AI RESEARCH
SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions
arXiv CS.CL
•
ArXi:2604.08477v1 Announce Type: cross Reinforcement Learning with Verifiable Rewards (RLVR) has significantly improved large language model (LLM) reasoning in formal domains such as mathematics and code. Despite these advancements, LLMs still struggle with general reasoning tasks requiring capabilities such as causal inference and temporal understanding. Extending RLVR to general reasoning is fundamentally constrained by the lack of high-quality, verifiable