Research2026-05-06
Poly-EPO: Training Exploratory Reasoning Models
Source: Arxiv CS.AI
arXiv:2604.17654v3 Announce Type: replace Abstract: Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and scale performance with test-time compute. In this paper, we present a framework for post-training...
arxivpapersreasoning