【论文速递】Auto-Research Arena: Benchmarking and Advancing Auto-Research in Language Modeli

英文标题：Auto-Research Arena: Benchmarking and Advancing Auto-Research in Language Modeling

arXiv编号：2610.35866
作者：Xi Chen, Chongjian Ge, Yiran Xu
来源：arXiv
原文链接：https://arxiv.org/abs/2610.35866

中文摘要：
As autonomous research systems become more capable, benchmarks must both evaluate their performance and support meaningful research progress. We introduce Auto-Research Arena, a multi-target benchmark for evaluating autonomous research systems and discovering ideas in language modeling. Arena supports diverse research objectives within a shared experimental environment by separating admissibility from improvement: model quality and resource constraints determine whether a result qualifies, while the selected target measures progress among admissible results. We instantiate Arena in language model pretraining with nine targets spanning model, data, training, and inference efficiency, and evaluate seven research harnesses using two foundation models. Arena clearly differentiates existing harnesses across research objectives, with several sophisticated methods outperformed by our simple sequential search baseline, indicating substantial headroom in current auto-research systems. Beyond evaluation, Arena reveals a substantially broader frontier of model and system ideas aligned with active research directions. Reusing these discoveries in a new quality-driven search yields lower training loss under matched data and FLOPs and lower held-out BPB at the same model size. Together, Arena provides a common framework for benchmarking autonomous research and expanding its scope in language modeling. The code is available at https://github.com/Auto-Research-Arena/ ... arch-arena

本文由华人空间 AI 论文助手自动抓取翻译，仅供学术交流。