AION: Next-Generation Tasks and Practical Harness for Time Series
Not on the map. Why?
Abstract (arXiv)
Time series research is moving beyond fixed forecasting benchmarks toward realistic tasks that combine prediction, contextual reasoning, tool use, and structured decision support. Most benchmarks are built around clean data and short evaluation loops; agents alone may miss temporal constraints, evidence checks, or review before finalizing outputs. We first formalize next-generation time series tasks as three-component tuples consisting of a task file, a workspace, and a validation interface. We then present AION, a time series harness built from six component groups: agents, skills, rules, memory, evaluation, and protocols. In this harness, we use three design principles: temporal grounding, temporal knowledge-grounded reasoning, and reliability mechanisms such as post-experiment analysis and layered review. A Kaggle Store Sales case study shows that the harness produces more detailed process traces, more artifacts, and more review steps than the same base agent operating in OpenCode direct build mode. Taken together, these results argue for a paradigm shift from fixed tasks to realistic ones under real-world constraints.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 28 of its 43 references that are in the map. First posted on arXiv 24 May 2026.
Builds on
28 of 43 references.
References · 28
- 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
- 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
- 2024Chronos: Learning the Language of Time Seriescited by 759
- 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
- 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
- 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 366
- 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 249
- 2024Foundation Models for Time Series Analysis: A Tutorial and Surveycited by 239
- 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 212
- 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 197
- 2020Deep Learning for Time Series Forecasting: Tutorial and Literature Surveycited by 117
- 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 110
16 more
- 2021Darts: User-Friendly Modern Machine Learning for Time Seriescited by 91
- 2025Time-MQA: Time Series Multi-Task Question Answering with Context Enhancementcited by 82
- 2024Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysiscited by 74
- 2025Moirai 2.0: When Less Is More for Time Series Forecastingcited by 69
- 2026Natural-Language Agent Harnessescited by 61
- 2024Deep Learning for Multivariate Time Series Imputation: A Surveycited by 57
- 2025MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answeringcited by 55
- 2024TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysiscited by 29
- 2025TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Modelscited by 27
- 2024Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Datacited by 17
- 2026TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Taskscited by 17
- 2025TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agentscited by 15
- 2024A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecastingcited by 14
- 2026Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecastingcited by 9
- 2026MMTS-BENCH: A Comprehensive Benchmark for Time Series Understanding and Reasoningcited by 9
- 2025EventTSF: Event-Aware Non-Stationary Time Series Forecastingcited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.