ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry

TL;DR

This paper introduces ACF, a new framework for covert communication among autonomous agents that overcomes cognitive asymmetry issues by decoupling semantic reasoning from statistical layers, ensuring reliable secret exchange.

Contribution

ACF is the first framework to structurally decouple covert communication from semantic reasoning, enabling effective communication despite cognitive asymmetry in agent networks.

Findings

ACF outperforms symmetric baselines under severe cognitive asymmetry.

ACF maintains semantic fidelity and covert capacity with provable error bounds.

ACF guarantees robust effective information capacity in agent networks.

Abstract

As generative artificial intelligence evolves, autonomous agent networks present a powerful paradigm for interactive covert communication. However, because agents dynamically update internal memories via environmental interactions, existing methods face a critical structural vulnerability: cognitive asymmetry. Conventional approaches demand strict cognitive symmetry, requiring identical sequence prefixes between the encoder and decoder. In dynamic deployments, inevitable prefix discrepancies destroy synchronization, inducing severe channel degradation. To address this core challenge of cognitive asymmetry, we propose the Asymmetric Collaborative Framework (ACF), which structurally decouples covert communication from semantic reasoning via orthogonal statistical and cognitive layers. By deploying a prefix-independent decoding paradigm governed by a shared steganographic configuration, ACF eliminates the reliance on cognitive symmetry. Evaluations on realistic memory-augmented workflows demonstrate that under severe cognitive asymmetry, symmetric baselines suffer severe channel degradation, whereas ACF uniquely excels across both semantic fidelity and covert communication. It maintains computational indistinguishability, enabling reliable secret extraction with provable error bounds, and providing robust Effective Information Capacity guarantees for modern agent networks.