Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.19748 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917511132348416 |
|---|---|
| author | Xiaolong, Yin Yu, Liu Jiahang, Shen Xingyu, Lu Jingzhe, Ni Fengxiao, Fan Fan, Sang |
| author_facet | Xiaolong, Yin Yu, Liu Jiahang, Shen Xingyu, Lu Jingzhe, Ni Fengxiao, Fan Fan, Sang |
| contents | Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation methods based on large language models (LLMs) often fall short when handling complex CAD models characterized by long operation sequences, diverse operation types, and strong geometric constraints, primarily because reasoning chains break and effective error-correction mechanisms are lacking. To address this problem, this paper proposes a memory-augmented reinforcement learning framework for CAD generation agents. The framework encapsulates the underlying geometric kernel into a structured toolchain callable by the agent and builds a closed-loop mechanism of design intent understanding, global planning, execution, and multi-dimensional verification. It also designs a dual-track memory module consisting of a case library and a skill library, and proposes a dynamic utility retrieval algorithm. By introducing reinforcement learning into retrieval and policy optimization, the agent can effectively avoid retrieval traps in which examples are semantically similar but geometrically infeasible, enabling online self-correction and continual evolution without additional large-scale annotated data. Experiments show that the proposed method significantly improves both the success rate and geometric consistency on complex CAD model generation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_19748 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Memory-Augmented Reinforcement Learning Agent for CAD Generation Xiaolong, Yin Yu, Liu Jiahang, Shen Xingyu, Lu Jingzhe, Ni Fengxiao, Fan Fan, Sang Artificial Intelligence Multiagent Systems Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation methods based on large language models (LLMs) often fall short when handling complex CAD models characterized by long operation sequences, diverse operation types, and strong geometric constraints, primarily because reasoning chains break and effective error-correction mechanisms are lacking. To address this problem, this paper proposes a memory-augmented reinforcement learning framework for CAD generation agents. The framework encapsulates the underlying geometric kernel into a structured toolchain callable by the agent and builds a closed-loop mechanism of design intent understanding, global planning, execution, and multi-dimensional verification. It also designs a dual-track memory module consisting of a case library and a skill library, and proposes a dynamic utility retrieval algorithm. By introducing reinforcement learning into retrieval and policy optimization, the agent can effectively avoid retrieval traps in which examples are semantically similar but geometrically infeasible, enabling online self-correction and continual evolution without additional large-scale annotated data. Experiments show that the proposed method significantly improves both the success rate and geometric consistency on complex CAD model generation tasks. |
| title | Memory-Augmented Reinforcement Learning Agent for CAD Generation |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2605.19748 |