Generalist agents for contextualized time series

Arxiv CS.AI (top papers)

Proposes Harnessing Generalist Agents for Contextualized Time Series (HAGCTS), a framework that leverages LLM-based agents to incorporate rich contextual information for time series analysis. Achieves state-of-the-art results on forecasting, classification, and anomaly detection benchmarks.

See 1 more source

GITCO: Gated Inference-Time Context Optimization in TSFMs5 days agoManya Pandey, Dhruv Kumar, Murari Mandal, Saurabh Deshpande

Arxiv CS.AI (top papers)·Zihao LiKaifeng JinYuanchen BeiJiaru ZouAvaneesh KumarXuying NingYanjun ZhaoMengting AiBaoyu JingHanghang TongJingrui He

6 days ago