EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale

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, biology, web research, and general science. Evaluations on ten benchmarks spanning scientific research/coding/experimentation, scientific reasoning and information search, and practical scientific problem solving compare EvoMaster against OpenHands, OpenClaw, and Codex. EvoMaster achieves the highest score on nine of the ten benchmarks and the strongest average score (58.0%) among the four agents, validating its efficacy and generality as the premier foundational framework for the next generation of autonomous scientific discovery.