{"data":{"id":"1bafc480-2adf-497b-b5bc-a767cda9e167","title":"Eval-production behavior gaps in agent safety and the role of eval-awareness","summary":"Researchers compare agent success rates on safety evaluations with success rates on comparable production decisions, using the Respecting Warnings evaluation as a representative test. Some models perform substantially worse on evaluations than in production, with the largest gaps in models that most often verbalize incorrect evaluation objectives. The authors find that evaluation-objective awareness is closely associated with the gap, and that objective framing can causally change evaluation success rates.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://alignment.openai.com/eval-production-behavior-gap/","publishedAt":"2026-11-03T08:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["Codex"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-03T08:00:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"industry","atlasIds":null}}