- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
SafeForge is a safety guardrail for embodied agents. It combines scene objects, attributes, and spatial relations with predefined safety templates, uses soft logic to derive concrete constraints, and checks actions against these constraints. The authors evaluate it on SafeAgentBench and a modified long-horizon subset, reporting strong results.
Critical strengths
- The problem is important. Considering the environment when judging safety is more reasonable than rejecting actions based only on their names.
- The rule reasoning component exposes the conditions that trigger a constraint, making the basis for a safety judgment easier to trace.
Critical weaknesses
-
Aggregation and learning. I still have questions about directly combining confidence scores from different sources using a product t-norm. The authors acknowledge the independence approximation but provide no calibration results or ablations. It is also unclear how the learnable noisy-OR weights are trained and whether Table 2 uses trained or initial weights. The code contains learnable parameters, but the corresponding experimental details are missing.
-
Evaluation. Section 4.1 and Appendix C formulate the task as binary classification of an entire plan. The long-horizon tasks are modified by adding explicit hazardous actions, and all 50 instances are unsafe. The 100% result therefore does not by itself show that the system detects implicit temporal hazards or intercepts the step that causes them. Page 7 mentions scene updates, but Algorithm 2 does not show them, and the supplied evaluator reasons only once before the action loop. A complete trajectory is needed to explain scene updates and rule recomputation. If the evaluation only tests plan classification, the claims should be narrowed. The experiments also provide limited evidence of generalization to other scenes. The authors could evaluate original long-horizon tasks and benign tasks, or consider a process-oriented benchmark such as IS-Bench.
-
Baselines. Appendix B excludes invalid outputs separately for each method without reporting how many samples remain. Some baselines have very low detection rates or high false rejection rates, so input adaptation and task mismatch need to be ruled out, particularly for RoboGuard and AgentSpec. RoboGuard already generates constraints from updated scene information, so its classification as lacking dynamic interception in Table 1 needs explanation. ShieldAgent also uses learnable probabilistic rules, while HomeGuard addresses contextual risks in embodied tasks. The authors should compare with these methods or explain their exclusion.
-
Rule activation. In the code, templates sharing a hazard predicate are activated using that predicate's aggregated probability. In a check of the activation function, a high
fire_hazard(wood,stove)activated cloth- and oil-related templates even whenis_cloth(wood)=0andis_oil(wood)=0. The conditions of each template are not checked separately, which could cause false rejections. The authors should clarify whether this implementation was used in the experiments and how it affects the results. -
Code and experimental setup. The code contains two LLM branches: one supplements rules when too few are activated, and the other can directly return an unsafe judgment before symbolic reasoning. Were these branches used for Table 2? If so, how much of the improvement comes from the LLM rather than rule reasoning? This also needs to be reconciled with Table 1's classification of SafeForge as not using an LLM safety judge. In the supplied package, the three data files are empty, and I could not find a complete entry point for reproducing Table 2. The authors should provide the version and configuration used for the experiments.
Questions for authors
- Were both LLM branches enabled for Table 2? Can the authors compare an LLM-only judge, the rule system with the LLM branches disabled, and the full system using the same inputs and safety knowledge?
- How is the scene updated as actions execute? Can the authors provide a complete trajectory showing observations, rule recomputation, and action interception?
- How are templates sharing a hazard predicate activated individually, as discussed in W4? Did this implementation affect the reported false rejection rate?
- How many safe and unsafe samples remain for each baseline? Which defense component does “Poex” refer to? The POEX paper mainly introduces an attack method and also studies different defenses, so the comparator needs to be specified.