Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents
Mingyang, Chen, Yida +4
Financial LLM agents are often evaluated by comparing their end-to-end returns with those of a baseline and testing the paired difference against zero. This measures whether deploy…
cs.AI2026
EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts
Yiming Lu, Sihang Zeng, Zhengxu Tang +3
Epidemic LLM forecasters are usually trained and evaluated as static supervised models, whereas operational pandemic forecasting is a streaming process in which labels arrive after…