A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models

• URL: http://arxiv.org/abs/2509.11575v2
• Date: Sun, 02 Nov 2025 22:14:09 GMT
• Title: A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models
• Authors: Ching Chang, Yidan Shi, Defu Cao, Wei Yang, Jeehyun Hwang, Haixin Wang, Jiacheng Pang, Wei Wang, Yan Liu, Wen-Chih Peng, Tien-Fu Chen,
• Abstract summary: Time series reasoning treats time as a first-class axis and incorporates intermediate evidence directly into the answer.<n>This survey defines the problem and organizes the literature by reasoning topology with three families: direct reasoning in one step, linear chain reasoning with explicit intermediates, and branch-structured reasoning.
• Score: 22.683448537572897
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time series reasoning treats time as a first-class axis and incorporates intermediate evidence directly into the answer. This survey defines the problem and organizes the literature by reasoning topology with three families: direct reasoning in one step, linear chain reasoning with explicit intermediates, and branch-structured reasoning that explores, revises, and aggregates. The topology is crossed with the main objectives of the field, including traditional time series analysis, explanation and understanding, causal inference and decision making, and time series generation, while a compact tag set spans these axes and captures decomposition and verification, ensembling, tool use, knowledge access, multimodality, agent loops, and LLM alignment regimes. Methods and systems are reviewed across domains, showing what each topology enables and where it breaks down in faithfulness or robustness, along with curated datasets, benchmarks, and resources that support study and deployment (https://github.com/blacksnail789521/Time-Series-Reasoning-Survey). Evaluation practices that keep evidence visible and temporally aligned are highlighted, and guidance is distilled on matching topology to uncertainty, grounding with observable artifacts, planning for shift and streaming, and treating cost and latency as design budgets. We emphasize that reasoning structures must balance capacity for grounding and self-correction against computational cost and reproducibility, while future progress will likely depend on benchmarks that tie reasoning quality to utility and on closed-loop testbeds that trade off cost and risk under shift-aware, streaming, and long-horizon settings. Taken together, these directions mark a shift from narrow accuracy toward reliability at scale, enabling systems that not only analyze but also understand, explain, and act on dynamic worlds with traceable evidence and credible outcomes.

Related papers

• Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure [58.89643769707751]
  We study latent chain-of-thought as a manipulable causal process in representation space.<n>We find that latent-step budgets behave less like homogeneous extra depth and more like staged functionality with non-local routing.<n>These results motivate mode-conditional and stability-aware analyses as more reliable tools for interpreting and improving latent reasoning systems.
  arXiv  Detail & Related papers  (2026-02-09T15:25:12Z)
• Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagation [5.191980417814362]
  LLM agents excel when environments are mostly static and the needed information fits in a model's context window.<n>ReAct-style agents are especially brittle in this regime.<n>We propose EoG, a framework in which an LLM performs bounded local evidence mining and labeling (cause vs symptom) while a deterministic controller manages, state, and belief propagation to compute a minimal explanatory frontier.
  arXiv  Detail & Related papers  (2026-01-25T17:27:19Z)
• STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning [16.11676643415448]
  patio-temporal reasoning in time series involves the explicit synthesis of temporal dynamics, spatial dependencies, and textual context.<n>This capability is vital for high-stakes decision-making in systems such as traffic networks, power grids, and disease propagation.<n>To address the gap, we introduce ST-Bench, a benchmark consisting of four core tasks, including etiological reasoning, entity identification, correlation reasoning, and in-context forecasting.<n>We then propose STReasoner, which empowers LLM to integrate time series, graph structure, and text for explicit reasoning.
  arXiv  Detail & Related papers  (2026-01-06T18:46:12Z)
• Explainable Artificial Intelligence for Economic Time Series: A Comprehensive Review and a Systematic Taxonomy of Methods and Concepts [0.0]
  This survey reviews and organizes the growing literature on XAI for economic time series.<n>We propose a taxonomy that classifies methods by (i) explanation mechanism.<n>We synthesize time-series-specific adaptations that reduce lag fragmentation and computational cost.
  arXiv  Detail & Related papers  (2025-12-14T00:45:30Z)
• TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis [23.92333631221749]
  We introduce TelecomTS, a large-scale observability dataset derived from a 5G telecommunications network.<n>We show that existing approaches struggle with the abrupt, noisy, and high-variance dynamics of observability data.
  arXiv  Detail & Related papers  (2025-10-07T15:54:34Z)
• Learning to Route: A Rule-Driven Agent Framework for Hybrid-Source Retrieval-Augmented Generation [55.47971671635531]
  Large Language Models (LLMs) have shown remarkable performance on general Question Answering (QA)<n>Retrieval-Augmented Generation (RAG) addresses this limitation by enriching LLMs with external knowledge.<n>Existing systems primarily rely on unstructured documents, while largely overlooking relational databases.
  arXiv  Detail & Related papers  (2025-09-30T22:19:44Z)
• Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies [0.0]
  This survey aims to categorizing visual reasoning into five major types (relational, symbolic, temporal, causal, and commonsense)<n>We review evaluation protocols designed to assess functional correctness, structural consistency, and causal validity, and critically analyze their limitations in terms of generalizability, explanatory power.
  arXiv  Detail & Related papers  (2025-08-14T10:53:35Z)
• Topology-Aware Conformal Prediction for Stream Networks [54.505880918607296]
  We propose Spatio-Temporal Adaptive Conformal Inference (textttCISTA), a novel framework that integrates network topology and temporal dynamics into the conformal prediction framework.<n>Our results show that textttCISTA effectively balances prediction efficiency and coverage, outperforming existing conformal prediction methods for stream networks.
  arXiv  Detail & Related papers  (2025-03-06T21:21:15Z)
• On the Identification of Temporally Causal Representation with Instantaneous Dependence [50.14432597910128]
  Temporally causal representation learning aims to identify the latent causal process from time series observations. Most methods require the assumption that the latent causal processes do not have instantaneous relations. We propose an textbfIDentification framework for instantanetextbfOus textbfLatent dynamics.
  arXiv  Detail & Related papers  (2024-05-24T08:08:05Z)
• Causal Temporal Regime Structure Learning [49.77103348208835]
  We present CASTOR, a novel method that concurrently learns the Directed Acyclic Graph (DAG) for each regime.<n>We establish the identifiability of the regimes and DAGs within our framework.<n>Experiments show that CASTOR consistently outperforms existing causal discovery models.
  arXiv  Detail & Related papers  (2023-11-02T17:26:49Z)
• Generic Temporal Reasoning with Differential Analysis and Explanation [61.96034987217583]
  We introduce a novel task named TODAY that bridges the gap with temporal differential analysis. TODAY evaluates whether systems can correctly understand the effect of incremental changes. We show that TODAY's supervision style and explanation annotations can be used in joint learning.
  arXiv  Detail & Related papers  (2022-12-20T17:40:03Z)
• Path Signature Area-Based Causal Discovery in Coupled Time Series [0.0]
  We propose the application of confidence sequences to analyze the significance of the magnitude of the signed area between two variables. This approach provides a new way to define the confidence of a causal link existing between two time series.
  arXiv  Detail & Related papers  (2021-10-23T19:57:22Z)
• Data Generating Process to Evaluate Causal Discovery Techniques for Time Series Data [1.5293427903448025]
  We propose a framework for developing, evaluating, and benchmarking time series causal discovery methods. The framework can be used to fine tune novel methods on vast amounts of data, without "overfitting" them to a benchmark. Using our framework, we evaluate prominent time series causal discovery methods and demonstrate a notable degradation in performance when their assumptions are invalidated.
  arXiv  Detail & Related papers  (2021-04-16T11:38:29Z)
• Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series [21.11327248500246]
  We propose a deep ensemble approach for explaining deep learning-based time series predictions. A measure of uncertainty in the relevance scores is computed by taking the standard deviation across the relevance scores produced by each model. Results demonstrate that the proposed ensemble is more accurate in locating relevant time steps.
  arXiv  Detail & Related papers  (2020-10-16T10:32:06Z)
• Supporting Optimal Phase Space Reconstructions Using Neural Network Architecture for Time Series Modeling [68.8204255655161]
  We propose an artificial neural network with a mechanism to implicitly learn the phase spaces properties. Our approach is either as competitive as or better than most state-of-the-art strategies.
  arXiv  Detail & Related papers  (2020-06-19T21:04:47Z)

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.