#verifiablerewards — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #verifiablerewards, aggregated by home.social.
-
2025 saw significant advancements in #LLMs, with #ReinforcementLearning from #VerifiableRewards (#RLVR) emerging as a key stage in training, leading to improved #reasoning capabilities. The industry also began to understand the unique “jagged” intelligence of LLMs, excelling in specific domains but lacking generalisation. https://karpathy.bearblog.dev/year-in-review-2025/?eicker.news #tech #media #news
-
ReasoningGym: Reasoning Environments for RL with Verifiable Rewards
https://arxiv.org/abs/2505.24760
#HackerNews #ReasoningGym #ReinforcementLearning #VerifiableRewards #AIResearch #MachineLearning