Preprint
Aug 2026
Learning Context-Free Grammars for Grammar-Constrained Decoding via Declarative Agentic Programming with Guarantees
This work defines an agent, called Autogrammar, that automatically learns context-free grammars from documentation and execution data, formalized as a Kripke structure whose nondeterministic choices are resolved by a language model, enabling declarative control of agent behavior via linear temporal logic constraints.
K. Cheang, G. Hulette, Rahul Kumar et al.
· 0 citations