TS-Debate: Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918307828858880 |
|---|---|
| author | Trirat, Patara Kwak, Jin Myung Heo, Jay Lee, Heejun Hwang, Sung Ju |
| author_facet | Trirat, Patara Kwak, Jin Myung Heo, Jay Lee, Heejun Hwang, Sung Ju |
| contents | Recent progress at the intersection of large language models (LLMs) and time series (TS) analysis has revealed both promise and fragility. While LLMs can reason over temporal structure given carefully engineered context, they often struggle with numeric fidelity, modality interference, and principled cross-modal integration. We present TS-Debate, a modality-specialized, collaborative multi-agent debate framework for zero-shot time series reasoning. TS-Debate assigns dedicated expert agents to textual context, visual patterns, and numerical signals, preceded by explicit domain knowledge elicitation, and coordinates their interaction via a structured debate protocol. Reviewer agents evaluate agent claims using a verification-conflict-calibration mechanism, supported by lightweight code execution and numerical lookup for programmatic verification. This architecture preserves modality fidelity, exposes conflicting evidence, and mitigates numeric hallucinations without task-specific fine-tuning. Across 20 tasks spanning three public benchmarks, TS-Debate achieves consistent and significant performance improvements over strong baselines, including standard multimodal debate in which all agents observe all inputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_19151 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TS-Debate: Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning Trirat, Patara Kwak, Jin Myung Heo, Jay Lee, Heejun Hwang, Sung Ju Artificial Intelligence Multiagent Systems Recent progress at the intersection of large language models (LLMs) and time series (TS) analysis has revealed both promise and fragility. While LLMs can reason over temporal structure given carefully engineered context, they often struggle with numeric fidelity, modality interference, and principled cross-modal integration. We present TS-Debate, a modality-specialized, collaborative multi-agent debate framework for zero-shot time series reasoning. TS-Debate assigns dedicated expert agents to textual context, visual patterns, and numerical signals, preceded by explicit domain knowledge elicitation, and coordinates their interaction via a structured debate protocol. Reviewer agents evaluate agent claims using a verification-conflict-calibration mechanism, supported by lightweight code execution and numerical lookup for programmatic verification. This architecture preserves modality fidelity, exposes conflicting evidence, and mitigates numeric hallucinations without task-specific fine-tuning. Across 20 tasks spanning three public benchmarks, TS-Debate achieves consistent and significant performance improvements over strong baselines, including standard multimodal debate in which all agents observe all inputs. |
| title | TS-Debate: Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2601.19151 |