List your company

Multi-hop Question Answering on HotpotQA (Evidence score)

33.2Evidence ScoreEVE-Agent
19.36822.95926.5530.141May 21, 2026

Evaluation results

MethodLinks
EVE-AgentSearch=true2026.0533.2
Initial (no search)Search=false2026.0524.7
Dr. ZeroSearch=true2026.0520.9
Initial (search)Search=true2026.0519.9