Skip to main content
Search

# Agent library design

1 related articles

Subscribe to updates
  1. arXiv

    Opus 5.5's agent-designed libraries cut downstream code and beat the human production library by 2.3 points, yet 11 of 15 tasks merely reproduce human abstractions

    The authors introduce LibraryDesignBench, a two-phase benchmark in which a designer agent implements a full-featured library from a specification that lists required capabilities without prescribing interfaces, and three user agents from different model families then solve problems with it, scored by pass rate squared times simplicity relative to reference solutions written with the real production library; across 15 library-design tasks, 242 expert-validated problems and four languages, Opus 5.5 scores 48.9, 2.3 points above the production library, designers reproduce production-library abstractions on 11 of 15 tasks, 64% of audited excess code traces to rigid or hard-to-use interfaces rather than missing capabilities, and adding prescriptive agent-first guidance raises the score to 46.

You’re all caught up