RuleGraph: Graph-of-Rules Planning for Safe Task Completion in LLM-Enabled Robo
Overview
Source roundup from published reports. Claims below are attributed to their publishers, not independently verified. arXiv Robotics — research abstracts: Refuse the Harm, Complete the Task via Graph-of-Rules Planning for LLM-Enabled Robots. This research presents RuleGraph, a multi-agent Graph-of-Rules planning framework that allows LLM-enabled robots to reject harmful parts of instructions while completing legitimate tasks. The method distributes safety en…
Generated from attributed reports · Updated 4 minutes ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · Reported success rate: 0 percent · Basis not reported
“nchmarks in two environments using Attack Success Rate (ASR) and Task Success Rate (TSR). RuleGraph reduces ASR to 0% on both benchmarks while achieving the highest TSR among all methods, reaching 98.57% on the RoboGuard benchmark and 84.54% on our long-horizon compound instructions.”
Exact source · revision 1Source owner not reported
Reported quantity · benchmark: 0 other · Basis not reported
“nchmarks in two environments using Attack Success Rate (ASR) and Task Success Rate (TSR). RuleGraph reduces ASR to 0% on both benchmarks while achieving the highest TSR among all methods, reaching 98.57% on the RoboGuard benchmark and 84.54% on our long-horizon compound instructions.”
Exact source · revision 1Source owner not reported
Reported quantity · environment: 0 other · Basis not reported
“nchmarks in two environments using Attack Success Rate (ASR) and Task Success Rate (TSR). RuleGraph reduces ASR to 0% on both benchmarks while achieving the highest TSR among all methods, reaching 98.57% on the RoboGuard benchmark and 84.54% on our long-horizon compound instructions.”
Exact source · revision 1Source owner not reported
Reported quantity · method: 0 other · Basis not reported
“nchmarks in two environments using Attack Success Rate (ASR) and Task Success Rate (TSR). RuleGraph reduces ASR to 0% on both benchmarks while achieving the highest TSR among all methods, reaching 98.57% on the RoboGuard benchmark and 84.54% on our long-horizon compound instructions.”
Exact source · revision 1Source owner not reported
Evidence dependency changes (2)
- 2026-10-30T22:20:03.914Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T22:19:47.932Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalRefuse the Harm, Complete the Task via Graph-of-Rules Planning for LLM-Enabled Robots
This research presents RuleGraph, a multi-agent Graph-of-Rules planning framework that allows LLM-enabled robots to reject harmful parts of instructions while completing legitimate tasks. The method distributes safety enforcement across multiple reasoning stages, achieving 0% attack success rate and high task success rates on benchmark environments.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).