cs.LGNov 16, 2026

TrainExplorer: Autonomous LLM Post-Training via Plan-and-Decouple Exploration

Authors: Xuannan Liu, Tian Lan, Zekun Li, Xing Cui, Zhengfeng Yu, Feihu Jiang, Qianghuai Jia, Longyue Wang, 

Organizations: Beijing University of Posts and Telecommunications · Alibaba Group · Minzu University of China · Beijing Institute of Technology · 

Abstract

LLM-based agents can automate model post-training, accelerating progress toward recursive self-improvement. Despite their promise, existing approaches remain under-explored and face two main challenges: (1) strategy lock-in that limits exploration beyond the initial strategy; and (2) coupled execution that obscures the effects of individual modifications. To address these challanges, we propose TrainExplorer, a multi-agent framework for autonomous post-training, that incorporates strategy planning and execution decoupling, to achieve broaden strategy exploration. First, strategy planning draws on scientific literature to construct a candidate search space of training strategies. Then, decoupled execution enables single-component interventions and attribution to guide strategy exploration. Extensive experiments on PostTrainBench demonstrate that TrainExplorer achieves a weighted aggregate score of 39.02, outperforming Claude Code using the same LLM by 7.32 and surpassing GPT-5.6 Sol-powered Codex, which scores 36.23. Code will be available.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. PostTrainBench: Can LLM Agents Automate LLM Post-Training?

    Mar 9, 2026Ben Rank, Hardik Bhatnagar, Ameya Prabhu +4LLM Post-TrainingAutonomous Research Agents

  2. AutoTrainess: Teaching Language Models to Improve Language Models Autonomously

    Jun 30, 2026Zhaojian Yu, Penghao Yin, Shuzheng Gao +3Tool-Augmented Language Model AgentsLLM Tool Use

  3. What is Missing from AI Post-Training AI: An Empirical Analysis

    Aug 19, 2026Joy Jia Yin Lim, Xin Huang, Hao Peng +5AI Agent EvaluationLLM Agent Self-Improvement