ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative Agents

2025-09-29

AI Summary

Generative agents suffer from identity drift, belief neglect, and hallucination propagation in long-horizon tasks due to unstructured memory accumulation. To address this, we propose ID-RAG: an Identity-enhanced Retrieval-Augmented Generation framework grounded in a dynamic knowledge graph that explicitly encodes an agent’s core beliefs, personality traits, and values as structured, queryable entities—enabling identity-driven decision-making and real-time contextual grounding. Inspired by Chronicle, ID-RAG significantly improves temporal coherence and behavioral interpretability. In a mayoral election social simulation benchmark, ID-RAG increases fourth-step identity recall by a substantial margin and reduces system convergence time by 19% (GPT-4o) to 58% (GPT-4o mini). To our knowledge, this is the first scalable approach that jointly models identity consistency and long-term memory, establishing a foundation for robust, interpretable, and temporally coherent agent behavior.

Technology Category

• Multiagent Systems: Modeling other Agents
• Knowledge Representation and Reasoning: Reasoning with Beliefs
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Generative agents powered by language models are increasingly deployed for long-horizon tasks. However, as long-term memory context grows over time, they struggle to maintain coherence. This deficiency leads to critical failures, including identity drift, ignoring established beliefs, and the propagation of hallucinations in multi-agent systems. To mitigate these challenges, this paper introduces Identity Retrieval-Augmented Generation (ID-RAG), a novel mechanism designed to ground an agent's persona and persistent preferences in a dynamic, structured identity model: a knowledge graph of core beliefs, traits, and values. During the agent's decision loop, this model is queried to retrieve relevant identity context, which directly informs action selection. We demonstrate this approach by introducing and implementing a new class of ID-RAG enabled agents called Human-AI Agents (HAis), where the identity model is inspired by the Chronicle structure used in Perspective-Aware AI, a dynamic knowledge graph learned from a real-world entity's digital footprint. In social simulations of a mayoral election, HAis using ID-RAG outperformed baseline agents in long-horizon persona coherence - achieving higher identity recall across all tested models by the fourth timestep - and reduced simulation convergence time by 19% (GPT-4o) and 58% (GPT-4o mini). By treating identity as an explicit, retrievable knowledge structure, ID-RAG offers a foundational approach for developing more temporally coherent, interpretable, and aligned generative agents. Our code is open-source and available at: https://github.com/flybits/humanai-agents.

Problem

• Maintaining persona coherence in long-horizon generative agents
• Preventing identity drift and belief inconsistencies over time
• Reducing hallucinations in multi-agent systems through structured identity

Innovation

• ID-RAG uses dynamic knowledge graph for identity modeling
• Retrieves relevant identity context during decision loop
• Enables persona coherence through structured identity grounding