TS-Debate: Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning
This addresses the challenge of numeric fidelity and modality interference in time series analysis for users relying on large language models, representing a novel method for a known bottleneck rather than a foundational advancement.
The paper tackled the problem of zero-shot time series reasoning by introducing TS-Debate, a multimodal collaborative debate framework that assigns expert agents to different modalities and uses a structured protocol to coordinate their interaction, achieving consistent and significant performance improvements over strong baselines across 20 tasks on three public benchmarks.
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.