Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents
CLE is a 50+ expert, 120-task benchmark of five-level ladders (600 levels, 89 professional roles, 12 domains) that unlocks each level only after the prior one is passed, so agents must build on accumulated experience. Across 17 harness-model configurations of frontier LLMs, feedback plus one revision gives a median 5.3 percentage point gain, yet the best system clears only 47.7% of levels and finishes all five levels in just 23.3% of tasks.
Why it matters
Gives recursive self-improvement claims a hard, expert-authored benchmark where frontier agents currently fail more than half the time.
Importance: 3/5
Notable preprint; a benchmark with frontier-model failure rates.