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

arXiv cs.AI / 5/1/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper argues that agentic AI is evolving from using individual tools to coordinating multi-agent systems through unified interfaces.
It notes that many current agent architectures use fixed roles and hard-coded coordination flows, which constrains personalization and adaptation to each user’s needs and context.
It proposes “on-demand persona-based agent generation,” dynamically creating agents and personas at runtime based on user characteristics, task requirements, and workflow context.
The authors present a pipeline for integrating real-time persona generation into agentic platforms, aiming to enable new design paradigms for building more contextually appropriate agent workflows.

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.