# DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents

Source: [DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents](<https://www.sota2.com/research/paper/69b8dfed0636e5bf4afbe869>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-18T05:00:04.467Z

Authors: Snehasis Mukhopadhyay

Published: 2026-03-14T06:45:43.000Z

## Abstract

Reliable detection of deceptive behavior in Large Language Model (LLM) agents is an essential prerequisite for safe deployment in high-stakes agentic contexts. Prior work on scheming detection has focused exclusively on black-box monitors that observe only externally visible tool calls and outputs, discarding potentially rich internal reasoning signals. We introduce DECEPTGUARD, a unified framework that systematically compares three monitoring regimes: black-box monitors (actions and outputs only), CoT-aware monitors (additionally observing the agent's chain-of-thought reasoning trace), and activation-probe monitors (additionally reading hidden-state representations from a frozen open-weights encoder).   We introduce DECEPTSYNTH, a scalable synthetic pipeline for generating deception-positive and deception-negative agent trajectories across a novel 12-category taxonomy spanning verbal, behavioral, and structural deception. Our monitors are optimized on 4,800 synthetic trajectories and evaluated on 9,200 held-out samples from DeceptArena, a benchmark of realistic sandboxed agent environments with execution-verified labels.   Across all evaluation settings, CoT-aware and activation-probe monitors substantially outperform their black-box counterparts (mean pAUROC improvement of +0.097), with the largest gains on subtle, long-horizon deception that leaves minimal behavioral footprints. We empirically characterize a transparency-detectability trade-off: as agents learn to suppress overt behavioral signals, chain-of-thought becomes the primary detection surface but is itself increasingly unreliable due to post-training faithfulness degradation.   We propose HYBRID-CONSTITUTIONAL ensembles as a robust defense-in-depth approach, achieving a pAUROC of 0.934 on the held-out test set, representing a substantial advance over the prior state of the art.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Deception Detection on DeceptArena (test)](<https://www.sota2.com/research/sota/deception-detection-on-deceptarena-test.md>): Deception Detection; DeceptArena (test); False Assertion Score: 0.927.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.13791>)

[PDF](<https://arxiv.org/pdf/2603.13791.pdf>)
