ReCreate: Reasoning and Creating Domain Agents Driven by Experience

TL;DR

ReCreate is an experience-driven framework that automatically creates and adapts domain agents by leveraging interaction histories, outperforming existing methods and human-designed agents across various domains.

Contribution

It introduces a novel agent-as-optimizer paradigm that systematically uses interaction experiences for automatic agent creation and adaptation.

Findings

ReCreate outperforms human-designed agents in multiple domains.

It surpasses existing automated agent generation methods.

ReCreate effectively learns from minimal seed scaffolds.

Abstract

Large Language Model agents are reshaping the industrial landscape. However, most practical agents remain human-designed because tasks differ widely, making them labor-intensive to build. This situation poses a central question: can we automatically create and adapt domain agents in the wild? While several recent approaches have sought to automate agent creation, they typically treat agent generation as a black-box procedure and rely solely on final performance metrics to guide the process. Such strategies overlook critical evidence explaining why an agent succeeds or fails, and often require high computational costs. To address these limitations, we propose ReCreate, an experience-driven framework for the automatic creation of domain agents. ReCreate systematically leverages agent interaction histories, which provide rich concrete signals on both the causes of success or failure and the avenues for improvement. Specifically, we introduce an agent-as-optimizer paradigm that effectively learns from experience via three key components: (i) an experience storage and retrieval mechanism for on-demand inspection; (ii) a reasoning-creating synergy pipeline that maps execution experience into scaffold edits; and (iii) hierarchical updates that abstract instance-level details into reusable domain patterns. In experiments across diverse domains, ReCreate consistently outperforms human-designed agents and existing automated agent generation methods, even when starting from minimal seed scaffolds.