Evidence and limits
Finding: Human-expert comparisons across time budgets show why task duration and resource allocation must be part of an agent baseline.
Impact: Watch the recorded review topic (see source), the recorded review topic (see source), the recorded review topic (see source).
Boundary: Small, selected engineering environments, noisy rare successes, test feedback and costly GPU access limit generalization. Reported token/labor comparisons exclude GPU cost in the cited figure. Next: Compare matched time and total cost, retain failed runs and avoid treating the average expert as a universal comparator. Added candidate with Selected full-text review; not an exhaustive evaluation appraisal; not full-text validated, replicated or adopted
Flags: Selected full-text review; not an exhaustive evaluation: Small, selected engineering environments, noisy rare successes, test feedback and costly GPU access limit generalization. Reported token/labor comparisons exclude GPU cost in the cited figure.
Record State: Candidate only: not accepted into the reviewed catalog
What was reviewed: Selected full-text review; not an exhaustive evaluation