Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning
cs.AI
Submitted: 2026-10-04
Updated: 2026-10-04
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning
- TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering
- Harnessing Generalist Agents for Contextualized Time Series
- TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering
- Proximal Policy Optimization Algorithms
- ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
- MMTS-BENCH: A Comprehensive Benchmark for Time Series Understanding and Reasoning
- AION: Next-Generation Tasks and Practical Harness for Time Series
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
- Agents' Last Exam
- 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