Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2604.16345 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918476769132544 |
|---|---|
| author | Miura, Akira Sasahara, Yuki Demura, Momoka Masubuchi, Yuji Asai, Tetsuya Mitsui, Chikahiko |
| author_facet | Miura, Akira Sasahara, Yuki Demura, Momoka Masubuchi, Yuji Asai, Tetsuya Mitsui, Chikahiko |
| contents | While advances in materials informatics have accelerated the development of Self-Driving Laboratories (SDLs), human-led experiments remain standard in many educational and exploratory research laboratories. In specific lab settings, formal documentation alone is often insufficient for safe and reliable operation. We refer to the gap between formal documentation and reliable execution in such settings as the experimental last mile; this gap mainly involves site-specific operational know-how, including local rules, routine checks, procedural details, and safety-conscious actions that are can be verbalizable but are often under-documented in standard manuals. In this proof-of-concept study, we developed a human-in-the-loop AI assistant that combines first-person experimental video, multimodal AI, and retrieval-augmented generation (RAG). Using powder X-ray diffraction experiments and student-recorded video data as inputs, the system extracts site-specific laboratory knowledge from recorded procedures, including physical techniques and audible confirmation that conventional manuals could omit. It then provides grounded responses based on the resulting manual. To reduce the risk of unsupported outputs, the system employs a two-layer safety design: source restriction through RAG and strict system-prompt constraints. Instructor-based evaluation showed alignment with expected guidance for questions covered by the manual. For out-of-scope queries, the system appropriately refused to answer, indicating a reduced risk of hallucination. Expert evaluation further indicated that the generated advisory reports were useful and safe (utility: 3.25/4.00; safety: 4.00/4.00). These results suggest the feasibility of a framework for bridging the experimental last mile in which AI supports laboratory practice under explicit human supervision rather than replacing human judgment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16345 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Bridging the Experimental Last Mile: Digitizing Laboratory Know-How for Safe AI-Assisted Support Miura, Akira Sasahara, Yuki Demura, Momoka Masubuchi, Yuji Asai, Tetsuya Mitsui, Chikahiko Human-Computer Interaction Artificial Intelligence While advances in materials informatics have accelerated the development of Self-Driving Laboratories (SDLs), human-led experiments remain standard in many educational and exploratory research laboratories. In specific lab settings, formal documentation alone is often insufficient for safe and reliable operation. We refer to the gap between formal documentation and reliable execution in such settings as the experimental last mile; this gap mainly involves site-specific operational know-how, including local rules, routine checks, procedural details, and safety-conscious actions that are can be verbalizable but are often under-documented in standard manuals. In this proof-of-concept study, we developed a human-in-the-loop AI assistant that combines first-person experimental video, multimodal AI, and retrieval-augmented generation (RAG). Using powder X-ray diffraction experiments and student-recorded video data as inputs, the system extracts site-specific laboratory knowledge from recorded procedures, including physical techniques and audible confirmation that conventional manuals could omit. It then provides grounded responses based on the resulting manual. To reduce the risk of unsupported outputs, the system employs a two-layer safety design: source restriction through RAG and strict system-prompt constraints. Instructor-based evaluation showed alignment with expected guidance for questions covered by the manual. For out-of-scope queries, the system appropriately refused to answer, indicating a reduced risk of hallucination. Expert evaluation further indicated that the generated advisory reports were useful and safe (utility: 3.25/4.00; safety: 4.00/4.00). These results suggest the feasibility of a framework for bridging the experimental last mile in which AI supports laboratory practice under explicit human supervision rather than replacing human judgment. |
| title | Bridging the Experimental Last Mile: Digitizing Laboratory Know-How for Safe AI-Assisted Support |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2604.16345 |