Files
ModelHub XC b79d58a581 初始化项目,由ModelHub XC社区提供模型
Model: Caaaarr1e/StepSafe-4B
Source: Original Platform
2026-11-13 05:32:55 +08:00

1.4 KiB

license, base_model, pipeline_tag, tags
license base_model pipeline_tag tags
apache-2.0 Qwen/Qwen3-4B text-generation
agent-safety
guardrail
safety-monitor
qwen3

StepSafe-4B

A step-level reasoning monitor for LLM agents, trained from Qwen3-4B with a supervised warm start and ASPO. Before each proposed agent action executes, it writes a short reasoning trace and returns a ten-field verdict: CONTINUE lets the action run, ASK pauses it with a clarification question, and STOP blocks it.

\boxed{act:<CONTINUE|ASK|STOP>, risk:<0-100>, obj:<entity|NONE>, fail:<label>, fault:<label>,
       harm:<label>, src:<label>, timing:<label>, q:<question|NONE>, cite:<sequence|NONE>}

Table 1 of the paper (4,033 trajectories, %):

Benchmark Acc mF1 J
ASSE-Safety 70.9 70.9 44.0
ASSE-Security 83.5 83.5 66.9
R-Judge 84.0 84.0 68.0
AgentHarm 93.8 87.0 64.8
ATBench 71.6 71.6 43.2
Overall 76.5 76.5 53.0

Usage

The prompts are built by the StepSafe code (github.com/carriegu0818/StepSafe), which also evaluates the model:

MODEL=<path to this model> bash scripts/eval_stepsafe.sh

Enable thinking; the paper decodes greedily with up to 2,048 new tokens.

Citation

@misc{stepsafe,
  title  = {StepSafe: Learning Timely Intervention with Context-Aware Safety Reasoning},
  author = {Anonymous},
  year   = {2026}
}