Metraipolis › archive › dc_0764e99fbfbd

Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories — arXiv:2608.19621

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.19621
License (as archived): CC0-1.0
Archived: 2026-10-18T11:39:12.119Z
SHA-256 of the archived text: 028cd844e96591d41462b8fa6fdddec3420d0fdc0d1ab553229ea51ac5db8fbc
Stable URL of this page: https://metraipolis.com/documento/dc_0764e99fbfbd

How to cite

Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories — arXiv:2608.19621 — arXiv (en), https://arxiv.org/abs/2608.19621 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0764e99fbfbd (Metraipolis archive dc_0764e99fbfbd, sha256 028cd844e96591d41462b8fa6fdddec3420d0fdc0d1ab553229ea51ac5db8fbc)

BibTeX

@misc{dc0764e99fbfbd,
  title = {Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories — arXiv:2608.19621},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19621},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0764e99fbfbd; sha256 028cd844e96591d41462b8fa6fdddec3420d0fdc0d1ab553229ea51ac5db8fbc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19621. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) offer a scalable approach to social simulation, but their credibility depends on how agents are constructed. Existing methods can partially reproduce population-level patterns, yet often fail to capture human-like diversity. Our analysis shows that static-profile agents exhibit stronger demographic separation and within-group compression than humans, a pattern consistent with identity essentialism: demographic labels can encourage models to treat group-average tendencies as individual traits, homogenizing responses within groups. We argue that this limitation arises from two related factors: sparse, static agent representations and the limited ability of prompt-only memory to persistently integrate experience. Inspired by complementary memory systems, we propose LifeMem, a longitudinal memory framework that combines structured life-event retrieval with agent-specific parametric memory for experience integration. Experiments on Understanding Society with three LLMs show that LifeMem improves alignment with human data in terms of response distributions, overall and within-group diversity, and patterns of within-person response change across life stages. These findings highlight the value of longitudinal life-event memory for constructing more faithful and dynamically evolving social agents.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.19621 — 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 2026-10-18T11:38:27.901Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).