Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.00876 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914570848698368 |
|---|---|
| author | Liu, Yuyang Wang, Jingya Lv, Liuzhenghao Tian, Yonghong |
| author_facet | Liu, Yuyang Wang, Jingya Lv, Liuzhenghao Tian, Yonghong |
| contents | Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical execution in wet-labs. In these irreversible environments, probabilistic hallucinations are not merely incorrect; they can cause equipment damage or experimental failure. We propose BioProAgent, a neuro-symbolic framework that anchors probabilistic planning in a deterministic Finite State Machine (FSM). We introduce a State-Augmented Planning mechanism that enforces a rigorous Design-Verify-Rectify workflow, ensuring hardware compliance before execution. Furthermore, we address the context bottleneck inherent in complex device schemas by Semantic Symbol Grounding, reducing token consumption by ~6* through symbolic abstraction. In the extended BioProBench benchmark, BioProAgent achieves 95.6% physical compliance (compared to 21.0% for ReAct), demonstrating that neuro-symbolic constraints are essential for reliable autonomy in irreversible physical environments. Code: https://github.com/YuyangSunshine/bioproagent | Website: https://yuyangsunshine.github.io/BioPro-Project. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00876 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning Liu, Yuyang Wang, Jingya Lv, Liuzhenghao Tian, Yonghong Artificial Intelligence Multiagent Systems Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical execution in wet-labs. In these irreversible environments, probabilistic hallucinations are not merely incorrect; they can cause equipment damage or experimental failure. We propose BioProAgent, a neuro-symbolic framework that anchors probabilistic planning in a deterministic Finite State Machine (FSM). We introduce a State-Augmented Planning mechanism that enforces a rigorous Design-Verify-Rectify workflow, ensuring hardware compliance before execution. Furthermore, we address the context bottleneck inherent in complex device schemas by Semantic Symbol Grounding, reducing token consumption by ~6* through symbolic abstraction. In the extended BioProBench benchmark, BioProAgent achieves 95.6% physical compliance (compared to 21.0% for ReAct), demonstrating that neuro-symbolic constraints are essential for reliable autonomy in irreversible physical environments. Code: https://github.com/YuyangSunshine/bioproagent | Website: https://yuyangsunshine.github.io/BioPro-Project. |
| title | BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2603.00876 |