← Back to the wire

Peer-Predictive Self-Training for Language Model Reasoning

AnnouncementResearchJul 10, 2026

Shi Feng and four co-authors submitted the paper "Peer-Predictive Self-Training for Language Model Reasoning" to arXiv on April 14, 2026. The paper was revised twice, with version three posted on July 9, 2026. It is categorized under cs.CL, cs.AI, and cs.GT. The submission includes a 585 KB PDF and is assigned a DOI via DataCite.

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01medPRIMARY
Shi FengPerson
Canonical: https://arxiv.org/abs/2604.13356