3 papers
cs.LG2026
Two Heads Are Better Than One: Aggregating Weaker LLMs for Better Forecasts
Cheng Peng, Ruixi Luo, Zhi Chen +1
Large language models (LLMs) are increasingly used to forecast real-world events, but access to the strongest individual forecaster may be costly or otherwise constrained. We study…
cs.LG2026
Prior-Agnostic Robust Forecast Aggregation
Zhi Chen, Cheng Peng, Wei Tang
Robust forecast aggregation combines the predictions of multiple information sources to perform well in the worst case across all possible information structures. Previous work lar…
cs.GT2024
Mechanism Design for Congested Facility Location
Cheng Peng, Houyu Zhou
This paper investigates mechanism design for congested facility location problems, where agents are partitioned into groups with conflicting interests (e.g., competition for bookin…