Unverified50% confidenceFactExact time
Several recent empirical works have questioned the actual utility of first-order momentum in reinforcement learning with verifiable rewards (RLVR).
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe optimization landscape of RLVR is fundamentally different from supervised learning: the reward signal is sparse and discrete, gradient estimates come from sampled responses, and the variance is significantly higher than in traditional training settings.80% similarVerifiedRLVR is Reinforcement Learning with Verifiable Rewards, which guides model optimization by designing verifiable reward signals.78% similarUnverified近期研究表明RL（尤其是RLVR）并没有给模型注入大量新知识，而更像是激发和对齐预训练阶段已具备的能力77% similarUnverifiedThe researchers believe the issue is most likely a systemic byproduct of current mainstream reinforcement learning training paradigms (such as RLHF and RLEF), rather than an engineering error on the part of any individual vendor.76% similarUnverified强化学习训练比监督学习更不稳定，将NVFP4激进量化引入RL训练会进一步放大固有不稳定性75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032929API
curl https://kongchang.com/api/v1/knowledge/claims/1032929MCP
get_claim(id=1032929)