EchoGuard: An Agentic Framework with Knowledge-Graph Memory for Detecting Manipulative Communication in Longitudinal Dialogue

2026-03-05

AI Summary

Current AI systems struggle to effectively identify context-dependent covert psychological manipulations—such as gaslighting and guilt induction—due to limited context windows and catastrophic forgetting. This work proposes a knowledge graph–based agent framework that employs a Log-Analyze-Reflect cycle to structure dialogue logs, dynamically track, and interpret six categories of manipulative patterns. By innovatively leveraging the knowledge graph as a core for long-term episodic and semantic memory, the framework integrates large language models with graph-structured event modeling to enable interpretable interventions in longitudinal conversations. The system generates Socratic prompting strategies to foster user self-awareness while preserving autonomy. Both theoretical analysis and empirical evaluation demonstrate that the approach significantly enhances users’ ability to recognize manipulative communication, balancing safety and user agency.

Technology Category

• Multiagent Systems: Agent Communication
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

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.

Problem

• manipulative communication
• longitudinal dialogue
• knowledge graph
• agentic AI
• context-dependent tactics

Innovation

• Knowledge Graph Memory
• Agentic AI
• Manipulative Communication Detection
• Longitudinal Dialogue Analysis
• Socratic Prompting