HACHIMI: Scalable and Controllable Student Persona Generation via Orchestrated Agents
Student Personas (SPs) are emerging as infrastructure for educational LLMs, yet prior work often relies on ad-hoc prompting or hand-crafted profiles with limited control over educational theory and population distributions. We formalize this as Theory-Aligned and Distribution-Controllable Persona Generation (TAD-PG) and introduce HACHIMI, a multi-agent Propose-Validate-Revise framework that generates theory-aligned, quota-controlled personas. HACHIMI factorizes each persona into a theory-anchored educational schema, enforces developmental and psychological constraints via a neuro-symbolic validator, and combines stratified sampling with semantic deduplication to reduce mode collapse. The ...
| Authors | Yilin Jiang, Fei Tan, Xuanyu Yin et al. |
|---|---|
| Primary category | cs.CL |
| Published | 5 March 2026 |
| Last updated at source | 24 April 2026 |
Connected in the knowledge graph
- sii-research/HACHIMI-1MDataset · cited by
Models and datasets referencing this paper
- sii-research/HACHIMI-1MDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.