Published Research
SPE-235393-MS · 2026 · ADIPEC 2026 · ABU DHABI SPE-235393-MS First author

Propose-Validate-Correct Shadow-Plant Architecture for Safe AI Agents in Process Operations

Simulate the move before the plant feels it.

Mohammed Imran Khan1,2 , Manju Khanna2 , Abhishek Shivkumar1 , Tuhin Sharma1 , Adinarayana Sakala1 , Nirav Kumar1 , Pranjalya Singh1 , Darshika Pundir1 , Atrik Ghosh1

  • 1 Red Hat, Bengaluru, Karnataka, India
  • 2 Amrita School of Computing, Amrita Vishwa Vidyapeetham, Bengaluru, Karnataka, India

DOI 10.2118/235393-MS

// Summary

A safety layer where every agent action is tested on a shadow plant first. Unsafe proposals are rejected with feedback so the agent can correct itself - before anything reaches the real process.

LLM agents can propose physically unsafe control actions in process plants. PVC is a framework-agnostic safety layer: every proposed action is simulated in a shadow plant before it can reach the real process. On OpsEnv (CSTR), shadow-equipped agents record zero actual violations across 282 PVC cells, intercept 1,552 unsafe proposals, and keep completion statistically on par with direct agents. Descriptive feedback lifts self-correction 3× versus binary reject. Plan-and-Execute with PVC runs 31× faster than ReAct with PVC for Gemini Flash.

0

actual violations on the real process across 282 PVC cells

1,552

unsafe proposals intercepted before execution

3×

higher self-correction with descriptive feedback vs binary

31×

faster wall time: Plan-and-Execute+PVC vs ReAct+PVC (Gemini)

// Explainer video

0:00 / 0:00

The Shadow Gate - AI Safety in Process Operations

Space = play · ← → seek · M mute

// How it works

1

Propose

Agent emits JSON action

2

Validate

Shadow plant forward-sim N=5

3

Correct

Structured feedback, K≤3

4

Execute / Escalate

Only safe moves reach the plant

// Problem

LLM agents can hallucinate setpoints outside safe envelopes. Approve-everything restores the human bottleneck. Trust-everything lets unsafe moves hit the plant. Neither extreme works for safety-critical operations.

// Approach

PVC inserts a physics-grounded shadow plant between the agent and the process. Propose → validate (forward simulate N=5 timesteps / 50 s) → correct with structured feedback (up to K=3 attempts), or escalate. Built on LangGraph + OpsEnv CSTR ODEs. Advisory layer only - not a replacement for certified SIS.

// Notable contributions

  • ▹ PVC pattern: propose-validate-correct loop with configurable feedback granularity as a safety gate for LLM agents
  • ▹ Shadow plant: physics-grounded CSTR simulator for pre-execution validation
  • ▹ Structured agent output: JSON proposals in natural-language rationale with conservative parse fallbacks
  • ▹ Evidence from 440 experiment cells across 4 setups, 4 LLMs, 3 feedback levels, and 11 scenarios
  • ▹ Model-specific violation profiling showing order-of-magnitude differences in unsafe proposal rates

// Method

Benchmark: OpsEnv open-source CSTR (mass/energy/level ODEs, Arrhenius kinetics, PI cooling)
Setups: react_shadow, react_direct, plan_exec_shadow, plan_exec_direct
Models: Gemini 2.5 Flash (cloud); Qwen 2.5 32B, Llama 3.1 8B, Mistral 7B (Ollama 4-bit)
Feedback levels: binary, descriptive, suggested fix

// Figures from the paper

Graphs as published

Exact figures extracted from the SPE manuscript - architecture, heatmaps, completion, wall time, and the rest. Click any figure to enlarge.

Fig. 1

Propose-Validate-Correct architecture

Fig. 1. Every agent-proposed control action is validated by the shadow plant before it can reach the real process. Unsafe proposals loop back with physics feedback (up to K=3), or escalate to an operator.

Fig. 2

Constraint exceedances by model and setup

Fig. 2. Shadow-equipped setups record zero actual violations across every model. Without PVC, ReAct Direct drives most of the 1,128 baseline violations - Mistral 7B alone contributes 414.

Fig. 3

Completion score by model and agent setup

Fig. 3. Error bars show one standard deviation. PVC mean completion sits at 0.581; the completion trade-off versus direct agents is negligible (Cohen's d = -0.053).

Fig. 4

Mean wall time by model and setup (log scale)

Fig. 4. Gray lines span the range of setup means per model. Plan-and-Execute with PVC is ~31× faster than ReAct with PVC for Gemini Flash, with the same zero-violation guarantee.

Fig. 5

Self-Correction Success Rate by feedback level

Fig. 5. For Gemini Flash shadow agents (Tiers 1 and 2). Descriptive feedback lifts A-series SCSR from 16.7% to 50.9% (3.0×). Suggested-fix adds only +2.7 pp.

// Key findings

01

PVC eliminates actual plant violations for every model and architecture tested (282 shadow cells).

02

Without PVC, violation propensity spans 5.3 (Gemini) to 25.9 (Mistral) per react_direct cell - PVC normalizes safety across models.

03

Correction works in optimization (A-series SCSR 40.3%) but is conservative in upsets (B-series SCSR 0% at the 20% stability threshold).

04

Completion trade-off is negligible (Cohen's d = −0.053); CI spans zero. Formal equivalence not confirmed at current sample size.

05

81% of rejections are stability/trajectory-based - they need forward simulation, not static range checks alone.

// Concepts

PVC

propose → validate → correct

Shadow plant

physics sim before execution

OpsEnv

open CSTR benchmark

LangGraph

orchestration of the PVC loop

// Slideshow

PVC Shadow-Plant Architecture

15 slides · native playback with animations

Loading deck…

Preparing…

Share: