2 papers
cs.AI2026
TimeSeek: Temporal Reliability of Agentic Forecasters
Hamza Mostafa, Om Shastri, Dennis Lee
We introduce TimeSeek, a benchmark for studying how the reliability of agentic LLM forecasters changes over a prediction market's lifecycle. We evaluate 10 frontier models on 150 C…
cs.CE2026
Factor Dimensionality and the Bias-Variance Tradeoff in Diffusion Portfolio Models
Avi Bagchi, Michael Tesfaye, Om Shastri
In this paper, we implement and evaluate a conditional diffusion model for asset return prediction and portfolio construction on large-scale equity data. Our method models the full…