RESEARCH · RESEARCH · #596
arXiv paper evaluates two-agent vs one-call résumé screening with GPT-5.5 and Claude Opus 4.7
The arXiv preprint (arXiv:2609.19530v1) compares traditional one-call résumé screening to a two-agent protocol where employer- and candidate-side agents exchange evidence, using GPT-5.5 and Claude Opus 4.7 on 600 constructed résumé-job pairs. Two-agent screening advanced a larger share of applications overall (GPT-5.5: 33.3%→39.3%; Opus 4.7: 34.0%→35.5%), substantially increased pass rates on a 191-pair borderline pool (GPT-5.5: 4.5%→26.2%; Opus 4.7: 6.5%→16.1%), changed some one-call decisions in both directions, and produced selections that recurred less often on re-runs (notably under GPT-5.5).
KEY POINTS
- The arXiv preprint (arXiv:2609.19530v1) compares traditional one-call résumé screening to a two-agent protocol where employer- and candidate-side agents exchange evidence, using GPT-5.5 and Claude Opus 4.7 on 600 constructed résumé-job pairs.
- Two-agent screening advanced a larger share of applications overall (GPT-5.5: 33.3%→39.3%; Opus 4.7: 34.0%→35.5%), substantially increased pass rates on a 191-pair borderline pool (GPT-5.5: 4.5%→26.2%; Opus 4.7: 6.5%→16.1%), changed some one-call decisions in both directions, and produced selections that recurred less often on re-runs (notably under GPT-5.5).
- As hiring systems become agent-mediated, the screening procedure itself (not just model choice) can materially affect who reaches human review and how consistently access is granted.
WHY IT MATTERS
As hiring systems become agent-mediated, the screening procedure itself (not just model choice) can materially affect who reaches human review and how consistently access is granted.