EchoGuard: An Agentic Framework with Knowledge-Graph Memory for Detecting Manipulative Communication in Longitudinal Dialogue
This framework aims to empower individuals to recognize manipulative communication, a common and harmful problem, by providing an AI system with structured, longitudinal memory capabilities.
This paper introduces EchoGuard, an agentic AI framework designed to help individuals identify manipulative communication tactics like gaslighting and guilt-tripping in longitudinal dialogue. It addresses the limitations of existing AI systems by using a Knowledge Graph (KG) as its core memory to track subtle, context-dependent manipulation patterns.
Manipulative communication, such as gaslighting, guilt-tripping, and emotional coercion, is often difficult for individuals to recognize. Existing agentic AI systems lack the structured, longitudinal memory to track these subtle, context-dependent tactics, often failing due to limited context windows and catastrophic forgetting. We introduce EchoGuard, an agentic AI framework that addresses this gap by using a Knowledge Graph (KG) as the agent's core episodic and semantic memory. EchoGuard employs a structured Log-Analyze-Reflect loop: (1) users log interactions, which the agent structures as nodes and edges in a personal, episodic KG (capturing events, emotions, and speakers); (2) the system executes complex graph queries to detect six psychologically-grounded manipulation patterns (stored as a semantic KG); and (3) an LLM generates targeted Socratic prompts grounded by the subgraph of detected patterns, guiding users toward self-discovery. This framework demonstrates how the interplay between agentic architectures and Knowledge Graphs can empower individuals in recognizing manipulative communication while maintaining personal autonomy and safety. We present the theoretical foundation, framework design, a comprehensive evaluation strategy, and a vision to validate this approach.