LodeHQ
AI news for people who shipFree, by email

AI · arxiv.org · Tuesday, 27 October 2026

Best agent clears only 47.7% of levels on a learn-from-experience exam

Continual Learning Exam tests whether agents improve from experience. It has 120 expert-written tasks, each a five-level ladder, across 89 professional roles, and later levels build on earlier work. Across 17 harness-model setups, feedback after a failure plus one revision added a median 5.3 percentage points. The best system cleared 47.7% of levels and finished all five levels in just 23.3% of tasks.

Read the source: arxiv.org ↗In the 27 October issue →