Refuse the Harm, Complete the Task via Graph-of-Rules Planning for LLM-Enabled Robots
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 enforcement across multiple reasoning stages, achieving 0% attack success rate and high task success rates on benchmark environments.
This paper introduces RuleGraph, a multi-agent planning framework that enables LLM-enabled robots to safely complete tasks by rejecting harmful sub-tasks while executing legitimate ones. The approach reduces reliance on centralized safety decisions and achieves high task success rates across benchmark environments.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported success rate
0%
View original evidence
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.
Open source S6benchmark
0
View original evidence
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.
Open source S6environment
0
View original evidence
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.
Open source S6method
0
View original evidence
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.
Open source S6
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
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.
Open source S6
Source：arXiv Robotics — research abstracts · arxiv.org