ServiceNow AI Research

9

CUA-Suite: Expert Trajectories and Pixel-Precise Grounding for Computer-use Agents
Workshop at the International Conference of Machine Learning (ICML),  2026.
Cite
Hierarchical Retrieval at Scale: Bridging Transparency and Efficiency
Hierarchical Retrieval at Scale: Bridging Transparency and Efficiency
Information retrieval is a core component of many intelligent systems as it enables conditioning of outputs on new and large-scale …
Workshop at the International Conference of Machine Learning (ICML),  2026.
Paper Cite Video
Overcoming the Modality Gap in Context-Aided Forecasting
Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to …
Workshop at the International Conference of Machine Learning (ICML),  2026.
Cite
Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs
Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs
Forecasting in real-world settings requires models to integrate not only historical data but also relevant contextual information, …
Workshop at the Neural Information Processing Systems (NeurIPS),  2025.
Paper Cite
GitChameleon: Evaluating AI Code Generation Against Python Library Version Incompatibilities
GitChameleon: Evaluating AI Code Generation Against Python Library Version Incompatibilities
The rapid evolution of software libraries presents a significant challenge for code generation models, which must adapt to frequent …
Workshop at the Neural Information Processing Systems (NeurIPS),  2025.
Paper Cite Code
How to Train Your LLM Web Agent: A Statistical Diagnosis
How to Train Your LLM Web Agent: A Statistical Diagnosis

Large language model (LLM) agents for web interfaces have advanced rapidly, yet open-source systems still lag behind proprietary …

Workshop at the Neural Information Processing Systems (NeurIPS),  2025.
Paper Cite
Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs
Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs
Forecasting in real-world settings requires models to integrate not only historical data but also relevant contextual information, …
Conference on Language Modeling Workshops,  2025.
Paper Cite
Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training
Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training
We introduce a framework for optimizing domain-specific dataset construction in foundation model training. Specifically, we seek a …
Conference on Language Modeling Workshops,  2025.
Paper Cite
AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery
AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery
We introduce AgentAda, the first LLM-powered analytics agent that can learn and use new analytics skills to extract more specialized …
Workshop at the Annual Meeting of the Association for Computational Linguistics (ACL),  2025.
Paper Cite
Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
We propose Adaptive Diffusion Denoised Smoothing, a method for certifying the predictions of a vision model against adversarial …
Workshop at the International Conference of Machine Learning (ICML),  2025.
Paper Cite