Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning

Jing Xie; Haochen Yuan; Yunbo Wang

cs.AIOct 4, 2026

Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning

Authors: Jing Xie, Haochen Yuan, Yunbo Wang

Organizations: MoE Key Lab of Artificial Intelligence, Institute of AI, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China

Abstract

Time-series question answering (TSQA) requires grounding linguistic queries and diverse answer formats in complex numerical observations. However, existing methods heavily overfit to specific datasets and struggle to generalize when input series, question contexts, and answer requirements shift simultaneously. To address this challenge, we propose TSHarness, an agentic framework that establishes a decoupled workflow for cross-dataset zero-shot TSQA. At its core, TSHarness divides and conquers numerical perception and contextual reasoning via a structured Time-Series Perception State (TPS). Guided by a reusable memory of analytical knowledge, a learned Tool Selector adaptively invokes numerical tools to extract salient statistical and temporal features into the TPS. The answering agent then performs semantic reasoning over the TPS to generate target outputs, triggering iterative re-perception through the feedback loop when evidence is deemed insufficient. By separating numerical feature extraction from question-specific reasoning, TSHarness eliminates the need for target-side training or answer feedback, providing a generalizable, cost-efficient foundation for zero-shot TSQA.

Figures & tables

Figure 1: Motivation and overview of TSHarness . (a) Specialized TSQA models exhibit uneven cross-dataset performance as time-series inputs, question context, and answer requirements change. (b) TSHarness decouples perception from answering through a unified TPS representation.

Figure 2: Workflow of TSHarness . Guided by procedural memory, the Perceiver populates the TPS with grounded measurements, refined by the Tool Selector . The Answerer interprets the accumulated evidence alongside the question, actively initiating an iterative feedback loop to request further evidence. Source-developed resources are completely frozen for zero-shot transfer.

Specialized Time-Series Models
Method	Base LLM	TSRBench	Target Benchmarks
Method	Base LLM	TSRBench	Time-MQA	ChatTime	CaTSBench	TSAQA	TimeOmni
ChatTime	LLaMA-2-7B	19.95	28.79	88.77	9.63	11.36	19.66
Time-MQA	Qwen2.5-7B	30.47	54.98	37.07	26.05	45.07	32.04
	Llama3-8B	20.95	54.58	33.34	51.27	40.30	33.25
	Mistral-7B	36.27	55.91	35.47	47.79	42.61	31.55

Table 1: Cross-dataset zero-shot TSQA evaluation (Accuracy, %). TSHarness is developed exclusively on the source benchmark (TSRBench) and deployed for zero-shot evaluation on five unseen target benchmarks. TSHarness ⋆ incorporates the learned RL-based Tool Selector . Shaded orange cells indicate in-domain training for ChatTime and Time-MQA, directly contrasting with the strictly zero-shot deployment of TSHarness. The best results within each backbone group are highlighted in bold ; second-best results within the open-weight agentic group are underlined .

Variant	In-domain	Zero-shot
Variant	TSRBench	Time-MQA	ChatTime	CaTSBench	TSAQA	TimeOmni
Full TSHarness	62.62	65.78	96.10	96.60	59.47	55.10
w/o Tool	46.12	60.92	63.59	91.02	47.33	52.43
w/o Memory	60.44	68.45	96.12	96.12	58.74	54.37
w/o Tool + Memory	42.48	60.92	63.35	91.02	48.79	52.91

Table 2: Ablation study of core components across in-domain and zero-shot target datasets (Accuracy, %). We evaluate variants of TSHarness by disabling numerical tools and procedural memory using Qwen3.8-27B as the backbone LLM. Numerical tool orchestration proves indispensable for both in-domain and transfer accuracy. Best results are shown in bold .

Figure 3: Analysis of answer refinement and active re-perception dynamics. (a) Transitions from initial pre-TPS hypotheses to final verified answers across benchmarks. Diamond markers represent net accuracy changes in percentage points. (b) Evidence fulfillment rates among queries triggering the re-perception loop (%). Fulfilled and Incomplete indicate acquired evidence with full and partial request coverage, respectively. Gray indicates that no additional evidence was obtained through re-perception.

Panel of Figure 4 — Figure 4: Deployment choices for learned tool selection. (a) Mean accuracy and total tool-execution ratios across all five target benchmarks (matched Controller = 100%). All five points are measured configurations; lines connect adjacent points. (b) The separate TSRBench cumulative distribution under efficiency-oriented deployment.

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Benchmark	Time series and context	QA capabilities	Answer forms
TSRBench	Single or multiple series with domain context	Perception, reasoning, prediction, and decision-making	Multiple choice
ChatTime	Synthetic series of varying lengths	Trend, volatility, seasonality, and outlier recognition	Multiple choice
Time-MQA	Real-world series with contextual descriptions	Statistical properties, patterns, anomalies, and structural changes	True/false; multiple choice
CaTSBench	Series paired with textual descriptions	Caption and series retrieval, description consistency, and pairwise comparison	True/false; multiple choice
TSAQA	Cross-domain series and temporal patches	Classification, anomalies, characterization, comparison, transformations, and temporal relationships	True/false; multiple choice; ordered labels
TimeOmni-1	Series with event and domain context	Causality discovery, scenario understanding, and decision-making	Multiple choice

Appendix

Table 3: Time-series inputs, QA capabilities, and answer forms covered by the evaluation.

Tool family	Computation	Returned information
Statistics and value profile	Summary statistics, quantiles, extrema, and adjacent differences	Values, extrema locations, largest rise and drop
Trend	Linear fit on normalized time; slope scaled by series standard deviation	Direction, strength, normalized slope
Seasonality	Autocorrelation and spectral analysis	Period and periodicity strength
Volatility	Early/late standard deviations and their ratio	Variability level and change
Anomalies and change points	Median-deviation and local-residual scores; mean and variance changes across windows	Event positions, types, directions, and scores
Cross-series	Contemporaneous and lagged correlations	Channel pairs, correlations, and strongest lag

Appendix

Table 4: Representative tools used to construct TPS fields. Measurements and temporal locations are computed from the input observations.

Component	Contents and role
Statistics $\mathcal{S}_{j}$	Distributions and value profiles, including means, standard deviations, extrema, and their locations.
Temporal features $\mathcal{F}_{j}$	Trends, periodicity, volatility, segments, changes, anomalies, and cross-series relationships.
Task extensions $\mathcal{D}_{r}$	Named analyses that add evidence required by the question beyond the common fields.

Appendix

Table 5: TPS field groups and their analytical roles.

LLM role	Inputs	Outputs
Perception planning	Bounded series view, question context, eligible tools, Memory summaries, and execution limits.	Tool names and arguments; a Memory query and retrieval choices.
TPS synthesis	Tool evidence, retrieved Memory entries, series identity, channels, length, and question context.	Measured fields to include and a factual summary $h_{j}$ describing the series.
Initial hypothesis	Raw numerical series, question context, answer choices, and output requirements.	A parsed candidate answer and its generated response, stored as an initial hypothesis in a named extension.
Initial extension planning	Core findings, question, evidence requirements, and available tools and Memory.	Analysis requests specifying operations, arguments, and required evidence.
Answerer	Question and answer requirements, TPS with the provisional hypothesis, evidence coverage, available operations, and request budget.	A task-formatted prediction with evidence references, or a request specifying the additional evidence needed.

Appendix

Table 6: Inputs and outputs of the LLM roles connecting Perception, TPS, and the Answerer. Tool execution and numerical field assignment are performed by the harness between calls.

Setting	Value
Source training / development questions	96 / 48
Training passes	1
Rollouts per question / questions per batch	4 / 4
Text-hash dimension / scalar features	$128$ per block / $12$
Policy network	$396\rightarrow 64\rightarrow 1$ , $\tanh$
Perceiver prior: proposed / other tools	$0.8$ / $0.2$

Appendix

Table 7: Configuration of the learned Tool Selector in the matched base-tool experiment. The LLM and source-developed Tool and Memory resources remain fixed during policy optimization.

TSRBench
	Qwen3.8-27B			GPT-5.6-sol
Capability / task	Zero-shot	TSHarness	$\Delta$	Zero-shot	TSHarness	$\Delta$
Decision-making	25.40	50.79	+25.40	44.44	53.97	+9.52
Perception	68.57	71.43	+2.86	82.86	87.14	+4.29
Prediction	50.00	59.26	+9.26	61.11	57.41	-3.70
Reasoning	36.26	65.50	+29.24	71.93	81.87	+9.94

Appendix

Table 8: Accuracy (%) across source capabilities and target question categories, using the matched same-backbone predictions underlying Table 1 . TSRBench is grouped by capability, ChatTime and TimeOmni-1 by task, and Time-MQA by answer format.

\Delta

is TSHarness minus zero-shot in percentage points; bold indicates the higher score within each pair.

CaTSBench
	Qwen3.8-27B			GPT-5.6-sol
Capability / task	Zero-shot	TSHarness	$\Delta$	Zero-shot	TSHarness	$\Delta$
Caption retrieval: cross-domain	100.00	100.00	0.00	100.00	100.00	0.00
Caption retrieval: perturbed	100.00	100.00	0.00	100.00	100.00	0.00
Caption retrieval: same-domain	100.00	100.00	0.00	100.00	100.00	0.00
Paraphrase consistency	100.00	100.00	0.00	100.00	100.00	0.00

Appendix

Table 9: Task-level accuracy (%) on CaTSBench and TSAQA. All evaluated task categories are included. Both conditions use the same questions within each benchmark. Bold and

\Delta

follow Table 8 .

Qwen3.8-27B
Benchmark	Initial Accuracy (%)	Final Accuracy (%)	$\Delta$ (pp)	Revisit (%)
TSRBench	44.17	62.62	+18.45	0.00
Time-MQA	59.47	65.78	+6.31	0.24
ChatTime	74.30	96.10	+21.80	0.00
CaTSBench	93.45	96.60	+3.16	0.00
TSAQA	52.18	59.47	+7.28	0.24

Appendix

Table 10: Accuracy before and after TPS evidence integration within the same harness trajectory. Initial Accuracy scores the recorded pre-TPS hypothesis; Final Accuracy scores the final prediction. Both are reported in percent.

\Delta

is the net accuracy change in percentage points (pp), computed before rounding. Revisit gives the percentage of questions with an accepted evidence request. The initial hypothesis is a within-trajectory reference, distinct from the independently evaluated zero-shot baseline. Time-MQA uses the same subset as Table 8 .

Figure 5: Tool execution breakdown for the matched Controller and RL conditions. (a) Mean executions at each stage. (b) Mean executions by tool across all stages, ordered by Controller usage; the seven question-specific analytical and verification tools are pooled as Question tools. Both panels use executions per question; requested extensions average zero for Controller and less than 0.01 for RL.

Figure 6: Execution–accuracy trade-off across TSRBench capabilities. (a) Mean tool executions per question across all stages. (b) Accuracy on the same questions. The selector reduces execution demand in every group while preserving accuracy in decision-making and reasoning. Colors identify the same policies in both panels.

Benchmark	Accuracy-oriented	Efficiency-oriented
Time-MQA	65.78	63.67
ChatTime	96.12	94.90
CaTSBench	96.84	93.69
TSAQA	59.71	57.04
TimeOmni	55.10	53.40
Five-target mean	74.71	72.54

Appendix

Table 11: Target accuracy (%) for the two deployment regimes. Accuracy-oriented values correspond to TSHarness ⋆ in Table 1 . Both regimes reuse the same learned checkpoint.

Configuration	Accuracy (%)	Relative cost (%)	Tool savings (%)
Efficiency-oriented	72.54	43.61	56.39
Intermediate 1	73.62	57.43	42.57
Intermediate 2	74.10	74.28	25.72
Intermediate 3	74.55	85.23	14.77
Accuracy-oriented	74.71	98.24	1.76

Appendix

Table 12: Measured accuracy–cost trade-offs across all five target benchmarks, plotted in Figure 4 (a). Tool savings equal 100% minus relative execution cost; each cost is normalized to its matched Controller.

Time Series QA

Time-series question answering connects natural-language questions to evidence and reasoning over sequential data.

See all 32 papers

Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering
Jun 17, 2026Yafeng Wu, Huu Hiep Nguyen, Thin Nguyen +1Time Series Reasoning Time Series QA
Deakin University
T-SMART: Mechanism-Level Attribution for Tool-Augmented Time-Series Question Answering
Sep 12, 2026Ivan Delgado, Himansi Gupta, Bishal Khatri +4Time Series QA Time Series Reasoning
University of California, San Diego, CA, USA · West Virginia University, Morgantown, WV, USA
PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
Feb 26, 2026Junkai Lu, Peng Chen, Xingjian Wu +4Time Series Reasoning Time Series QA
East China Normal University, Shanghai, China · Aalborg University, Aalborg, Denmark

Jun 17, 2026J/K move · Enter open · S save

Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering

Yafeng Wu, Huu Hiep Nguyen, Thin Nguyen, Hung Le

Deakin University

Time Series Reasoning Time Series QA Question Answering Time Series Representation Learning

Open paper AskPDF arXiv

Recent advances in large language models (LLMs) have given rise to time-series question answering (TSQA), which formulates time-series analysis as natural-language question answering. However, directly feeding raw numerical series into LLMs suffers from a tokenization bottleneck: Byte Pair Encoding fragments continuous values into unstable tokens whose embeddings lack meaningful metric structure, resulting in the loss of magnitude, scale, and trend information. Prior methods use patch-based encoders that split the series into fixed windows, locking in one granularity that breaks patterns and hides exact timesteps, through a separate module that rarely transfers across datasets with different lengths or sampling rates. To address this challenge, we propose CADE (Contrastive Alignment with Direct Embedding), a novel framework for TSQA built upon two key components: direct timestep embedding and semantic alignment. The proposed framework maps each timestep directly into the LLM embedding space through a point-wise linear encoder and MLP projector, preserving exact index-level access while eliminating the need for patching and padding. To further bridge the semantic gap between time-series and language representations, we introduce a novel one-directional supervised contrastive loss that aligns time-series embeddings with frozen class-name text anchors. Experimental results on the public Time-MQA benchmark demonstrate that our framework consistently improves performance across six TSQA tasks, outperforming both open-source and proprietary LLM baselines.

Abstract

Time Series QA

Explore similar work

Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering

T-SMART: Mechanism-Level Attribution for Tool-Augmented Time-Series Question Answering

PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering