Reproduce “Nexus : An Agentic Framework for Context-Aware Time Series Forecasting” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sarkar Snigdha Sarathi Das, Palash Goyal, Mihir Parmar, Nanyun Peng, Vishy Tirumalashetty, Chun-Liang Li, Rui Zhang, Jinsung Yoon and 1 more
Nexus combines a numerical time-series forecast with two event-aware language-model outlooks. A profiling agent records patterns and changes, while macro and micro streams forecast shape and stepwise values; backtests calibrate prompts, and Bayesian synthesis combines all three using estimated errors. On Leaf’s 72-hour weather forecasts, Nexus reports 1.970°C MAE versus 2.632°C for MoiraiAgent, with smaller gains on short-horizon markets.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.