KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning
cs.AI
Submitted: 2026-05-28
Updated: 2026-09-09
Comments: Accepted at EMNLP 2026
Project page: https://foundation-model-research.github.io/KairosAgent
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- GPT-4 Technical Report
- Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting
- Augur: Modeling Covariate Causal Associations in Time Series via Large Language Models
- Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models
- Monash Time Series Forecasting Archive
- The Llama 3 Herd of Models
- TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- UniCA: Unified Covariate Adaptation for Time Series Foundation Model
- FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series
- LibCity: A Unified Library Towards Efficient and Comprehensive Urban Spatial-Temporal Prediction
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- OpenAI GPT-5 System Card
- TiMi: Empower Time Series Transformers with Multimodal Mixture of Experts
- GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning
- Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting
- Kimi K2.5: Visual Agentic Intelligence
- Bridging AI and Energy Forecasting: An Autonomous Workflow with Customized Toolkit
- Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domain
- SciTS: Scientific Time Series Understanding and Generation with LLMs
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection