6 papers
Qwen-CUA: Native Computer Use for (almost) Everything
Dunjie Lu, Shuai Bai, Tianyi Bai +42
Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive expe…
EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
Mianqiu Huang, Taofeng Xue, Chong Peng +12
Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments. Although imitation learning and offline t…
ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents
Youjin Wang, Run Zhou, Yingjie Ma +6
Adapting LLM agents to domain-specific tool calling remains notably brittle under evolving interfaces. Prompt and schema engineering is easy to deploy but often fragile under distr…
Social-JEPA: Emergent Geometric Isomorphism
Haoran Zhang, Youjin Wang, Yi Duan +6
World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such models from distinct viewpoints of the…
WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces
Sicheng Fan, Rui Wan, Yifei Leng +4
We introduce WebChain, the largest open-source dataset of human-annotated trajectories on real-world websites, designed to accelerate reproducible research in web agents. It contai…
WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
Sicheng Fan, Qingyun Shi, Shengze Xu +5
Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or costly, scarce human-crafted data and…