MinervaRL applies reinforcement learning with verifiable rewards from CTI standards to improve LLM structured output performance by 15.8 points over base models across 12 benchmarks.
Input includes report context and a question with options; output is a JSON object wrapped in<json object> tags containing a correct answers list
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs
MinervaRL applies reinforcement learning with verifiable rewards from CTI standards to improve LLM structured output performance by 15.8 points over base models across 12 benchmarks.