Paper Detail
Xinyu Zhu, Yuzhu Cai, Zexi Liu, Cheng Wang, Fengyang Li, Wenkai Jin, Wanxu Liu, Zehao Bing, Bingyang Zheng, Jingyi Chai, Shuo Tang, Rui Ye, Yuwen Du, Xianghe Pang, Yaxin Du, Tingjia Miao, Yuzhi Zhang, Ruoxue Liao, Zhaohan Ding, Linfeng Zhang, Yanfeng Wang, Weinan E, Siheng Chen
The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing agent frameworks are predominantly static, narrowly scoped, and lack the capacity to learn from trial and error. To bridge this gap, we present EvoMaster, a foundational evolving agent framework engineered specifically for Agentic Science at Scale. Driven by the core principle of continuous self-evolution, EvoMaster empowers agents to iteratively refine hypotheses, self-critique, and progressively accumulate knowledge across experimental cycles, faithfully mirroring human scientific inquiry. Crucially, as a domain-agnostic base harness, EvoMaster is exceptionally easy to scale up -- enabling developers to build and deploy highly capable, self-evolving scientific agents for arbitrary disciplines in approximately 100 lines of code. Built upon EvoMaster, we incubated the SciMaster ecosystem across domains such as machine learning, physics, and general science. Evaluations on four authoritative benchmarks (Humanity's Last Exam, MLE-Bench Lite, BrowseComp, and FrontierScience) demonstrate that EvoMaster achieves state-of-the-art scores of 41.1%, 75.8%, 73.3%, and 53.3%, respectively. It comprehensively outperforms the general-purpose baseline OpenClaw with relative improvements ranging from +159% to +316%, robustly validating its efficacy and generality as the premier foundational framework for the next generation of autonomous scientific discovery. EvoMaster is available at https://github.com/sjtu-sai-agents/EvoMaster.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{zhu2026evomaster,
title = {EvoMaster: A Foundational Agent Framework for Building Evolving Autonomous Scientific Agents at Scale},
author = {Xinyu Zhu and Yuzhu Cai and Zexi Liu and Cheng Wang and Fengyang Li and Wenkai Jin and Wanxu Liu and Zehao Bing and Bingyang Zheng and Jingyi Chai and Shuo Tang and Rui Ye and Yuwen Du and Xianghe Pang and Yaxin Du and Tingjia Miao and Yuzhi Zhang and Ruoxue Liao and Zhaohan Ding and Linfeng Zhang and Yanfeng Wang and Weinan E and Siheng Chen},
year = {2026},
abstract = {The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing agent frameworks are predominantly static, narrowly scoped, and lack the capacity to learn from trial and error. To bridge this gap, we present EvoMaster, a foundational evolving agent framework engineered specifically for Agentic Science at Scale. Driven by the core principle of continuous self-evolution, EvoMaster em},
url = {https://huggingface.co/papers/2604.17406},
keywords = {agentic science, evolving agent framework, self-evolution, hypothesis refinement, scientific inquiry, domain-agnostic base, autonomous scientific discovery, benchmark evaluation, state-of-the-art performance, code available, huggingface daily},
eprint = {2604.17406},
archiveprefix = {arXiv},
}
{}