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

arXiv: https://arxiv.org/abs/2609.14142 · HTML: https://mlsanity.com/paper/2609.14142/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Builds on (most cited first, 28 of 28)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Are Language Models Actually Useful for Time Series Forecasting?](https://mlsanity.com/paper/2406.16964/) (2024)
- [DePlot: One-shot visual language reasoning by plot-to-table translation](https://mlsanity.com/paper/2212.10505/) (2022)
- [Language Models Still Struggle to Zero-shot Reason about Time Series](https://mlsanity.com/paper/2404.11757/) (2024)
- [Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement](https://mlsanity.com/paper/2503.01875/) (2025)
- [MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering](https://mlsanity.com/paper/2503.16858/) (2025)
- [TimeSeriesExam: A time series understanding exam](https://mlsanity.com/paper/2410.14752/) (2024)
- [TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation](https://mlsanity.com/paper/2601.13653/) (2026)
- [A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models](https://mlsanity.com/paper/2509.11575/) (2025)
- [TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models](https://mlsanity.com/paper/2601.18744/) (2026)
- [Sycophancy in Vision-Language Models: A Systematic Analysis and an Inference-Time Mitigation Framework](https://mlsanity.com/paper/2408.11261/) (2024)
- [TSAQA: Time Series Analysis Question And Answering Benchmark](https://mlsanity.com/paper/2601.23204/) (2026)
- [Plots Unlock Time-Series Understanding in Multimodal Models](https://mlsanity.com/paper/2410.02637/) (2024)
- [TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering](https://mlsanity.com/paper/2510.07432/) (2025)
- [MMTS-BENCH: A Comprehensive Benchmark for Time Series Understanding and Reasoning](https://mlsanity.com/paper/2602.08588/) (2026)
- [ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Response](https://mlsanity.com/paper/2604.21199/) (2026)
- [TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning](https://mlsanity.com/paper/2606.01498/) (2026)
- [Measuring Agreeableness Bias in Multimodal Models](https://mlsanity.com/paper/2408.09111/) (2024)
- [Seeking SOTA: Time-Series Forecasting Must Adopt Taxonomy-Specific Evaluation to Dispel Illusory Gains](https://mlsanity.com/paper/2603.15506/) (2026)
- [Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning](https://mlsanity.com/paper/2605.19852/) (2026)
- [Representing Time Series as Structured Programs for LLM Reasoning](https://mlsanity.com/paper/2606.12481/) (2026)

## Abstract (arXiv)

Large language models (LLMs) can struggle with time-series question answering (TS-QA), especially when numerical signals are serialized as text and require explicit computation. Tool-augmented approaches improve performance, but existing systems often intertwine language reasoning, computation, and perception, making it difficult to determine which components drive the gains. We present T-SMART, a neurosymbolic framework that separates these roles: a frozen LLM interprets questions and selects operations, deterministic tools perform numerical computation, and structured perception is invoked only when needed. Controlled paired ablations show that deterministic computation provides the dominant benefit, improving accuracy by 31.7 percentage points over direct LLM reasoning on serialized time series, while language understanding and perception offer smaller complementary gains. These results indicate that tool-augmented TS-QA benefits primarily from reliable numerical execution rather than additional language-model reasoning and provide a controlled framework for analyzing component contributions in neurosymbolic time-series systems.