大型语言模型（LLMs）正从协助科学研究与工程开发拓展至自主开发和改进AI系统，推动AI for AI（AI4AI）成为递归自我改进（RSI）的实现路径。工作流驱动的机器学习工程（MLE）系统通过管理长周期实验的复杂编排，为该目标提供了可行路径；近期MLE系统采用模型导向交互，允许模型自主组织实验并基于执行反馈调整优化策略。然而，每项实验的反馈反映了多个前置决策，且一次长周期MLE运行包含大量此类高成本实验，因此训练需从长交互轨迹中筛选有用监督信号并从中间结果学习。我们提出一种用于自主长周期MLE优化的后训练方法，并将其应用于训练350亿参数的混合专家智能体模型MLExpert。我们设计Kaggle-MLE Factory以构建可执行任务和模型导向实验的交互框架；分层智能体监督微调（SFT）通过结果导向监督将通用工具使用与编码能力迁移至MLE；窗口交互强化学习（WIRL）将连续实验结果间的多轮决策视为一个执行窗口，并为其分配基于结果的共享奖励；异步收集与策略修正支持在轨迹结束前完成策略更新。在MLE-Bench Lite上，MLExpert将基础模型的平均奖牌率从37.9%提升至72.7%，达到与Kimi-K3、GLM-5.3等更大前沿模型相当的性能；进一步实验表明，MLExpert在NatureBench Lite、智能体支架优化及算法优化任务上均提升了性能，表明所学优化能力可泛化至其他任务。
英文摘要：
Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advancing AI for AI (AI4AI) as a pathway toward recursive self-improvement (RSI). Workflow-driven machine learning engineering (MLE) systems provide a practical path toward this pursuit through complex orchestration that manages long-horizon experimentation, while recent MLE systems adopt model-directed interaction, allowing models to autonomously organize experiments and adapt optimization strategies based on execution feedback. However, feedback from each experiment reflects several preceding decisions, and a long MLE run contains many such costly experiments. Training must therefore select useful supervision from long interaction trajectories and learn from intermediate outcomes. We propose a post-training method for autonomous long-horizon MLE optimization and apply it to train MLExpert, a 35B Mixture-of-Experts agentic model. We design the Kaggle-MLE Factory to construct executable tasks and an interaction harness for model-directed experimentation. Hierarchical agentic SFT transfers general tool-use and coding capabilities to MLE through outcome-guided supervision. Windowed Interaction RL (WIRL) treats the multi-turn decisions between successive experiment results as an execution window and assigns it a shared outcome-based reward. Asynchronous collection and policy correction support policy updates before the trajectory ends. On MLE-Bench Lite, MLExpert improves the average medal rate of the base model from 37.9% to 72.7%, achieving performance comparable to larger frontier models such as Kimi-K3 and GLM-5.3. Further experiments show that MLExpert improves performance on NatureBench Lite, agent scaffold optimization, and algorithm optimization, suggesting that the learned optimization capability generalizes to other tasks.
Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
Princeton University（普林斯顿大学）；Tsinghua University（清华大学）；Shanghai Jiao Tong University（上海交通大学）；University of Michigan（密歇根大学）；Tianqiao and Chrissy Chen Institute（天桥和克里斯·陈研究所）；The Chinese University of Hong Kong（香港中文大学）
Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning
Generative AI Lab, College of Computing and Data Science, Nanyang Technological University（生成式人工智能实验室，南洋理工大学计算与数据科学学院）；Tongyi Lab, Alibaba Group（阿里集团通义实验室）
Agentic AI with Orchestrator-Agent Trust: A Modular Visual Classification Framework with Trust-Aware Orchestration and RAG-Based Reasoning
University of the Peloponnese, Department of Informatics and Telecommunications（希腊皮埃蒙特大学信息与电信系）；Cornell University, Department of Biological and Environmental Engineering（康奈尔大学生物与环境工程系）
CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
Microsoft Research Asia（微软亚洲研究院）；Department of Biomedical Engineering, Yale University（耶鲁大学生物医学工程系）；Department of Radiology & Biomedical Imaging, Yale University（耶鲁大学放射学与生物医学成像系）
Towards Embodied Agentic AI: Review and Classification of LLM- and VLM-Driven Robot Autonomy and Interaction
Department of Computing, University of Turku（图尔库大学计算机系）；Institute of Computer Science, Zurich University of Applied Sciences（应用科学大学计算机科学研究所）；Centre for Artificial Ingelligence, Zurich University of Applied Sciences（应用科学大学人工智能中心）；Agentic Systems Lab, Department of Management, Technology and Economics, ETH Zürich（苏黎世联邦理工学院管理、科技与经济系代理系统实验室）；Faculty of Mathematics and Information Science, Warsaw University of Technology（华沙技术大学数学与信息科学学院）
From Segments to Scenes: Temporal Understanding for Agentic Autonomous Driving via Vision-Language Models
University of California, Berkeley（加州大学伯克利分校）；University of Cambridge（剑桥大学）；University of Toronto（多伦多大学）；ETH Zurich（苏黎世联邦理工学院）；University of Washington（华盛顿大学）；University of Southern California（南加州大学）
