Awesome Agentic Time Series

June 19, 2026 · View on GitHub

Awesome License: MITContribution Welcome Papers

A curated list of papers on Agentic Time Series, covering time series foundation models, LLM4TS, temporal reasoning, benchmarks, memory, world models, reliability, and fully agentic time series systems.

📢 News

🚩 2026-06- 📄 Our survey is released! See the PDF in this repository for the paper The Landscape of Agentic Time Series Systems: Architectures, Reliability, and Frontiers.

🚩 2026-06- 📚 We create this repository to maintain a paper list on Awesome-Agentic-Time-Series.

🚩 Contributions are welcome. If a relevant paper is missing or misclassified, please open an issue or submit a pull request.

Overview of the evolutionary path of time series intelligence across four major research streams: benchmarks, foundation models, LLM4TS, and time series agents.

Figure: Overview of the evolutionary path of time series intelligence across four major research streams: benchmarks, foundation models, LLM4TS, and time series agents.

💡Introduction

The compositional architecture of the closed-loop agentic time series system.

Figure: The compositional architecture of the closed-loop agentic time series system.

📚 Paper list

Surveys and Position Papers

  • [2026/05] Agentic Trading: When LLM Agents Meet Financial Markets. [paper]
  • [2026/04] From Prompts to Agents: A Comprehensive Survey of LLM-Driven Time Series Analysis. [paper]
  • [2026/02] Position: Beyond Model-Centric Prediction—Agentic Time Series Forecasting. [paper]
  • [2025/10] Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision. [paper]
  • [2025/09] A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models. [paper]
  • [2025/06] Large Language Models for Time Series Analysis: Techniques, Applications, and Challenges. [paper]
  • [2025/02] Achieving Time Series Reasoning Requires Rethinking Model Design, Tasks Formulation, and Evaluation. [paper]
  • [2024/02] Large Language Models for Time Series: A Survey. [paper]

Benchmarks and Datasets

Forecasting and General Evaluation

  • [2026/02] It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks. [paper]
  • [2025/09] fev-bench: A Realistic Benchmark for Time Series Forecasting. [paper]
  • [2024/10] GIFT-Eval: A Benchmark for General Time Series Forecasting Model Evaluation. [paper]
  • [2023/06] ChatGPT Informed Graph Neural Network for Stock Movement Prediction. [paper]
  • [2018/10] Hybrid Deep Sequential Modeling for Social Text-Driven Stock Prediction. [paper]
  • [2018/07] Stock Movement Prediction from Tweets and Historical Prices. [paper]

Multimodal and Text-Paired Datasets

  • [2026/03] FinTexTS: Financial Text-Paired Time-Series Dataset via Semantic-Based and Multi-Level Pairing. [paper]
  • [2025/09] Fidel-TS: A High-Fidelity Multimodal Benchmark for Time Series Forecasting. [paper]
  • [2025/06] Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series. [paper]
  • [2025/06] FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis. [paper]
  • [2025/05] MoTime: A Dataset Suite for Multimodal Time Series Forecasting. [paper]
  • [2024/11] Multi-Modal Forecaster: Jointly Predicting Time Series and Textual Data. [paper]
  • [2024/10] Context is Key: A Benchmark for Forecasting with Essential Textual Information. [paper]
  • [2024/09] From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection. [paper]
  • [2024/06] Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis. [paper]
  • [2024/06] LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis. [paper]
  • [2024/02] FNSPID: A Comprehensive Financial News Dataset in Time Series. [paper]
  • [2021/09] Well Googled is Half Done: Multimodal Forecasting of New Fashion Product Sales with Image-based Google Trends. [paper]

Reasoning, QA and Diagnostic Evaluation

  • [2026/06] ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning. [paper]

  • [2026/06] TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning. [paper]

  • [2026/04] TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale. [paper]

  • [2026/04] TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems. [paper]

  • [2026/04] ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Response. [paper]

  • [2026/03] HEARTS: Benchmarking LLM Reasoning on Health Time Series. [paper]

  • [2026/02] TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks. [paper]

  • [2026/02] MMTS-BENCH: A Comprehensive Benchmark for Time Series Understanding and Reasoning. [paper]

  • [2026/01] TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models. [paper]

  • [2026/01] TSAQA: Time Series Analysis Question And Answering Benchmark. [paper]

  • [2025/09] When LLM Meets Time Series: Can LLMs Perform Multistep Time Series Reasoning and Inference. [paper]

  • [2025/09] CaTS-Bench: Can Language Models Describe Time Series?. [paper]

  • [2025/07] TIME-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback. [paper]

  • [2025/06] ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset. [paper]

  • [2025/03] Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement. [paper]

  • [2025/03] MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering. [paper]

  • [2025/02] Investigating Compositional Reasoning in Time Series Foundation Models. [paper]

  • [2024/10] TimeSeriesExam: A Time Series Understanding Exam. [paper]

  • [2024/10] Can LLMs Understand Time Series Anomalies?. [paper]

  • [2024/04] Language Models Still Struggle to Zero-shot Reason about Time Series. [paper]

  • [2024/04] Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmark. [paper]

  • [2020/05] ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data. [paper]

Agentic, Engineering and Decision Evaluation

  • [2026/05] Foresight Arena: An On-Chain Benchmark for Evaluating AI Forecasting Agents. [paper]
  • [2026/05] Dr-CiK: A Testbed for Foresight-Driven Agents. [paper]
  • [2025/07] LLM Agents Struggle at Engineering Time Series Solutions. [paper]
  • [2025/05] TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents. [paper]

Event Forecasting and Future Prediction

  • [2026/01] FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains. [paper]
  • [2025/10] LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena. [paper]
  • [2025/08] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction. [paper]
  • [2025/02] ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities. [paper]
  • [2024/04] AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval. [paper]
  • [2022/06] Forecasting Future World Events with Neural Networks (AutoCast). [paper]

Time Series Foundation Models

  • [2026/05] Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling. [paper]
  • [2026/05] Toto 2.0: Time Series Forecasting Enters the Scaling Era. [paper]
  • [2026/05] Time Series Causal Discovery via Context-Conditioned and Causality-Augmented Pretraining. [paper]
  • [2026/05] AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting. [paper]
  • [2026/03] Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling. [paper]
  • [2026/03] TimeCAP: A channel aware pre training framework for multivariate time series forecasting. [paper]
  • [2026/02] TS-Memory: Plug-and-Play Memory for Time Series Foundation Models. [paper]
  • [2026/02] MEMTS: Internalizing Domain Knowledge via Parameterized Memory for Retrieval-Free Domain Adaptation of Time Series Foundation Models. [paper]
  • [2025/11] Moirai 2.0: When Less Is More for Time Series Forecasting. [paper]
  • [2025/10] Synthetic Series-Symbol Data Generation for Time Series Foundation Models. [paper]
  • [2025/10] Chronos-2: From Univariate to Universal Forecasting. [paper]
  • [2025/08] Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting. [paper]
  • [2025/06] LightGTS: A Lightweight General Time Series Forecasting Model. [paper]
  • [2025/05] TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysis. [paper]
  • [2025/05] TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning. [paper]
  • [2025/05] Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting. [paper]
  • [2025/03] TS-RAG: Retrieval-Augmented Generation-Based Time Series Foundation Models are Stronger Zero-Shot Forecaster. [paper]
  • [2025/02] Sundial: A Family of Highly Capable Time Series Foundation Models. [paper]
  • [2025/02] GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series Data. [paper]
  • [2025/01] From Tables to Time: Extending TabPFN-v2 to Time Series Forecasting. [paper]
  • [2024/09] Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts. [paper]
  • [2024/07] Toto: Time Series Optimized Transformer for Observability. [paper]
  • [2024/03] UniTS: Building a Unified Time Series Model. [paper]
  • [2024/03] Chronos: Learning the Language of Time Series. [paper]
  • [2024/02] Unified Training of Universal Time Series Forecasting Transformers. [paper]
  • [2024/02] Timer: Generative Pre-trained Transformers Are Large Time Series Models. [paper]
  • [2024/02] MOMENT: A Family of Open Time-series Foundation Models. [paper]
  • [2024/01] Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series. [paper]
  • [2023/10] TimeGPT-1. [paper]
  • [2023/10] Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting. [paper]
  • [2023/10] A Decoder-Only Foundation Model for Time-Series Forecasting. [paper]

LLM4TS

Translation and Alignment

  • [2026/05] What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions. [paper]
  • [2026/05] STaT: Resolving Shape Distortion in Non-Stationary Time Series via Tri-Modal Synergy. [paper]
  • [2026/05] PaP-NF: Probabilistic Long-Term Time Series Forecasting via Prefix-as-Prompt Reprogramming and Normalizing Flows. [paper]
  • [2026/05] Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting. [paper]
  • [2026/02] Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysis. [paper]
  • [2026/01] Bridging Temporal and Textual Modalities: A Multimodal Framework for Automated Cloud Failure Root Cause Analysis. [paper]
  • [2026/01] An Exploratory Study to Repurpose LLMs to a Unified Architecture for Time Series Classification. [paper]
  • [2025/10] TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning. [paper]
  • [2025/10] OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data. [paper]
  • [2025/09] Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement. [paper]
  • [2025/09] AXIS: Explainable Time Series Anomaly Detection with Large Language Models. [paper]
  • [2025/08] UniCast: A Unified Multimodal Prompting Framework for Time Series Forecasting. [paper]
  • [2025/08] Semantic-Enhanced Time-Series Forecasting via Large Language Models. [paper]
  • [2025/08] From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization. [paper]
  • [2025/08] DP-GPT4MTS: Dual-Prompt Large Language Model for Textual-Numerical Time Series Forecasting. [paper]
  • [2025/07] DualSG: A Dual-Stream Explicit Semantic-Guided Multivariate Time Series Forecasting Framework. [paper]
  • [2025/06] Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives. [paper]
  • [2025/05] Human in the Loop Adaptive Optimization for Improved Time Series Forecasting. [paper]
  • [2025/03] TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop. [paper]
  • [2025/03] GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images. [paper]
  • [2025/02] Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative. [paper]
  • [2025/02] Adapting Large Language Models for Time Series Modeling via a Novel Parameter-efficient Adaptation Method. [paper]
  • [2025/01] Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series. [paper]
  • [2025] STEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis. [paper]
  • [2025] FreqLLM: Frequency-Aware Large Language Models for Time Series Forecasting. [paper]
  • [2024/12] ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning. [paper]
  • [2024/12] ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data. [paper]
  • [2024/11] A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization. [paper]
  • [2024/09] Towards Time Series Reasoning with LLMs. [paper]
  • [2024/06] TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment. [paper]
  • [2024/05] MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs. [paper]
  • [2024/03] CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning. [paper]
  • [2024/03] S2S^2IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting. [paper]
  • [2024/03] JoLT: Jointly Learned Representations of Language and Time-Series. [paper]
  • [2024/02] Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning. [paper]
  • [2024/02] AutoTimes: Autoregressive Time Series Forecasters via Large Language Models. [paper]
  • [2023/10] Time-LLM: Time Series Forecasting by Reprogramming Large Language Models. [paper]
  • [2023/10] TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting. [paper]
  • [2023/08] TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series. [paper]
  • [2023/08] LLM4TS: Two-Stage Fine-Tuning for Time-Series Forecasting with Pre-trained LLMs. [paper]
  • [2023/02] One Fits All: Power General Time Series Analysis by Pretrained LM. [paper]
  • [2022/10] PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting. [paper]

Temporal Reasoning

  • [2026/05] Reasoning-Aware Training for Time Series Forecasting. [paper]
  • [2026/05] Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs. [paper]
  • [2026/02] TimeOmni-VL: Unified Models for Time Series Understanding and Generation. [paper]
  • [2026/02] Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning. [paper]
  • [2026/02] PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering. [paper]
  • [2026/02] Adaptive Time Series Reasoning via Segment Selection. [paper]
  • [2026/01] Rationale-Grounded In-Context Learning for Time Series Reasoning with Multimodal Large Language Models. [paper]
  • [2025/12] Chain-of-thought Reviewing and Correction for Time Series Question Answering. [paper]
  • [2025/12] Delving into Large Language Models for Effective Time-Series Anomaly Detection. [paper]
  • [2025/10] Training-Free Time Series Classification via In-Context Reasoning with LLM Agents (FETA). [paper]
  • [2025/10] Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement Learning. [paper]
  • [2025/10] Augur: Modeling Covariate Causal Associations in Time Series via Large Language Models. [paper]
  • [2025/09] Trading-R1: Financial Trading with LLM Reasoning via Reinforcement Learning. [paper]
  • [2025/09] TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models. [paper]
  • [2025/06] TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning. [paper]
  • [2025/06] Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs. [paper]
  • [2025/05] Time-R1: Towards Comprehensive Temporal Reasoning in LLMs. [paper]
  • [2025/05] Can Slow-Thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting. [paper]
  • [2025/04] Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models. [paper]
  • [2025/02] Retrieval-augmented Large Language Models for Financial Time Series Forecasting. [paper]
  • [2024/08] Can LLMs Serve as Time Series Anomaly Detectors?. [paper]
  • [2024/02] LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting. [paper]

Agentic Time Series Systems

Perception Agents

  • [2026/05] MarsTSC: Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning. [paper]
  • [2026/03] Optimizing Multi-Agent Weather Captioning via Text Gradient Descent: A Training-Free Approach with Consensus-Aware Gradient Fusion. [paper]
  • [2026/03] Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents. [paper]
  • [2026/03] AGCD: Agent-Guided Cross-Modal Decoding for Weather Forecasting. [paper]
  • [2026/02] MAS4TS: Visual Reasoning over Time Series via Multi-Agent System. [paper]
  • [2026/01] TS-Debate: Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning. [paper]
  • [2025/11] Hierarchical AI-Meteorologist: LLM-Agent System for Multi-Scale and Explainable Weather Forecast Reporting. [paper]
  • [2025/08] ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents. [paper]
  • [2025/02] TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents. [paper]
  • [2025/02] Can Multimodal LLMs Perform Time Series Anomaly Detection?. [paper]
  • [2024/10] Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation. [paper]
  • [2024/05] CityGPT: Towards Urban IoT Learning, Analysis and Interaction with Multi-Agent System. [paper]

Reasoning Agents

  • [2026/05] KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning. [paper]
  • [2026/05] SAGE: Detecting Time Series Anomalies Like an Expert: A Multi-Agent LLM Framework with Specialized Analyzers. [paper]
  • [2026/02] AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning. [paper]
  • [2026/01] TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation. [paper]
  • [2026/01] ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction Evolution. [paper]
  • [2025/12] Multi-Agent Adversarial Time Series Forecasting. [paper]
  • [2025/11] AlphaCast: An Interaction-Driven Agentic Reasoning Framework for Cognition-Inspired Time Series Forecasting. [paper]
  • [2025/10] TS-Agent: A Time Series Reasoning Agent with Iterative Statistical Insight Gathering. [paper]
  • [2025/08] CALM: Continuous, Adaptive, and LLM-Mediated Anomaly Detection in Time-Series Streams. [paper]
  • [2025/06] FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making. [paper]
  • [2025/04] Can Competition Enhance the Proficiency of Agents Powered by Large Language Models in the Realm of News-driven Time Series Forecasting?. [paper]
  • [2024/10] TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis. [paper]

Planning and Action Agents

  • [2026/06] Harnessing Generalist Agents for Contextualized Time Series. [paper]
  • [2026/06] GenAutoML: An Agentic Framework for Dynamic Architecture Generation and Optimization in Time-Series Analysis. [paper]
  • [2026/05] Nexus: An Agentic Framework for Time Series Forecasting. [paper]
  • [2026/05] AION: Next-Generation Tasks and Practical Harness for Time Series. [paper]
  • [2026/03] SEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithms. [paper]
  • [2026/02] Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting. [paper]
  • [2026/01] LLM-Enhanced Reinforcement Learning for Time Series Anomaly Detection. [paper]
  • [2026/01] AutoLFM: A Multi-Agent LLM Framework for Automated Building Load Forecasting. [paper]
  • [2026] An Interpretable Agent-Assisted Pipeline for Statistical Anomaly Detection in IoT Temperature Time Series. [paper]
  • [2026] MoiraiAgent: An Agentic Framework for Context-Aware Time-Series Forecasting. [paper]
  • [2025/12] Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting. [paper]
  • [2025/12] Many Minds, One Goal: Time Series Forecasting via Sub-task Specialization and Inter-agent Cooperation. [paper]
  • [2025/11] TimeCIEL: Contextual Interactive Ensemble Learning for Time Series Classification. [paper]
  • [2025/10] TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis. [paper]
  • [2025/09] TimeCopilot. [paper]
  • [2025/08] Structured Agentic Workflows for Financial Time-Series Modeling with LLMs and Reflective Feedback. [paper]
  • [2025/08] DCATS: Empowering Time Series Forecasting with LLM-Agents. [paper]
  • [2025/06] MAT-AITSC: Multi-Agent Transformer-based Automated Imbalanced Time Series Classification with Hyperparameter Optimization. [paper]
  • [2025/05] R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization. [paper]
  • [2025/05] MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices. [paper]
  • [2025/05] AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection. [paper]
  • [2025/01] Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via LLMs. [paper]
  • [2024/12] TradingAgents: Multi-Agents LLM Financial Trading Framework. [paper]
  • [2024/07] FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making. [paper]
  • [2024/01] Open-TI: Open Traffic Intelligence with Augmented Language Model. [paper]
  • [2024] MAS-LSTM: A Multi-Agent LSTM-Based Approach for Scalable Anomaly Detection in IIoT Networks. [paper]

Memory and Knowledge Agents

  • [2026/06] MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition. [paper]
  • [2026/04] CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting. [paper]
  • [2026/04] An Autonomous Large Language Model-Agent Framework for Transparent and Local Time Series Forecasting. [paper]
  • [2026/02] MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning. [paper]
  • [2025/10] ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination. [paper]
  • [2025/08] FLAIRR-TS: Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series. [paper]
  • [2025/07] ElliottAgents: A Natural Language-Driven Multi-Agent System for Stock Market Analysis and Prediction. [paper]
  • [2025/07] MERIT: Multi-Agent Collaboration for Unsupervised Time Series Representation Learning. [paper]
  • [2025/06] Integrating Traditional Technical Analysis with AI: A Multi-Agent LLM-Based Approach to Stock Market Forecasting. [paper]
  • [2024/11] ChatKG: Visualizing Time-Series Patterns Aided by Intelligent Agents and a Knowledge Graph. [paper]
  • [2024/10] ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration. [paper]
  • [2024/05] SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series. [paper]
  • [2024/08] Agentic Retrieval-Augmented Generation for Time Series Analysis. [paper]
  • [2023/11] FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design. [paper]

World-Model and Data Agents

  • [2026/05] Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding. [paper]
  • [2026/05] AegisTS: A Hierarchical Agent System with Reinforcement Learning for Multivariate Time Series Data Cleaning. [paper]
  • [2026/04] Time Series Augmented Generation for Financial Applications. [paper]
  • [2026/04] Hubble: An LLM-Driven Agentic Framework for Safe, Diverse, and Reproducible Alpha Factor Discovery. [paper]
  • [2026/04] AIVV: Neuro-Symbolic LLM Agent-Integrated Verification and Validation for Trustworthy Autonomous Systems. [paper]
  • [2026/02] AgriWorld: A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents. [paper]
  • [2026/02] Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases. [paper]
  • [2025/10] StockAgent: A Multi-Agent Collaborative Framework for Financial Time Series Prediction. [paper]
  • [2025/09] Hi-DARTS: Hierarchical Dynamically Adapting Reinforcement Trading System. [paper]
  • [2025/04] Multi-Agent Deep Reinforcement Learning for Integrated Demand Forecasting and Inventory Optimization in Sensor-Enabled Retail Supply Chains. [paper]
  • [2025/03] FinArena: A Human-Agent Collaboration Framework for Financial Market Analysis and Forecasting. [paper]
  • [2025/03] BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling. [paper]
  • [2024/07] A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading. [paper]
  • [2024/03] A Multi-Agent Reinforcement Learning Framework for Optimizing Financial Trading Strategies based on TimesNet. [paper]
  • [2024/02] A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist. [paper]
  • [2023/02] Dynamic Ensemble for Probabilistic Time-Series Forecasting via Deep Reinforcement Learning. [paper]

Reliability, Safety and Trustworthiness

  • [2026/05] Foresight Arena: An On-Chain Benchmark for Evaluating AI Forecasting Agents. [paper]
  • [2026/04] Hubble: An LLM-Driven Agentic Framework for Safe, Diverse, and Reproducible Alpha Factor Discovery. [paper]
  • [2026/04] AIVV: Neuro-Symbolic LLM Agent-Integrated Verification and Validation for Trustworthy Autonomous Systems. [paper]
  • [2025/12] Multi-Agent Adversarial Time Series Forecasting. [paper]
  • [2025/10] Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision. [paper]
  • [2025/06] FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making. [paper]
  • [2025/05] MAS-LSTM: A Multi-Agent LSTM-Based Approach for Scalable Anomaly Detection in IIoT Networks. [paper]

👋 Contributing

Pull requests are welcome. Please follow the format:

  • [YYYY/MM] Full paper title. [[paper](URL)]

If the paper has code, data, project pages, or benchmark resources, feel free to add them after the paper link.

📖 Citation

If you find this repository useful, please consider citing the associated survey once available.

@article{hulandscape,
  title={The Landscape of Agentic Time Series Systems: Architectures, Reliability, and Frontiers},
  author={Hu, Yifan and Yang, Jie and Dai, Xilin and Cai, Wanxu and Ding, Kuiye and Li, Yuante and Liu, Qinghua and Ma, Enze and Qu, Zhiyuan and Wang, Yixin and others}
}

📄 License

This repository is released under the MIT License.

⭐️ Star History

Star History Chart