{"data":{"id":"b6689001-c392-4a5f-bcd3-de9c3a3507a7","title":"Refuse the Harm, Complete the Task via Graph-of-Rules Planning for LLM-Enabled Robots","summary":"Researchers introduce safe task completion, a setting where an LLM-enabled robot refuses the harmful part of a compound instruction while still completing its legitimate sub-tasks. They propose RuleGraph, a multi-agent Graph-of-Rules planning framework that spreads safety enforcement across several reasoning and verification stages. On two benchmarks, RuleGraph reduces Attack Success Rate to 0% and reports Task Success Rates of 98.57% on RoboGuard and 84.54% on long-horizon compound instructions.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.24603v1","publishedAt":"2026-10-17T10:13:12.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"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":"2026-10-17T10:13:12.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}