Paper page - EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

Source: https://huggingface.co/papers/2603.08127

Abstract

EvoScientist is an adaptive multi-agent framework that enhances scientific discovery by continuously learning from past interactions through persistent memory modules.

The increasing adoption ofLarge Language Models(LLMs) has enabled AI scientists to perform complex end-to-end scientific discovery tasks requiring coordination of specialized roles, including idea generation and experimental execution. However, most state-of-the-art AI scientist systems rely on static, hand-designed pipelines and fail to adapt based on accumulated interaction histories. As a result, these systems overlook promising research directions, repeat failed experiments, and pursue infeasible ideas. To address this, we introduce EvoScientist, an evolvingmulti-agent AI scientistframework that continuously improves research strategies throughpersistent memoryand self-evolution. EvoScientist comprises three specialized agents: aResearcher Agent(RA) forscientific idea generation, anEngineer Agent(EA) forexperiment implementationand execution, and anEvolution Manager Agent(EMA) that distills insights from prior interactions into reusable knowledge. EvoScientist contains twopersistent memorymodules: (i) anideation memory, which summarizes feasible research directions from top-ranked ideas while recording previously unsuccessful directions; and (ii) anexperimentation memory, which captures effective data processing and model training strategies derived from code search trajectories and best-performing implementations. These modules enable the RA and EA to retrieve relevant prior strategies, improving idea quality andcode execution success ratesover time. Experiments show that EvoScientist outperforms 7 open-source and commercial state-of-the-art systems inscientific idea generation, achieving higher novelty, feasibility, relevance, and clarity via automatic and human evaluation. EvoScientist also substantially improvescode execution success ratesthrough multi-agent evolution, demonstratingpersistent memory’s effectiveness for end-to-end scientific discovery.

View arXiv pageView PDFGitHub2.76kAdd to collection

Get this paper in your agent:

hf papers read 2603\.08127

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2603.08127 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2603.08127 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2603.08127 in a Space README.md to link it from this page.

Collections including this paper2