Story
arxiv_llm_reliability ยท Oct 19, 2026 ยท paper
Source brief
FinHopper: A Progressive Multi-Hop Benchmark for Complex Financial Agents with Step-wise Evaluation
arxiv.orgOct 19, 2026
original source linked
In brief
Financial agents are expected to answer factual investment queries through open search, but financial multi-hop retrieval differs from general multi-hop QA in a crucial way: each intermediate answer is an exact typed...
Feed lens
agentevaluation