ArXiv TLDR

Building Persona-Based Agents On Demand: Tailoring Multi-Agent Workflows to User Needs

🐦 Tweet
2604.27882

Giuseppe Arbore, Andrea Sillano, Luigi De Russis

cs.AIcs.HC

TLDR

This paper introduces on-demand persona generation to dynamically tailor multi-agent workflows, enhancing personalization and context-specific interaction in AI agent systems.

Key contributions

  • Identifies limitations of fixed agent architectures in current multi-agent systems.
  • Introduces on-demand persona generation for dynamic, personalized agent workflows.
  • Enables crafting agents and personas at runtime based on user, task, and context.
  • Details a pipeline for integrating real-time AI persona crafting into agent platforms.

Why it matters

Current multi-agent systems struggle with personalization due to hard-coded roles. This research offers a solution by enabling dynamic, context-aware agent creation. It moves beyond one-size-fits-all configurations, making AI agents more adaptable and efficient for diverse user needs.

Original Abstract

Recent advances in agentic AI are shifting automation from discrete tools to proactive multi-agent systems that coordinate multi-specialized capabilities behind unified interfaces. However, today's agent systems typically rely on hard-coded agent architectures with fixed roles, coordination patterns, and interaction flows that limit end-user personalization and make adaptation to individual needs and contexts difficult. Given this limitation, we argue that on-demand persona-based agent generation offers a promising path towards more efficient and contextually appropriate interaction within agentic workflows. By dynamically crafting agents and personas at run-time to match user characteristics, task demands, and workflow context, agentic platforms can move beyond one-size-fits-all configurations. We present a pipeline for on-demand persona generation in agentic platforms, detailing how real-time crafting of AI personas can be systematically integrated within agent systems, aiming to open new possibilities in agentic platform design paradigms.

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.