11 papers
CastClaw: A Human-in-the-Loop Autonomous Agent for Interactive Time Series Forecasting
Xiaoyu Tao, Mingyue Cheng, Ze Guo +4
Practical time-series forecasting requires domain knowledge, constraints, plausibility checks, and human intervention. We present CastClaw, an interactive forecasting system center…
SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning
Panjing He, Mingyue Cheng, Yucong Luo +2
Spreadsheets are widely used to organize, analyze, and manipulate semi-structured data, yet automated spreadsheet reasoning remains challenging for large language models (LLMs). Re…
CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecasting
Xiaoyu Tao, Mingyue Cheng, Bokai Pan +6
Time series forecasting is fundamental to decision-making in complex systems, where future dynamics are influenced not only by historical observations but also by evolving contextu…
Learning Agentic Time Series Forecasting via Trajectory Distillation and Memory-Based Reinforcement Learning
Xiaoyu Tao, Mingyue Cheng, Chuang Jiang +7
Recent agentic time series forecasting (TSF) approaches use large language models (LLMs) to autonomously orchestrate analytical and forecasting tools and reason about temporal patt…
AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning
Xiaoyu Tao, Yuchong Wu, Mingyue Cheng +2
Time series anomaly detection is critical in many real-world applications, where effective solutions must localize anomalous regions and support reliable decision-making under comp…
Robust Residual Correction via Selective Deployment for Time Series Forecasting
Jianxiang Xie, Yuncheng Hua, Mingyue Cheng +3
Post-hoc residual correction can reduce forecasting error, but always-on updates often fail to generalize: when residual signals are weak or noisy, expressive correctors can overfi…
TimeFlow: Towards Stochastic-Aware and Efficient Time Series Generation via Flow Matching Modeling
He Panjing, Cheng Mingyue, Li Li +1
Generating high-quality time series data has emerged as a critical research topic due to its broad utility in supporting downstream time series mining tasks. A major challenge lies…
OneCast: Structured Decomposition and Modular Generation for Cross-Domain Time Series Forecasting
Tingyue Pan, Mingyue Cheng, Shilong Zhang +5
Cross-domain time series forecasting is a valuable task in various web applications. Despite its rapid advancement, achieving effective generalization across heterogeneous time ser…
STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models
Huajian Zhang, Mingyue Cheng, Yucong Luo +1
Table reasoning with large language models (LLMs) plays a critical role in building intelligent systems capable of understanding and analyzing tabular data. Despite recent progress…
AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Time Series Forecasting
Xiaohan Zhang, Tian Gao, Mingyue Cheng +5
Time series forecasting is typically treated as a single-pass numerical prediction task based on historical observations. However, real-world forecasting often requires expert-like…
Towards Context-aware Reasoning-enhanced Generative Searching in E-commerce
Zhiding Liu, Ben Chen, Mingyue Cheng +6
Search-based recommendation is one of the most critical application scenarios in e-commerce platforms. Users' complex search contexts--such as spatiotemporal factors, historical in…