智能体
arxiv.org ·
用纵向生命轨迹缓解 LLM 智能体中的身份本质主义
该论文指出静态画像智能体存在比人类更强的人口统计分离与组内压缩现象，即身份本质主义：人口标签使模型把群体平均倾向当作个体特质，导致组内回答同质化。作者认为原因在于智能体表示稀疏静态，且仅靠提示的记忆难以持续整合经验。为此提出 LifeMem，一个结合结构化生活事件检索与智能体专属参数化记忆的纵向记忆框架。在 Understanding Society 数据集上对三个 LLM 的实验显示，LifeMem 在响应分布、整体与组内多样性以及个体跨人生阶段的响应变化模式上更贴近人类数据。
AI推荐理由 arXiv 正式论文（v3，2026-09-22 修订），作者与摘要信息完整，事实明确、信息密度高。核心新信息是提出 LifeMem 纵向记忆框架，用结构化生活事件检索加智能体专属参数化记忆来缓解 LLM 智能体的身份本质主义（人口统计标签导致群体内回答同质化），并在 Understanding Society 数据集上用三个 LLM 验证其在响应分布、组内多样性和人生阶段内变化模式上更贴近人类数据。局限在于摘要未给出具体指标数值，且属于社会模拟场景，对通用 Agent 能力的迁移价值尚待验证。
72
正文
Computer Science > Computation and Language
arXiv:2608.19621 (cs)
[Submitted on 20 Aug 2026 (v1), last revised 22 Sep 2026 (this version, v3)]
Title:Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories
Authors:Hexi Wang, Yujia Zhou, Bangde Du, Weihang Su, Xinyuan Cao, Qingyi Pan, Qingyao Ai, Yueyue Wu, Min Zhang, Yiqun Liu
View a PDF of the paper titled Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories, by Hexi Wang and 9 other authors
View PDF
HTML (experimental)
Abstract: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.
Comments:
Subjects:
Computation and Language (cs.CL)
MSC classes:
68T50
ACM classes:
I.2.7
Cite as:
arXiv:2608.19621 [cs.CL]
(or
arXiv:2608.19621v3 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.19621
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Hexi Wang [view email]
[v1]
Thu, 20 Aug 2026 04:13:11 UTC (1,685 KB)
[v2]
Fri, 21 Aug 2026 09:45:31 UTC (1,686 KB)
[v3]
Tue, 22 Sep 2026 15:16:08 UTC (1,483 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories, by Hexi Wang and 9 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new
|
recent
| 2026-08
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)