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.

Topics

• Robotics and embodied AI

Related items

• InfoSafety Mid-Training: Internalizing LLM Safety as a Foundational CapabilitySimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoConcerns in Benchmarking Jailbreaks: An Empirical Study of Attack Success RatesSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoBeyond Attack Success Rate: Cost-Aware Metric for Evaluating Iterative LLM JailbreaksSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoBudgeted Attack Scheduling for LLM Red-Teaming: The Roles of Static Priors, Semantic Guidance, and Online FeedbackSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoPeer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code SecuritySimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)