Computer-use agents increasingly tackle tasks ranging from everyday desktop activities to long-horizon professional workflows. Yet interfaces centered on screenshots and mouse-and-keyboard actions can impose a human-interaction prior, requiring repeated screen interpretation while leaving the computer's semantic and pr...
Hao-Qing Wang, Xiao-Yi Zhang, Si-Cheng Fan et al.· 0 citations
The proposed EDRM (Entropy Dynamics-based Reasoning Manifold), a lightweight routing framework whose default heuristic requires no router training, supports selective reasoning based on early decoding signals and demonstrates the potential of entropy-based control for efficient LLM inference.
Wei Xia, Haoqing Wang, Zhi-Hong Deng et al.· 2 citations
This work systematically compares six causal structures, eight latent representations, and four training objectives, covering popular design choices in existing WAMs, to provide a systematic understanding of how core design choices affect world-action modeling and what principles can guide the development of future WAM...
The RLVR across domains exhibits small mutual interferences, and reasoning-intensive domains have mutually synergistic effects, and the internal mechanisms from the perspectives of information constraints, model prediction behavior and self-verification are analyzed.
Haoqing Wang, Xiang Long, Ziheng Li et al.· arXiv.org· 11 citations
FaithEyes, a multi-agent self-judging framework that uses a VLM to judge whether each process image helps answer the question and designs a multi-agent framework where the model itself serves as a subagent to judge the tool calls from the main agent, eliminating any dependence on external models at inference.
Mage-VL is presented, an efficient codec-native streaming foundation model for real-time multimodal understanding and interaction and establishes AI4AI data pipelines encompassing prompt-code joint optimization for multimodal captioning and AI-driven performance diagnosis to guide training recipes.