{"data":{"id":"b2aad7a0-f220-41e2-b357-24d3ba76f5c9","title":"When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents","summary":"RSE-Bench is a benchmark for evaluating skill self-evolution in LLM agents under ordinary, non-adversarial noise, covering four domains and six benchmarks. Across three methods and two backbones, noisy learning retains only 25.5% to 42.1% of the aggregate gain of clean self-evolution, depending on noise type. Perturbations confined to execution records and outcome-record pairings cause average losses comparable to input-side noise.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2610.19910v1","publishedAt":"2026-10-14T10:03:53.000Z","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":"2026-10-14T10:03:53.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}