Metraipolis › archive › dc_ebd8a5042efa

To Align Long, Plan Short: Simulating Diverse Profile-Aligned Students by Realizing Short-Term Plans in Long-Horizon Learning Environments — arXiv:2611.02002

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02002
License (as archived): CC0-1.0
Archived: 2026-11-03T10:52:49.811Z
SHA-256 of the archived text: ee797cb67b5a9585bcfaaf2763a75a502b902cb37951bce116fc5106e931bbe0
Stable URL of this page: https://metraipolis.com/documento/dc_ebd8a5042efa

How to cite

To Align Long, Plan Short: Simulating Diverse Profile-Aligned Students by Realizing Short-Term Plans in Long-Horizon Learning Environments — arXiv:2611.02002 — arXiv (en), https://arxiv.org/abs/2611.02002 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebd8a5042efa (Metraipolis archive dc_ebd8a5042efa, sha256 ee797cb67b5a9585bcfaaf2763a75a502b902cb37951bce116fc5106e931bbe0)

BibTeX

@misc{dcebd8a5042efa,
  title = {To Align Long, Plan Short: Simulating Diverse Profile-Aligned Students by Realizing Short-Term Plans in Long-Horizon Learning Environments — arXiv:2611.02002},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02002},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebd8a5042efa; sha256 ee797cb67b5a9585bcfaaf2763a75a502b902cb37951bce116fc5106e931bbe0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02002. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Simulated students offer a scalable way to test learning platforms and AI tutors before deployment with real students and to augment scarce data for studying learning at scale. Existing LLM-based simulators primarily target short, language-centered interactions. In open-ended learning environments, however, student behavior emerges from patterns across long-horizon interaction trajectories, where turn-level prompting can drift from an assigned behavior profile. We introduce ALPS (Align Long-term by Planning Short-term), a hierarchical simulated student conditioned on observable, environment-specific behavior profiles. Rather than selecting every action independently, ALPS alternates between planning profile-aligned task segments and generating the corresponding actions. We evaluate ALPS in both data-sufficient and data-scarce settings, where supervision comes either from real student trajectories or from a teacher LLM. Across both settings, we compare in-context learning (ICL), supervised fine-tuning (SFT), reward-ranked fine-tuning (RAFT), and their sequential combination (SFT followed by RAFT). Experiments in an inquiry-based physics game and a pharmacy simulation evaluate behavioral density and coverage against held-out real data, and profile consistency using a human-aligned LLM judge. Across both settings, ALPS consistently outperforms turn-level generation, achieving comparable density and judge pass rates under scarce supervision, although coverage remains lower. These results show that hierarchical planning enables faithful, profile-aligned simulation over long interaction horizons, even with limited real student data.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2611.02002 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:49:38.329Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).