{"data":{"id":"1fdeb0e1-1a19-4d35-be68-0ee3d8082c6f","title":"Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents","summary":"The study compares three evaluation frameworks (trace-based LLM judging, text-only LLM judging with red-teaming, and deterministic heuristics) on two enterprise analytics agents using frozen execution traces. On 72 ground-truth cases, the trace-based framework reached the best balance (F1=0.90), while text-only evaluation matched its recall but produced 5x more false alarms. Phase 3 found 24 novel failures with zero overlap between functional testing and security red-teaming.","solution":"The authors recommend a two-framework strategy: trace-based evaluation for functional assessment and adversarial red-teaming for security validation.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2611.14493v1","publishedAt":"2026-11-10T18:50:06.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-11-10T18:50:06.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}