Dynamic Agentic AI Expert Profiler System Architecture for Multidomain Intelligence Modeling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917387769479168 |
|---|---|
| author | Adeseye, Aisvarya Isoaho, Jouni Virtanen, Seppo Tahir, Mohammad |
| author_facet | Adeseye, Aisvarya Isoaho, Jouni Virtanen, Seppo Tahir, Mohammad |
| contents | In today's artificial intelligence driven world, modern systems communicate with people from diverse backgrounds and skill levels. For human-machine interaction to be meaningful, systems must be aware of context and user expertise. This study proposes an agentic AI profiler that classifies natural language responses into four levels: Novice, Basic, Advanced, and Expert. The system uses a modular layered architecture built on LLaMA v3.1 (8B), with components for text preprocessing, scoring, aggregation, and classification. Evaluation was conducted in two phases: a static phase using pre-recorded transcripts from 82 participants, and a dynamic phase with 402 live interviews conducted by an agentic AI interviewer. In both phases, participant self-ratings were compared with profiler predictions. In the dynamic phase, expertise was assessed after each response rather than at the end of the interview. Across domains, 83% to 97% of profiler evaluations matched participant self-assessments. Remaining differences were due to self-rating bias, unclear responses, and occasional misinterpretation of nuanced expertise by the language model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05345 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Dynamic Agentic AI Expert Profiler System Architecture for Multidomain Intelligence Modeling Adeseye, Aisvarya Isoaho, Jouni Virtanen, Seppo Tahir, Mohammad Artificial Intelligence In today's artificial intelligence driven world, modern systems communicate with people from diverse backgrounds and skill levels. For human-machine interaction to be meaningful, systems must be aware of context and user expertise. This study proposes an agentic AI profiler that classifies natural language responses into four levels: Novice, Basic, Advanced, and Expert. The system uses a modular layered architecture built on LLaMA v3.1 (8B), with components for text preprocessing, scoring, aggregation, and classification. Evaluation was conducted in two phases: a static phase using pre-recorded transcripts from 82 participants, and a dynamic phase with 402 live interviews conducted by an agentic AI interviewer. In both phases, participant self-ratings were compared with profiler predictions. In the dynamic phase, expertise was assessed after each response rather than at the end of the interview. Across domains, 83% to 97% of profiler evaluations matched participant self-assessments. Remaining differences were due to self-rating bias, unclear responses, and occasional misinterpretation of nuanced expertise by the language model. |
| title | Dynamic Agentic AI Expert Profiler System Architecture for Multidomain Intelligence Modeling |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.05345 |