# SPARK: Search Personalization via Agent-Driven Retrieval and Knowledge-sharing

arXiv: https://arxiv.org/abs/2512.24008 · HTML: https://mlsanity.com/paper/2512.24008/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 55 references that are in the map.
- First posted on arXiv 30 Dec 2025.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 14 of 14)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [A Tutorial on Thompson Sampling](https://mlsanity.com/paper/1707.02038/) (2017)
- [Multi-Stage Document Ranking with BERT](https://mlsanity.com/paper/1910.14424/) (2019)
- [Unveiling Privacy Risks in LLM Agent Memory](https://mlsanity.com/paper/2502.13172/) (2025)
- [User Modeling and User Profiling: A Comprehensive Survey](https://mlsanity.com/paper/2402.09660/) (2024)
- [Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots](https://mlsanity.com/paper/2410.11876/) (2024)
- [Attentive Long Short-Term Preference Modeling for Personalized Product Search](https://mlsanity.com/paper/1811.10155/) (2018)
- [Towards Explainable Temporal User Profiling with LLMs](https://mlsanity.com/paper/2505.00886/) (2025)
- [Learning to Search in Long Documents Using Document Structure](https://mlsanity.com/paper/1806.03529/) (2018)
- [The Personalization Paradox: the Conflict between Accurate User Models and Personalized Adaptive Systems](https://mlsanity.com/paper/2103.01771/) (2021)
- [Temporal User Profiling with LLMs: Balancing Short-Term and Long-Term Preferences for Recommendations](https://mlsanity.com/paper/2508.08454/) (2025)

## Abstract (arXiv)

Personalized search demands the ability to model users' evolving, multi-dimensional information needs; a challenge for systems constrained by static profiles or monolithic retrieval pipelines. We present SPARK (Search Personalization via Agent-Driven Retrieval and Knowledge-sharing), a framework in which coordinated persona-based large language model (LLM) agents deliver task-specific retrieval and emergent personalization. SPARK formalizes a persona space defined by role, expertise, task context, and domain, and introduces a Persona Coordinator that dynamically interprets incoming queries to activate the most relevant specialized agents. Each agent executes an independent retrieval-augmented generation process, supported by dedicated long- and short-term memory stores and context-aware reasoning modules. Inter-agent collaboration is facilitated through structured communication protocols, including shared memory repositories, iterative debate, and relay-style knowledge transfer. Drawing on principles from cognitive architectures, multi-agent coordination theory, and information retrieval, SPARK models how emergent personalization properties arise from distributed agent behaviors governed by minimal coordination rules. The framework yields testable predictions regarding coordination efficiency, personalization quality, and cognitive load distribution, while incorporating adaptive learning mechanisms for continuous persona refinement. By integrating fine-grained agent specialization with cooperative retrieval, SPARK provides insights for next-generation search systems capable of capturing the complexity, fluidity, and context sensitivity of human information-seeking behavior.