EvoMaster: A Foundational Agent Framework for Building Evolving Autonomous Scientific Agents at Scale
Abstract
EvoMaster is a scalable, self-evolving agent framework designed for large-scale scientific discovery that enables iterative hypothesis refinement and knowledge accumulation across experimental cycles.
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.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery (2026)
- Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research (2026)
- AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse (2026)
- SkillNet: Create, Evaluate, and Connect AI Skills (2026)
- TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration (2026)
- Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence (2026)
- Embodied Science: Closing the Discovery Loop with Agentic Embodied AI (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2604.17406 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper