OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915815198031872 |
|---|---|
| author | Liu, Qi Hao, Ruochen Li, Can Ma, Wanjing |
| author_facet | Liu, Qi Hao, Ruochen Li, Can Ma, Wanjing |
| contents | Automating scientific discovery in complex, experiment-driven domains requires more than iterative mutation of programs; it demands structured hypothesis management, environment interaction, and principled reflection. We present OR-Agent, a configurable multi-agent research framework designed for automated exploration in rich experimental environments. OR-Agent organizes research as a structured tree-based workflow that explicitly models branching hypothesis generation and systematic backtracking, enabling controlled management of research trajectories beyond simple mutation-crossover loops. At its core, we introduce an evolutionary-systematic ideation mechanism that unifies evolutionary selection of research starting points, comprehensive research plan generation, and coordinated exploration within a research tree. We introduce a hierarchical optimization-inspired reflection system in which short-term reflections act as verbal gradients, long-term reflections as verbal momentum, and memory compression as semantic weight decay, collectively forming a principled mechanism for governing research dynamics. We conduct extensive experiments across classical combinatorial optimization benchmarks as well as simulation-based cooperative driving scenarios. Results demonstrate that OR-Agent outperforms strong evolutionary baselines while providing a general, extensible, and inspectable framework for AI-assisted scientific discovery. All code and experimental data are publicly available at https://github.com/qiliuchn/OR-Agent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13769 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery Liu, Qi Hao, Ruochen Li, Can Ma, Wanjing Artificial Intelligence Computational Engineering, Finance, and Science Neural and Evolutionary Computing Automating scientific discovery in complex, experiment-driven domains requires more than iterative mutation of programs; it demands structured hypothesis management, environment interaction, and principled reflection. We present OR-Agent, a configurable multi-agent research framework designed for automated exploration in rich experimental environments. OR-Agent organizes research as a structured tree-based workflow that explicitly models branching hypothesis generation and systematic backtracking, enabling controlled management of research trajectories beyond simple mutation-crossover loops. At its core, we introduce an evolutionary-systematic ideation mechanism that unifies evolutionary selection of research starting points, comprehensive research plan generation, and coordinated exploration within a research tree. We introduce a hierarchical optimization-inspired reflection system in which short-term reflections act as verbal gradients, long-term reflections as verbal momentum, and memory compression as semantic weight decay, collectively forming a principled mechanism for governing research dynamics. We conduct extensive experiments across classical combinatorial optimization benchmarks as well as simulation-based cooperative driving scenarios. Results demonstrate that OR-Agent outperforms strong evolutionary baselines while providing a general, extensible, and inspectable framework for AI-assisted scientific discovery. All code and experimental data are publicly available at https://github.com/qiliuchn/OR-Agent. |
| title | OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery |
| topic | Artificial Intelligence Computational Engineering, Finance, and Science Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2602.13769 |