ReCreate: Reasoning and Creating Domain Agents Driven by Experience
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911628726894592 |
|---|---|
| author | Hao, Zhezheng Wang, Hong Luo, Jian Zhang, Jianqing Zhou, Yuyan Lin, Qiang Wang, Can Dong, Hande Chen, Jiawei |
| author_facet | Hao, Zhezheng Wang, Hong Luo, Jian Zhang, Jianqing Zhou, Yuyan Lin, Qiang Wang, Can Dong, Hande Chen, Jiawei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11100 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ReCreate: Reasoning and Creating Domain Agents Driven by Experience Hao, Zhezheng Wang, Hong Luo, Jian Zhang, Jianqing Zhou, Yuyan Lin, Qiang Wang, Can Dong, Hande Chen, Jiawei Artificial Intelligence 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. |
| title | ReCreate: Reasoning and Creating Domain Agents Driven by Experience |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.11100 |