Saved in:
Bibliographic Details
Main Authors: Wu, Xiao, Huang, Ting-Zhu, Deng, Liang-Jian, Yu, Xiaobing, Zhong, Yu, Deng, Shangqi, Khan, Ufaq, Wu, Jianghao, Liu, Xiaofeng, Razzak, Imran, Chang, Xiaojun, Xie, Yutong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.00403
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908848193798144
author Wu, Xiao
Huang, Ting-Zhu
Deng, Liang-Jian
Yu, Xiaobing
Zhong, Yu
Deng, Shangqi
Khan, Ufaq
Wu, Jianghao
Liu, Xiaofeng
Razzak, Imran
Chang, Xiaojun
Xie, Yutong
author_facet Wu, Xiao
Huang, Ting-Zhu
Deng, Liang-Jian
Yu, Xiaobing
Zhong, Yu
Deng, Shangqi
Khan, Ufaq
Wu, Jianghao
Liu, Xiaofeng
Razzak, Imran
Chang, Xiaojun
Xie, Yutong
contents Scientific discovery increasingly entails long-horizon exploration of complex hypothesis spaces, yet most existing approaches emphasize final performance while offering limited insight into how scientific exploration unfolds over time, particularly balancing efficiency-diversity trade-offs and supporting reproducible, human-in-the-loop discovery workflows. We introduce SelfAI, a self-directed, multi-agent-enabled discovery system that automates scientific exploration as a strategic, trajectory-driven decision-making process. SelfAI translates high-level research intent into executable experiments, reasons over accumulated experimental trajectories to guide subsequent exploration, and applies adaptive stopping decisions to terminate unproductive search paths within a closed-loop workflow governed by explicit efficiency-diversity trade-offs. Evaluated using real-world experiments spanning domains from machine learning to drug discovery, SelfAI consistently discovers high-quality solutions with substantially fewer redundant trials than classical optimization and recent LLM-based baselines. The proposed methods establish a general framework for organizing long-horizon scientific discovery and adaptive decision-making in complex scientific and engineering systems.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00403
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SelfAI: A self-directed framework for long-horizon scientific discovery
Wu, Xiao
Huang, Ting-Zhu
Deng, Liang-Jian
Yu, Xiaobing
Zhong, Yu
Deng, Shangqi
Khan, Ufaq
Wu, Jianghao
Liu, Xiaofeng
Razzak, Imran
Chang, Xiaojun
Xie, Yutong
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Scientific discovery increasingly entails long-horizon exploration of complex hypothesis spaces, yet most existing approaches emphasize final performance while offering limited insight into how scientific exploration unfolds over time, particularly balancing efficiency-diversity trade-offs and supporting reproducible, human-in-the-loop discovery workflows. We introduce SelfAI, a self-directed, multi-agent-enabled discovery system that automates scientific exploration as a strategic, trajectory-driven decision-making process. SelfAI translates high-level research intent into executable experiments, reasons over accumulated experimental trajectories to guide subsequent exploration, and applies adaptive stopping decisions to terminate unproductive search paths within a closed-loop workflow governed by explicit efficiency-diversity trade-offs. Evaluated using real-world experiments spanning domains from machine learning to drug discovery, SelfAI consistently discovers high-quality solutions with substantially fewer redundant trials than classical optimization and recent LLM-based baselines. The proposed methods establish a general framework for organizing long-horizon scientific discovery and adaptive decision-making in complex scientific and engineering systems.
title SelfAI: A self-directed framework for long-horizon scientific discovery
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.00403