Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team

Open paper
Benchmark Model Rank Results
code-generation-on-livecodebenchXolver#1Acc: 91.6
gsm8k-on-gsm8kXolver#2Accuracy: 98.1
mathematical-reasoning-on-aime24Xolver#4Acc: 94.4

Rank counts only results with a code link.