ServiceNow AI Research

Computer Agents

Grounding Computer Use Agents on Human Demonstrations
Grounding Computer Use Agents on Human Demonstrations
Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen …
International Conference on Learning Representations,  2026.
PDF Cite
Shifting AI Security to the Left: Design-Time Defenses to Mitigate the Risks of Prompt Injections
Shifting AI Security to the Left: Design-Time Defenses to Mitigate the Risks of Prompt Injections
Prompt injections pose a critical weakness for modern Large Language Models, making it difficult for AI to distinguish between …
NOW AI,  2025.
Cite
StarUI: Learning to Ground Agentic Perception in Desktop GUIs
Desktop environments remain the blind spot of multimodal-LLM agents: unlike web or mobile, they span heterogeneous software, lack …
NOW AI,  2025.
Cite
WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation
WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation
We present WebMMU, a multilingual benchmark that evaluates three core web tasks: (1) website visual question answering, (2) code …
NOW AI,  2025.
Cite
A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches
A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches
Existing approaches for low-resource text summarization primarily employ large language models (LLMs) like GPT-3 or GPT-4 at inference …
North American Chapter of the Association for Computational Linguistics (NAACL),  2025.
PDF Cite