{"ID":2835151,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00403","arxiv_id":"2512.00403","title":"SelfAI: A self-directed framework for long-horizon scientific discovery","abstract":"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.","short_abstract":"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,...","url_abs":"https://arxiv.org/abs/2512.00403","url_pdf":"https://arxiv.org/pdf/2512.00403v2","authors":"[\"Xiao Wu\",\"Ting-Zhu Huang\",\"Liang-Jian Deng\",\"Xiaobing Yu\",\"Yu Zhong\",\"Shangqi Deng\",\"Ufaq Khan\",\"Jianghao Wu\",\"Xiaofeng Liu\",\"Imran Razzak\",\"Xiaojun Chang\",\"Yutong Xie\"]","published":"2025-11-29T09:18:39Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Large Language Model\",\"LoRA\",\"Generative Adversarial Network\"]","has_code":false}