Agentic Reinforcement Learning (ARL) trains large language models to interleave reasoning with external tool execution to solve complex tasks. Most existing ARL methods train a single set of parameters to support both reasoning and tool-use behaviors, implicitly assuming that joint training leads to improved overall agent performance. Despite its widespread adoption, this assumption has rarely been examined empirically. In this paper, we systematically examine this assumption by introducing Capability Effect Attribution (CEA), which provides quantitative evidence of interference between reasoning and tool-use behaviors. Through an in-depth analysis, we show that these two capabilities often induce misaligned gradient directions, leading to training interference that undermines the effectiveness of joint optimization and challenges the prevailing ARL paradigm. To address this issue, we propose Disentangled Action--Reasoning Tuning (DART), a simple and efficient framework that explicitly decouples parameter updates for reasoning and tool use via separate low-rank adaptation modules. With this simple change alone, DART outperforms all joint-optimization baselines and approaches the 2-Agent upper bound across thirteen benchmarks on retrieval-augmented QA and NL2SQL, further supporting our finding of capability interference under shared optimization.
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 Comprehensive Survey of Agent Distillation across Models, Artifacts, and Harnesses
Central South University（中南大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Hong Kong Polytechnic University（香港理工大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
Beijing Institute of Technology（北京理工大学）；East China Normal University（华东师范大学）；University of Science and Technology of China（中国科学技术大学）；Tsinghua University（清华大学）；University of Chinese Academy of Sciences（中国科学院大学）
VERA: Scaling Verifiable Environments for Agentic co-Evolution
Nvidia（英伟达）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；National University of Singapore（新加坡国立大学）；Tsinghua University（清华大学）；Xian Jiaotong University（西安交通大学）；University of Pennsylvania（宾夕法尼亚大学）
Agentic Exploration of PDE Spaces using Latent Foundation Models for Parameterized Simulations
University of Michigan（密歇根大学）；Universidad Politécnica de Madrid（马德里理工大学）；Purdue University（普渡大学）；Universitat Politècnica de València（瓦伦西亚理工大学）；Caltech（加州理工学院）；University of Washington（华盛顿大学）
HEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation
Key Laboratory of Computing Power Network and Information Security, Ministry of Education（教育部算力网络与信息安全重点实验室）；Shandong Computer Science Center (National Supercomputer Center in Jinan)（山东省计算中心（国家超级计算济南中心））；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东省科学院））；Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing（山东省算力互联网与服务计算重点实验室）；Shandong Fundamental Research Center for Computer Science（山东省计算机科学基础研究中心）；University of Technology Sydney（悉尼科技大学）
Herculean: An Agentic Benchmark for Financial Intelligence
The Fin AI；Yale University（耶鲁大学）；Columbia University（哥伦比亚大学）；Stevens Institute of Technology（史蒂文斯理工学院）；NVIDIA（英伟达）；New York University（纽约大学）；Georgia Institute of Technology（佐治亚理工学院）；University of Florida（佛罗里达大学）；MBZUAI；Université de Montréal（蒙特利尔大学）；University of Minnesota（明尼苏达大学）；University of Massachusetts Boston（马萨诸塞大学波士顿分校）；National Institute of Advanced Industrial Science and Technology（国家先进工业科学与技术研究院）；University of Liverpool（利物浦大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；National University of Singapore（新加坡国立大学）；Halmstad University（哈尔姆斯塔德大学）；University of Manchester（曼彻斯特大学）；Cardiff University（卡迪夫大学）；McGill University（麦吉尔大学）；Mila – Quebec AI Institute（魁北克人工智能研究所）
