RLVR Makes Agents Win More, but Not Necessarily Reason Better

Publication
NeurIPS 2026 Workshop IAEval

Accepted at NeurIPS 2026 Workshop IAEval.

Wenhao Lu¹, Jae Hee Lee¹, Josua Spisak¹, Xufeng Zhao, Stefan Wermter¹

¹ Universität Hamburg

Read the paper on OpenReview.

Previous