{"data":{"id":"1e2576ff-e092-4c5e-8acb-f42698ec4d4a","title":"The Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red Teaming","summary":"This paper studies how automatic red teaming of LLM agents should split its roles. It finds that self-criticism by the target session is more effective than external criticism, because it draws on live execution context, and that self-proposal is weaker because awareness of the adversarial goal triggers refusal and sandbagging. A role-separated setup, with the target diagnosing failures and a separate attacker proposing the next attack, reaches 63.2% overall attack success rate on DTAP-BENCH.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2610.34965v1","publishedAt":"2026-10-26T07:34:02.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak","prompt_injection"],"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":"2026-10-26T07:34:02.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety","integrity"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051","AML.T0054"]}}