TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning

• URL: http://arxiv.org/abs/2605.10038v1
• Date: Mon, 11 May 2026 06:09:17 GMT
• Title: TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning
• Abstract summary: Time series analysis underpins forecasting, monitoring, and decision making in domains such as finance and weather.<n>We present TimeClaw, an exploratory execution learning framework that turns exploratory execution into reusable hierarchical distilled experience.
• Score: 22.232550112727267
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time series analysis underpins forecasting, monitoring, and decision making in domains such as finance and weather, where solving a task often requires both numerical accuracy and contextual reasoning. Recent progress has moved from specialized neural predictors to approaches built on LLMs and foundation models that can reason over time series inputs and use external tools. However, most such systems remain execution-centric: they focus on solving the current instance but learn little from exploratory execution. This is especially limiting in verifiable numeric settings, where multiple candidate executions and tool-use procedures may all be task-valid yet differ sharply in quantitative quality, and where early success can trigger tool-prior collapse that suppresses further exploration. To address this limitation, we present TimeClaw, an exploratory execution learning framework that turns exploratory execution into reusable hierarchical distilled experience through a four-stage loop: Explore, Compare, Distill, and Reinject. TimeClaw combines metric-supervised exploratory execution learning, task-aware tool dropout, and hierarchical distilled experience for inference-time reinjection, while keeping the base model frozen and avoiding online test-time adaptation. In an MTBench-aligned evaluation with 17 tasks that span finance and weather prediction and reasoning tasks, TimeClaw delivers consistent gains over the baselines. These results suggest that, for scientific systems, the bottleneck is not only execution-time capability, but how exploratory experience is compared, distilled, and reused.

Related papers

• Harnessing Generalist Agents for Contextualized Time Series [67.28481985993467]
  Time series are often embedded in rich contexts that are essential for holistic modeling.<n>In this work, we introduce TimeClaw, an agentic harness framework for time series.<n>TimeClaw integrates executable temporal tools for grounded and auditable analysis, experience-driven capability evolution for creating reusable analytical routines, and episodic multimodal memory for retrieving relevant reasoning traces.
  arXiv  Detail & Related papers  (2026-06-03T20:20:34Z)
• AION: Next-Generation Tasks and Practical Harness for Time Series [45.09526710303026]
  We first formalize next-generation time series tasks as three-components consisting of a task file, a workspace, and a validation interface.<n>We then present AION, a time series harness built from six component groups: agents, skills, rules, memory, evaluation, and protocols.<n>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.
  arXiv  Detail & Related papers  (2026-05-24T12:42:12Z)
• IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents [56.77101184011525]
  Large language model (LLM)-based agents solve complex tasks by leveraging multi-step reasoning with iterative tool calls and environment interactions.<n>Despite the prevalence of idle time in most agentic scenarios, existing works treat it as an unavoidable overhead.<n>We introduce IdleSpec, a scalable and generic inference approach that leverages idle-time computation to improve agent performance.
  arXiv  Detail & Related papers  (2026-05-21T08:25:17Z)
• Can We Predict Before Executing Machine Learning Agents? [74.39460101251792]
  We formalize the task of Data-centric Solution Preference and construct a comprehensive corpus of 18,438 pairwise comparisons.<n>We demonstrate that LLMs exhibit significant predictive capabilities when primed with a Verified Data Analysis Report.<n>We instantiate this framework in FOREAGENT, an agent that employs a Predict-then-Verify loop, achieving a 6x acceleration in convergence while surpassing execution-based baselines by +6%.
  arXiv  Detail & Related papers  (2026-01-09T16:44:17Z)
• Still Competitive: Revisiting Recurrent Models for Irregular Time Series Prediction [0.9883261192383609]
  We propose and study GRUwE: Gated Recurrent Unit with Exponential basis functions.<n>GRUwE supports both regression-based and event-based predictions in continuous time.
  arXiv  Detail & Related papers  (2025-10-17T19:04:16Z)
• Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis [19.649769354503658]
  We introduce TS-Reasoner, a Domain-Oriented Time Series Agent that integrates natural language reasoning with precise numerical execution.<n>We evaluate its capabilities through two axes: basic time series understanding and complex multi-step inference.
  arXiv  Detail & Related papers  (2024-10-05T06:04:19Z)
• TSI-Bench: Benchmarking Time Series Imputation [52.27004336123575]
  TSI-Bench is a comprehensive benchmark suite for time series imputation utilizing deep learning techniques. The TSI-Bench pipeline standardizes experimental settings to enable fair evaluation of imputation algorithms. TSI-Bench innovatively provides a systematic paradigm to tailor time series forecasting algorithms for imputation purposes.
  arXiv  Detail & Related papers  (2024-06-18T16:07:33Z)
• Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values [67.76168547245237]
  We introduce a novel framework called GST-Pro, which utilizes a graphtemporal process and anomaly scorer to detect anomalies. Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-11T10:10:16Z)
• Deep Ensembles Meets Quantile Regression: Uncertainty-aware Imputation for Time Series [45.76310830281876]
  We propose Quantile Sub-Ensembles, a novel method to estimate uncertainty with ensemble of quantile-regression-based task networks. Our method not only produces accurate imputations that is robust to high missing rates, but also is computationally efficient due to the fast training of its non-generative model.
  arXiv  Detail & Related papers  (2023-12-03T05:52:30Z)
• OneShotSTL: One-Shot Seasonal-Trend Decomposition For Online Time Series Anomaly Detection And Forecasting [21.841836315237376]
  Seasonal-trend decomposition is one of the most fundamental concepts in time series analysis. OneShotSTL is an efficient and accurate algorithm that can decompose time series online with an update time complexity of O(1).
  arXiv  Detail & Related papers  (2023-04-04T03:35:14Z)
• Temporal Dependencies in Feature Importance for Time Series Predictions [4.082348823209183]
  We propose WinIT, a framework for evaluating feature importance in time series prediction settings. We demonstrate how the solution improves the appropriate attribution of features within time steps. WinIT achieves 2.47x better performance than FIT and other feature importance methods on real-world clinical MIMIC-mortality task.
  arXiv  Detail & Related papers  (2021-07-29T20:31:03Z)
• Temporally Correlated Task Scheduling for Sequence Learning [143.70523777803723]
  In many applications, a sequence learning task is usually associated with multiple temporally correlated auxiliary tasks. We introduce a learnable scheduler to sequence learning, which can adaptively select auxiliary tasks for training. Our method significantly improves the performance of simultaneous machine translation and stock trend forecasting.
  arXiv  Detail & Related papers  (2020-07-10T10:28:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.