Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents
Read the original on arXiv Computation and Language →The paper introduces Skill-as-Pseudocode (SaP), a method that automatically converts markdown skill libraries for large language model agents into typed pseudocode with deterministic quality control. SaP extracts typed contracts from clusters of procedural passages and verifies them with a four‑check verifier before inlining them into a rewritten skill skeleton that includes both a typed signature and a concrete action template. On the ALFWorld unseen split, SaP outperforms the Graph-of-Skills baseline, achieving 82/402 paired game wins versus 47/402, while reducing input tokens and LLM calls per game.
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 Computation and Language.