Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents
The paper introduces Continual Learning Exam (CLE), a benchmark built by 50+ domain experts with 120 human-authored professional tasks, each organised as a five-level ladder (600 levels across 89 roles and 12 domains). Agents must pass each level to unlock the next, with later levels building on earlier experience. An evaluation agent scores submissions against human-authored rubrics. Across 17 harness-model configurations, diagnostic feedback and one revision yield a median completion gain of 5.3 percentage points. The best system clears 47.7% of levels and completes all five levels in 23.3% of tasks.
Open original source huggingface.coOne primary source; other links are context, not independent corroboration.
- Primary sourceHugging Face Daily Papers
- Discovery linkHugging Face
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
- Original paper+45
- Fetched source page+30
- No editor link review0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
The paper introduces Continual Learning Exam (CLE), a benchmark built by 50+ domain experts with 120 human-authored professional tasks, each organised as a five-level ladder (600 levels across 89 roles and 12 domains). Agents must pass each level to unlock the next, with later levels building on earlier experience. An evaluation agent scores submissions against human-authored rubrics. Across 17 harness-model configurations, diagnostic feedback and one revision yield a median completion gain of 5.3 percentage points. The best system clears 47.7% of levels and completes all five levels in 23.3% of tasks.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: huggingface.co. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
Source claims not independently checked; results come from the authors' own evaluation using an evaluation agent scoring against human-authored rubrics.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- CLE contains 120 human-authored tasks, each a five-level ladder, yielding 600 levels across 89 roles and 12 domains.
- Across 17 harness-model configurations, feedback and revision produce a median completion gain of 5.3 percentage points.
- The best-performing system clears only 47.7% of levels and completes all five levels in just 23.3% of tasks.
Source claims not independently checked; results come from the authors' own evaluation using an evaluation agent scoring against human-authored rubrics.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
Most agent benchmarks measure single-task success rather than improvement from accumulated experience. CLE targets sustained learning across professional workflows, and the results suggest current frontier LLM agents struggle with it. The dataset is also proposed as post-training material for continual learning.
Limits and open questions
Source claims not independently checked; results come from the authors' own evaluation using an evaluation agent scoring against human-authored rubrics.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.