1
微软 CEO 纳德拉如何使用智能体：动手操控、追问、继续推理，而非盲目信任
IT之家 9 月 28 日消息，在最新一期 Sources Podcast 节目中，微软 CEO 萨提亚 · 纳德拉披露了 Cowork 和 Excel 智能体在自己日常工作中的用途。 纳德拉会用这些模型追踪美国证券交易委员会（SEC）的文件并分析电子表格，其中尤其看重 Excel 智能体模拟因果推…
2
WebChallenger: A Reliable and Efficient Generalist Web Agent
新论文提出WebChallenger，一个可靠高效的通用Web智能体，专为复杂网页任务设计。
arXiv:2606.10423v1 Announce Type: new Abstract: Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rel…
3
Harnessing Generalist Agents for Contextualized Time Series
通用智能体如何理解并处理带上下文的时间序列？最新arXiv论文给出系统性探索。
arXiv:2606.05404v1 Announce Type: new Abstract: Time series are often embedded in rich contexts that are essential for holistic modeling. Moreover, re…
4
Can Generalist Agents Automate Data Curation?
探讨通用AI代理能否自动化数据管理，提供前沿学术视角与实验分析
arXiv:2606.04261v1 Announce Type: new Abstract: Curating training data is among the most consequential yet labor-intensive parts of modern AI developm…
5
DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths
通用智能体协作新框架，用可解释动态决策路径破解规模化合作难题
arXiv:2603.00309v2 Announce Type: replace Abstract: The increasingly popular agentic AI paradigm promises to harness the power of multiple, general-pu…
6
Governance by Construction for Generalist Agents
从架构设计入手，探讨如何对通用人工智能体进行有效治理，一篇前沿的技术论文。
arXiv:2605.20874v1 Announce Type: new Abstract: Enterprise agents are increasingly expected to operate autonomously across tools and interfaces, yet p…
7
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
将强化学习与环境合成结合，为扩展工具使用智能体提供稳健新方法。
arXiv:2605.18703v1 Announce Type: cross Abstract: Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlen…