cs.AINov 17, 2026

ConfGuard: a physics-grounded reference monitor for predictive-maintenance large-language-model agents

Authors: Arunkumar V, Gangadharan G. R., S. Senthilkumar

Organizations: University College of Engineering, BIT Campus, Anna University, Tiruchirappalli 620 024, India · Department of Computer Applications, National Institute of Technology Tiruchirappalli, Tiruchirappalli 620 015, India

Abstract

Large-language-model agents now close the industrial predictive-maintenance loop, reading sensor windows, retrieving procedures and dispatching work orders. Two attack channels meet there: injected text in a retrieved document can hijack the decision, and a bounded sensor perturbation can corrupt the remaining-useful-life estimate behind it. Recent agent defenses police data provenance and tool privilege but cannot tell whether a prognostic quantity is physically plausible. ConfGuard is a reference monitor with a physics-grounded policy. Its conformal monitor tests each prediction, anchored to the asset's admitted history, against degradation physics: capped remaining life never rises and falls at most one cycle per cycle. Calibrating its threshold over whole asset trajectories lets the operator set the expected share of a clean asset's windows the running monitor escalates. A physics-policy validator checks the agent's maintenance-urgency decision against the decision a deterministic policy derives from the same interval. On all 10,196 C-MAPSS test windows the monitor cuts a covert attacker's reach on healthy assets from 0.529 to 0.046 and closes suppression of failing assets (0.151 to 0), escalating 0.027 of clean windows against a 0.05 target, while the fixed physical range it replaces leaves both attacks open. Behind a Qwen3-14B planner the composed monitors hold urgency-class injection to 0.00 and the universal sensor attack to 0.12, against 0.29 and 0.54 for a defended prompt. An adaptive attacker defeats a Mahalanobis detector on 0.504 of windows and adversarial training on 0.485. We report an attack class the projection misses.

Figures & tables

Explore similar work

CardsList
  1. PrefixGuard: Online Failure Warning and Trace-Grounded Diagnosis for LLM Agents

    May 7, 2026Xinmiao Huang, Jinwei Hu, Qisong He +4Fault DetectionAI Agent Monitoring

  2. PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools

    Apr 2, 2026Yusheng Li, Tianjun Feng, Yunfeng Chen +6LLM Agent EvaluationAI Agent Benchmarks

  3. LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents

    Nov 2, 2026Sreehari Sankar, Debargha Ganguly, Vikash Singh +17Tool Access Control for LLM AgentsLLM Guardrails