ACL Findings2026
CTRL: Control-Based Time Series Forecasting with LLM-Guided Residual Learning
Minkyoung Kim, Daeun Ji, Yohan Lee, Beomsoo Kim, Beakcheol Jang
Abstract
Time series forecasting underpins critical decision-making across diverse domains. While large language models (LLMs) offer promising reasoning capabilities, existing LLMbased time series forecasting approaches either reduce them to numerical predictors that bypass their strengths, or allow direct forecast generation that destabilizes predictions in nonstationary settings. We introduce CTRL, a framework that decouples semantic reasoning from quantitative prediction. A frozen backbone generates base forecasts, while specialized LLM agents function as controllers that analyze backbone prediction errors through decomposed trend, seasonal, and irregular components, grounding reasoning in interpretable temporal structure. Each agent outputs compact control signals that a lightweight residual decoder translates into forecast corrections. CTRL incorporates label-free test-time adaptation that detects distribution shift from input statistics alone and readapts control signals with only 3-24 LLM calls via caching. CTRL is explicitly designed to improve robustness under non-stationary temporal dynamics and distribution shift, while remaining competitive on highly stationary time series where adaptive correction provides limited additional benefit.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on27
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
- Are Transformers Effective for Time Series Forecasting?Ailing Zeng, Muxi Chen, Lei Zhang, Qiang XuAAAI 2023 · 3,619 citations
- Tent: Fully Test-Time Adaptation by Entropy MinimizationDequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno A. Olshausen et al.ICLR 2021 · 1,731 citations
Related papers
- FLAIRR-TS - Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time SeriesGunjan Jalori, Preetika Verma, Sercan Ö. ArikEMNLP Findings 2025 · 1 citation
- Training-Free Test-Time Contrastive Learning for Large Language ModelsKaiwen Zheng, Kai Zhou, Jinwu Hu, Te Gu et al.ACL Findings 2026
- From Implicit Graph Encoding to Explicit Evidence: A Training-Free LLM Framework for Temporal Knowledge Graph ReasoningGuo Tang, Ke Cheng, Huiming Fan, Heng Chang et al.ACL Findings 2026
- MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned ReasoningXiaoyu Tao, Mingyue Cheng, Ze Guo, Shuo Yu et al.ICML 2026 · 8 citations
- TARo: Token-level Adaptive Routing for LLM Test-time AlignmentArushi Rai, Qiang Zhang, Hanqing Zeng, Yunkai Zhang et al.ACL Findings 2026
