Work

SAFE-LOOP: Detecting Silent Sensor Faults in LLM Control Agents with a Contract Gate

Year: 2026
Type: preprint
Abstract: SAFE-LOOP is a contract gate for LLM control agents. LLM agents now drive actuators unattended, so a stale reading becomes a silent wrong action. The gate sits between agent and actuators and builds its own belief from exactly the agent's readings. Over three simulated testbeds and one ICU replay, it detected 89.6–92.9% of stale readings on every channel tested; wrong outputs inside the drift window at 14.8% (HVAC) and 35.2% (wearable) with the fixed drift bound and 90.1% with a fitted HVAC drift model on four open models, and the ICU replay showed no measurable gain on them. With stale HVAC readings the gate cut the silent-fault rate from 99% to 10% (CI 6 to 15) with Claude Haiku 5.5 and from 53% to 7% (CI 3 to 12) with Claude Opus 5.5. Pooled over nine models, it removed 0.90 stale-reading HVAC violations per episode (CI 0.30 to 1.51) at 1.03–1.06 times the episode cost. On greenhouse moisture a per-step exposure bound holds up to 0.65 from the set x ≤ 0.58; its recovery hypothesis is checked on logs, not certified. The gate refuses 23.7% of fault-free HVAC reads (qwen3-235b) and locks out 31.3% of no-fault wearable decisions. Preprint. Code and data: 10.5281/zenodo.24186989.
Language: English
Open Access status: green
OpenAlex ID: W7226024847
Cites:
Cited by: 1
Related to: 10