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

arXiv: https://arxiv.org/abs/2509.25299 · HTML: https://mlsanity.com/paper/2509.25299/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 17 of 17)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia](https://mlsanity.com/paper/2312.03664/) (2023)
- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [Lifelong Learning of Large Language Model based Agents: A Roadmap](https://mlsanity.com/paper/2501.07278/) (2025)
- [Self-evolving Agents with reflective and memory-augmented abilities](https://mlsanity.com/paper/2409.00872/) (2024)
- [Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs](https://mlsanity.com/paper/2409.19401/) (2024)
- [A Survey of Personalization: From RAG to Agent](https://mlsanity.com/paper/2504.10147/) (2025)
- [Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example](https://mlsanity.com/paper/2408.06318/) (2024)
- [Comprehensible Artificial Intelligence on Knowledge Graphs: A survey](https://mlsanity.com/paper/2404.03499/) (2024)
- [Agentic Knowledgeable Self-awareness](https://mlsanity.com/paper/2504.03553/) (2025)
- [Perspective-Aware AI in Extended Reality](https://mlsanity.com/paper/2507.11479/) (2025)
- [MARS: Memory-Enhanced Agents with Reflective Self-improvement](https://mlsanity.com/paper/2503.19271/) (2025)

## Built on by (most cited first, 7 of 7)

- [Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring](https://mlsanity.com/paper/2603.27404/) (2026)
- [Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent Argumentation](https://mlsanity.com/paper/2606.10475/) (2026)
- [Situation Graph Prediction for User Perspective Modeling](https://mlsanity.com/paper/2602.13319/) (2026)
- [EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution](https://mlsanity.com/paper/2604.12776/) (2026)
- [Share No More Than the Request Requires: Federated Disclosure for Perspective-Aware AI](https://mlsanity.com/paper/2607.22953/) (2026)
- [MemoryForge: Synthesize Lifelong Memory for Human-Like LLM Agents](https://mlsanity.com/paper/2608.00007/) (2026)
- [Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents](https://mlsanity.com/paper/2609.21997/) (2026)

## Abstract (arXiv)

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.