LIBRA: Programmatic Induction of Executable Tool Libraries

LIBRA is a framework that transforms a flat catalog of tools into an executable library by having a large language model propose contracts for tool invocations, reusable outputs, state changes, and success conditions. These proposed compositions are then tested in a sandbox, and only the relations that succeed at runtime are retained, eliminating the need for dependency annotations or task‑specific training. The approach improves one‑shot recall and NDCG on several benchmarks, and further enhances retrieval performance after multiple iterations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents