# TREX：基于智能体树状探索的 LLM 微调自动化系统

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-04-15 08:00
- AIHOT 链接：https://aihot.virxact.com/items/cmo0vpnos02w6sli2r5oa2hzp
- 原文链接：https://arxiv.org/abs/2604.14116

## AI 摘要

研究团队推出 TREX 多智能体系统，通过 Researcher 与 Executor 模块协同及树状搜索机制，实现大语言模型训练全生命周期自动化，覆盖需求分析、文献调研、策略制定到训练评估。系统支持实验路径智能规划、历史结果复用与迭代洞察提炼。同步发布包含 10 个真实场景任务的 FT-Bench 基准测试，验证显示 TREX 能持续优化目标任务的模型性能。

## 正文

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.