Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning
cs.AI, cs.MA
Submitted: 2026-01-27
Updated: 2026-08-28
Comments: EMNLP 2026 (Main), Project Page: https://deepauto-ai.github.io/ts-debate/
Code: https://github.com/Graph-and-Geometric-Learning/MTBench
Project page: https://deepauto-ai.github.io/ts-debate
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models
- MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering
- Achieving Time Series Reasoning Requires Rethinking Model Design, Tasks Formulation, and Evaluation
- How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook
- Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data
- Universal Time-Series Representation Learning: A Survey
- TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation
- TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning
- Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection