Agentic time series forecasting extends conventional approaches beyond one-shot numerical prediction toward autonomous, context-aware interaction. However, existing benchmarks offer limited integrated support for diverse contextual information, forecasting-specific adaptive interactions, and systematic evaluation of fo...
Bo-Kai Pan, Rui-Jie Yang, Ming-Yue Cheng et al.· 0 citations
Time series forecasting (TSF) is a fundamental task in diverse decision-making scenarios, such as business intelligence, energy management, healthcare, and scientific discovery. Over the past decades, TSF has been extensively studied, with methods evolving from traditional statistical models to recent data-driven deep...
Ming-Yue Cheng, Zhi-Ding Liu, Xiao-Yu Tao et al.· IEEE Transactions on Knowled...· 21 citations
This paper proposes CastReasoner, an evidence-grounded reasoning model for context-aware time series forecasting that uses a structured chain of thought (CoT) to extract predictive evidence from contextual features, infer the future dynamics suggested by this evidence, and assess these dynamics against the forecast pri...
Xing-Peng Gao, Ming-Yue Cheng, Dao-Yu Wang et al.· 0 citations
Practical time-series forecasting requires domain knowledge, constraints, plausibility checks, and human intervention. We present CastClaw, an interactive forecasting system centered on an autonomous forecasting loop and supported by a forecasting-oriented harness. Users create and refine tasks in natural language thro...
Xiao-Yu Tao, Ming-Yue Cheng, Ze Guo et al.· 0 citations
CastFSR is proposed, an agentic framework that formulates context-aware forecasting as a Fast--Slow--Reflect workflow that supports both training-free inference with off-the-shelf LLMs and efficient deployment through a two-stage SFT and reinforcement learning strategy that transfers its orchestration capability to com...
Xiao-Yu Tao, Mingyue Cheng, Bo-Kai Pan et al.· 0 citations
CastClaw is presented, a human-in-the-loop autonomous forecasting system built through forecasting-oriented harness engineering that connects data, specialized models, analytical tools, user input, and a versioned execution record in one runtime.
Xiao-Yu Tao, Ming-Yue Cheng, Ze Guo et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.