LLM-Based Time Series Forecasting

Follow this topic Ask about this topic

LLM-based time series forecasting studies how language models can predict future values or events from numerical sequences, often enriched with news, clinical notes, weather, or other context. Common approaches map time-series patches or frequency features into frozen or lightly adapted LLMs, combine them with specialized time-series foundation models, or use retrieval and agents to interpret events and revise forecasts; probabilistic decoders and multimodal fusion address uncertainty and heterogeneous inputs. Applications include finance, traffic, energy, epidemics, and healthcare, with evaluations spanning long- and short-horizon accuracy, zero-shot transfer, and benchmarks such as GIFT-Eval and M4. A central tension is that contextual reasoning and pretraining can help under domain shift or sparse data, but numerical forecasters often remain stronger, while reported gains can be vulnerable to leakage and metrics that overlook calibration or tail errors.

Latest papers

100 papers11 papers in the last four weeks, down 42% on the four weeks before. 0.1% of all new papers.

Training-Free Continual Learning for Multimodal Forecasting via Prompt Evolution
Oct 20, 2026Laurent Mombaerts, Jonathan Taws, Jacopo Gargano +4LLM-Based Time Series Forecasting Prompt Optimization
Amazon Web Services · University of California
MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision
Oct 13, 2026Ziyang Zhang, Shenyi Li, Yilin Wang +4Multimodal Large Language Models Multimodal Dataset
Tsinghua University · Shanghai Artificial Intelligence Laboratory
GIFT-Eval-CTX: A Benchmark For Contextual Forecasting Model Evaluation
Oct 13, 2026Xu Liu, Hanshu Yan, Taha Aksu +6Time Series Forecasting Forecasting Benchmarks
Moirai Team, Salesforce AI Research
ChronoScribe: Semantic-Numerical Specialization for Instruction-Driven Time Series Forecasting
Oct 12, 2026Yuchen Jiao, Miao Zhang, Yuxuan Liu +1Time Series Forecasting LLM-Based Time Series Forecasting
Beijing University of Posts and Telecommunications
Textual Environmental Context and Spatial Graphs for LLM-Based Regional SST Forecasting
Oct 6, 2026Xiong Li, Xiaowei Zhou, Yanwei Yu +2Spatiotemporal Forecasting LLM-Based Time Series Forecasting
Ocean University of China, Qingdao, China
Can LLM-assisted regularization increase forecast accuracy for migration flows in low data regimes?
Oct 5, 2026Nathaniel T. Hindman, Fabricio MuraiTime Series Forecasting LLM-Based Time Series Forecasting
Artificial Intelligence Worcester Polytechnic Institute Worcester, Massachusetts · Data Science Worcester Polytechnic Institute Worcester, Massachusetts
FreSia: Frequency-Semantic Instantiation and Alignment for Multivariate Time Series Analysis
Oct 5, 2026Yubo Wang, Hui He, Hezhe Qiao +2Multivariate Time Series Forecasting Frequency-Domain Time Series Modeling
School of Computer Science and Technology, Beijing Institute of Technology, No.5 Zhongguancun South Street, Beijing, 100081, China · School of Computing and Information Systems, Singapore Management University, 80 Stamford Road, 178902, Singapore
SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting
Oct 2, 2026Mingtian Tan, Palash Goyal, Mihir Parmar +6Time Series Forecasting Exogenous Time Series Forecasting
Google Cloud AI Research · University of Virginia
OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning
Sep 30, 2026Tony Chen, Timo Stoffregen, Maxwell Xu +8Temporal Reasoning in Language Models LLM-Based Time Series Forecasting
Columbia University, USA · Stanford University, USA · Aionic Labs, Switzerland +4
JudgeCast: Time Series Forecasting with Experience-Informed Covariate Judgements
Sep 29, 2026Donguk Kwon, Wooseok Jeong, Dongha LeeTime Series Forecasting Time Series Forecasting with Covariates
Yonsei University · Konkuk University
Can Language Models Learn to Forecast Stock Prices
Sep 29, 2026Jiacheng Guo, Suozhi Huang, Shuzhen Li +11Financial Forecasting LLM-Based Time Series Forecasting
Princeton University · InclusionAI · Harvard University +1
RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting
Sep 27, 2026Tong Liu, Lanmiao Liu, Xiang HuStock Price Forecasting Financial Forecasting
Zircon Security · Utrecht University · The Max Planck Institute for Psycholinguistics +1
Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy Learning
Sep 26, 2026Junyi Wang, Yilin Wang, Wen Wu +1LLM-Based Time Series Forecasting Self-Evolving Agents
Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · Tsinghua University
TimeBraid: Unifying Time Series and Language for Understanding and Forecasting
Sep 24, 2026Xinyue Wang, Jiacheng Pang, Kun Zhou +7Unified Multimodal Models Multimodal Pretraining
University of California San Diego · Aether AI · University of Southern California
Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States
Sep 24, 2026Shuhao Li, Weidong Yang, Changan Liu +4Spatiotemporal Forecasting Conditional Generative Modeling
Fudan University Shanghai, China · Fudan University Shanghai, China Zhuhai Fudan Innovation Research Institute Zhuhai, China · College of Computing and Data Science Nanyang Technological University Singapore +2
TimeLitmus: A Diagnostic Benchmark for Cross-Modal Understanding and Explanation Faithfulness in Event-Conditioned Time-Series Prediction
Sep 21, 2026Jie Gong, Maowei Jiang, Zhiwei Liu +6LLM Evaluation LLM-Based Time Series Forecasting
School of Artificial Intelligence, Wuhan University, China · Nanjing Audit University, China · The University of Manchester, United Kingdom +3
CTRL: Control-Based Time Series Forecasting with LLM-Guided Residual Learning
Sep 20, 2026Minkyoung Kim, Daeun Ji, Yohan Lee +2Time Series Forecasting LLM-Based Time Series Forecasting
Graduate School of Information, Yonsei University, Seoul, Republic of Korea
Beyond Similarity: Coverage-Aware Prompt Selection for Time Series Forecasting with LLMs
Sep 19, 2026Daeun Ji, Minkyoung Kim, Dongkuk Kim +3LLM Prompting LLM-Based Time Series Forecasting
Graduate School of Information, Yonsei University, Seoul, Republic of Korea
DualCast: A Dual-Path Language Model for Bimodal Financial Time-Series Forecasting
Sep 18, 2026Wentao Zhao, Hongqiang Wu, Shanghang Liu +3Financial Forecasting Time Series Forecasting
Department of Automation, Tsinghua University, Beijing, 100084, China · School of Software, Tsinghua University, Beijing, 100084, China · School of Computer Science, Northwestern Polytechnical University, Xi’an, 710129, China +1
Tracing the Evidence Behind Zero-Shot Time-Series Forecasting: A Source-First Taxonomy and Audit Framework
Sep 18, 2026Delun Kong, Wanyun Ling, Chenxi Liu +1Zero-Shot Time Series Forecasting LLM-Based Time Series Forecasting
Department of Operations and Technology Technical University of Munich Heilbronn, Germany · Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong, China
Parameter-Efficient Adaptation of Pretrained Language Models for Time-Series Forecasting
Sep 14, 2026Tamanna Kumavat, Georg Brunner, Kyriakos FlourisTime Series Forecasting LLM-Based Time Series Forecasting
University of Zurich, Switzerland · Computer Vision Laboratory, ETH Zurich, Switzerland · MRC Biostatistics Unit, University of Cambridge, United Kingdom
STHMoE: Hypergraph-Enhanced Heterogeneous Dependency Coordination for LLM-Based Urban Traffic Data Forecasting
Sep 14, 2026Jiawen Chen, Qi Shao, Yongjian Chang +3Traffic Flow Estimation LLM-Based Time Series Forecasting
School of Mathematics, Southeast University, Nanjing 210096, China · School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China · Jiangsu Province Center for Applied Mathematical Sciences, Nanjing 210096, China
LLaTSA: Large Language Model-Aligned General-Purpose Transient Stability Analysis
Sep 13, 2026Chao Shen, Hongwei Zhen, Junyan Shao +3Power Systems Trajectory Prediction
Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting
Sep 10, 2026Jihoon Kwon, Lawrence Liu, Daekyung Park +15Financial Forecasting Time Series Forecasting
LinqAlpha · Carbon Arc · Kalshi +7
A Dynamic Fusion Large Language Model for Traffic Flow Prediction
Sep 10, 2026Xue Qiu, Jianli XiaoIntelligent Transportation Systems Traffic Flow Estimation
School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China
Bidirectional Multimodal Fusion of Sky Images and Time-Series for Solar Forecasting with Large Language Models
Sep 10, 2026Ken Chen, Maneesha Perera, Wei Wang +3Multivariate Time Series Forecasting Multimodal Large Language Models
Department of Mechanical Engineering, The University of Melbourne, Melbourne, Australia · Department of Mechanical Engineering, Sri Lanka Institute of Information Technology, Sri Lanka
It's All in the Way You Say It: The Role of Information Representation in LLM-Based Glycemic-Event Prediction
Sep 8, 2026Andrea Apicella, Pasquale Arpaia, Matteo Orefice +2LLM Prompting Blood Glucose Forecasting
Department of Information Engineering, Electrical Engineering, and Applied Mathematics (DIEM), University of Salerno, Fisciano (SA), Italy · Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy
PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting
Sep 4, 2026Maryam Fakhari, Mehran SafayaniLLM-Based Time Series Forecasting Financial Time Series
Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan, Iran
Compositional Spectral Prompts for LLM-based Online Time Series Forecasting
Sep 2, 2026Seungyoon Choi, Hyunchul Kim, Jae-Gil Lee +1Online Time Series Forecasting Time Series Forecasting
KAIST Daejeon, Republic of Korea
Can LLMs Take the Pulse of the Economy? A Real-Time Evaluation of LLM Nowcasts on Macroeconomic Indicators
Aug 31, 2026Xinyue Zhao, Ruiyi Zhang, Liqin Ye +3Time Series Forecasting LLM Agent Evaluation
Georgia Institute of Technology · University of California San Diego

Oct 20, 2026J/K move · Enter open · S save

Training-Free Continual Learning for Multimodal Forecasting via Prompt Evolution

Laurent Mombaerts, Jonathan Taws, Jacopo Gargano, Dinesh Gaddam+3

Amazon Web Services · University of California

LLM-Based Time Series Forecasting Prompt Optimization Multivariate Time Series Forecasting

Open paper AskPDF arXiv

Adapting a forecasting system to a changing world classically means retraining. We ask whether the task of continually learning regimes for time series forecasting can be represented by a piece of text: a guidance block, evolved by outcome-driven reflection and used in a frozen LLM forecaster's prompt. On a refreshed multimodal benchmark (weekly search indices, daily currencies, daily commodities, each window paired with web-retrieved news), we run GEPA-style prompt evolution under strict contamination control to prevent the data leakage common in timeseries benchmarks: the forecaster's knowledge cutoff predates every evaluated window. A 900-word evolved guidance carried by Llama-3.3-70B beats TimeSeries Foundation Models (TSFMs) on held-out data (GM MASE 0.776 vs. 0.898 for TabPFN-TS-3), transfers to more recent models without measurable loss, and costs dollars rather than GPU-days to update. We characterize the loop: out-of-loop gains concentrate in the first reflection, in-loop improvements overstate out-of-loop gains 2-3x unless an untouched monitor arbitrates, and error-only objectives silently suppress the text modality. We provide two extensions. First, compiling the guidance into executable code with a TSFM as a callable tool recovers most of the gain deterministically. Second, ablations show the advantage widens at short horizons and that removing the news text does not hurt the guided forecaster, consistent with the text's value being distilled into policy during learning. We argue that continual prompt evolution is a practical, training-free alternative to retraining for multimodal forecasting.