Li, Yining
author_facet Ma, Zerun
Wang, Guoqiang
Xie, Xinchen
Chen, Yicheng
Du, He
Li, Bowen
Sun, Yanan
Liu, Wenran
Chen, Kai
Li, Yining
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14116
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration
Ma, Zerun
Wang, Guoqiang
Xie, Xinchen
Chen, Yicheng
Du, He
Li, Bowen
Sun, Yanan
Liu, Wenran
Chen, Kai
Li, Yining
Artificial Intelligence
Computation and Language
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.
title TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2604.14116