Preserving Reasoning Diversity in Reinforcement Learning with Verifiable Rewards via Adaptive Replay
Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning capabilities of large language models, but often reduces the diversity of their reasoning behaviors.
By Wen-Zhi Li, Sainyam Galhotra, Claire CardiearXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Oct 21, 2026.
Comments
Sign in to join the discussion.