CastWorld: Benchmarking Context-Aware Agentic Time Series Forecasting Beyond Predictive Accuracy
cs.LG, cs.AI
Submitted: 2026-11-11
Updated: 2026-11-13
Code: https://github.com/Forever-Pan/CastWorld
Terminology
Sources
- TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents
- Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting
- TimeCopilot
- TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning
- GIFT-Eval-CTX: A Benchmark For Contextual Forecasting Model Evaluation
- Forecast Workflow Bench: Evaluating Language-Model Decisions with Budgeted Forecast Tools
- CastFlow: Bridging Evidence Acquisition and Accurate Prediction in Agentic Time Series Forecasting
- Dr-CiK: A Benchmark testing Deep Research for Context-Aided Forecasting
- Learning Agentic Time Series Forecasting via Trajectory Distillation and Memory-Based Reinforcement Learning
- CastFSR: Fast--Slow--Reflect Agentic Reasoning for Context-Aware Time Series Forecasting
- PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature
- When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
- TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis