An LLM-based generator-critic loop autoformalizes natural language policies into Cedar policies that cover substantially more of the source specification than hand-coded symbolic enforcement on MedAgentBench.
Contextual bandits with entropy-based human feedback, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Autoformalization of Agent Instructions into Policy-as-Code
An LLM-based generator-critic loop autoformalizes natural language policies into Cedar policies that cover substantially more of the source specification than hand-coded symbolic enforcement on MedAgentBench.