Beyond QASecClaw: Agent Scaling, Verifier Feedback, and Evidence Reliability in Software Assurance
Can additional specialist language-model contexts improve software assurance when deterministic tool evidence is already available? We study this question through five experiments spanning authored Java warning controls, OWASP Benchmark assessment, Defects4J test generation, SV-COMP assertion verdicts, and deliberately misleading evidence packages. The evaluated systems use…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
