AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Time Series Forecasting

arXiv:2511.08947 · cs.AI · Submitted 2025-11-12 · Read on arXiv

cs.AI

Submitted: 2025-11-12

Updated: 2026-10-12

Comments: Accepted by CIKM 2026

Code: https://github.com/echo01-ai/AlphaCast

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Time Series Forecasting — 3× in this paper · explained in 4 episodes
• Agentic Reasoning — 1× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• Chronos: Learning the Language of Time Series
• TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
• Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
• Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention
• Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
• HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting
• DeepSeek-V3 Technical Report
• LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting
• How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook
• iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
• Sundial: A Family of Highly Capable Time Series Foundation Models
• Improving Time Series Forecasting via Instance-aware Post-hoc Revision
• TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state
• WebGPT: Browser-assisted question-answering with human feedback
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems