Deep research agents are increasingly deployed to retrieve precise information from large corpora, yet multi-hop, long-horizon tasks remain challenging. Synthetic data generation has emerged as a scalable solution, with existing pipelines typically expanding seed tasks to increase their apparent depth and breadth. However, this expansion does not reliably translate into necessary reasoning: newly introduced evidence may be only weakly coupled to the answer, creating a mismatch between intended and empirical difficulty. To address this problem, we introduce GRADS, a graph-guided agentic data synthesis framework with explicit difficulty control. GRADS runs a closed loop of seed selection, evidence expansion, question--answer construction, and verification while maintaining a graph of the evidence and inference dependencies required to derive each answer. At each step, it conditions generation on a relevant subgraph, preserving indispensable inference without accumulating irrelevant context. Experiments across security, software-engineering, and scientific-document domains show that GRADS consistently generates verified tasks with empirically separated difficulty distributions, as measured by independent solvers. Moreover, under matched training budgets, post-training on this data delivers consistent gains at every level: SFT raises the solution-termination rate to over 95% while cutting tool calls and turns by up to 75%, RL trims tool use by up to a further 19.5%, and on our held-out, domain-specific benchmarks, the resulting 4B model matches Sonnet~4 on software engineering and surpasses it on the scientific and security domains.
Gradient Coupling: The Hidden Barrier to Generalization in Agentic Reinforcement Learning
Taobao & Tmall Group of Alibaba(阿里巴巴淘宝与天猫集团);Beijing Institute of Technology(北京理工大学);Beijing Key Laboratory of Research on Large Models and Intelligent Governance(北京大型模型与智能治理重点实验室);Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE(下一代智能搜索与推荐工程技术研究中心)
A Practical Guide for Designing, Developing, and Deploying Production-Grade Agentic AI Workflows
Old Dominion University(旧 Dominion 大学);Florida International University(佛罗里达国际大学);Nanyang Technological University(南洋理工大学);University of Colombo(科伦坡大学)
Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems
School of Computing and Information Systems, Singapore Management University(新加坡管理学院);School of Computing(计算学院);Research and Development, Mastercard(Mastercard研发)
LumiVideo: An Intelligent Agentic System for Video Color Grading
Northwestern University(西北大学);Northeastern University(东北大学);South China University of Technology(华南理工大学);Hong Kong Baptist University(香港浸会大学);Beijing Normal - Hong Kong Baptist University(北京师范大学-香港浸会大学)
RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
Pennsylvania State University(宾夕法尼亚州立大学);City University of New York(纽约市立大学);New York University(纽约大学);Amirkabir University of Technology(阿米尔卡比尔理工大学);Autodesk(欧特克公司);Carnegie Mellon University(卡内基梅隆大学)
CG-HAF: An Interpretable Global-Local Lesion-Burden Fusion Framework for Ordinal Acne Severity Grading in Agentic Skincare Support
International Islamic University Chittagong (IIUC)(吉大港国际伊斯兰大学);Rajshahi University of Engineering and Technology (RUET)(拉杰沙希工程技术大学);King Saud University(沙特国王大学);Charles Sturt University(查尔斯特大学);The University of Queensland(昆士兰大学)
V-Math: An Agentic Approach to the Vietnamese National High School Graduation Mathematics Exams
CIRTech Institute, HUTECH University, Ho Chi Minh City, Viet Nam(CIRTech研究院,HUTECH大学,胡志明市,越南);Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Vietnam(信息科技学院,HUTECH大学,胡志明市,越南);Nguyen Thai Hoc High School, Gia Lai Province, Vietnam(Nguyen Thai Hoc高中,嘉莱省,越南);Office of Scientific Research, Technology Management and International Cooperation, Tien Giang University, Vietnam(科研办公室,技术管理与国际合作办公室,Tien Giang大学,越南)
本文提出自主智能体框架 V-Math,集成问题生成、求解解释与个性化导师三个 AI 智能体,支持越南高中生备考及教师辅助出题,初步评估显示其能高准确率生成合规考题并提供连贯解释。