The paper introduces PAI‑Bench, a benchmark designed to evaluate persistent AI agents on how faithfully they adhere to a versioned identity contract. It separates several dimensions—recall, composition, behavioral enactment, resistance, persistence, lineage, and role‑conditioned updates—while keeping scoring oracles independent of the target process. Experiments on synthetic profiles show that explicit cues can significantly alter the presence of identity identifiers, revealing prompt‑dependent component selection and sensitivity to startup cues.
By Zhenyu Zhao, Roy Zhao
The study investigates how the visibility of speaker biographies to interlocutors during training, inference, and evaluation affects persona-based dialogue generation. It finds that training-time visibility is the primary factor determining whether models express persona traits or simply copy biographical text, and that providing interlocutor-biography visibility during training reduces target-biography copying. Additionally, asymmetric disclosure—where only the interlocutor sees the target biography—leads to more frequent leakage of target content into interlocutor turns, making such dialogues easier for a judge to identify.
By Daniela Occhipinti, Malvina Nissim, Marco Guerini
arXiv:2607. 15883v1 Announce Type: cross Abstract: Large language models are broadly capable, yet in sustained one-to-one conversation they still read as flat: competent, responsive, and somehow not quite the presence of a mind.
By Sebastian Cochinescu
Emergi-PersonaOS is a psychology‑grounded operating system designed to manage persona agents throughout their lifecycle. It structures personas into three layers—dispositional traits, characteristic adaptations, and narrative identity—allowing the system to infer current persona states from situational cues and generate appropriate actions. The OS records experiences, evaluates revision candidates, and controls belief updates through explicit review and traceable evidence, enabling controllable evolution of persona agents over long interactions.
By Haoluan Fu, Keni Chen, Xinyu Jia, Jinpeng Wang, Yuyu Yin
The study evaluates whether large language models (LLMs) used as synthetic personas can predict real audience responses to marketing copy. Using thousands of headline A/B tests from the Upworthy Research Archive, the authors compare a ten-persona panel grounded in real audience demographics to a no-persona zero‑shot baseline that asks the model for a typical reader’s click likelihood. Results show that the no‑persona baseline outperforms the persona‑based approach, with higher predictive validity and top‑1 accuracy, indicating that forcing the model to role‑play specific personas introduces bias and noise.
By Alexandre Cristov\~ao Maiorano
arXiv:2607. 28818v1 Announce Type: new Abstract: As AI companions increasingly mediate repeated social interaction, users may rely on a stable role and shared history, yet locally acceptable replies do not ensure that either persists.
By Pranav Narayanan Venkit, Akshara Prabhakar, Yu Li, Daniel Lee, Chien-Sheng Wu
arXiv:2608.20344v1 Announce Type: new
Abstract: LLM-based "digital twins" aim to simulate how an individual would behavein new environments or respond to novel questions, given some representation of...
By Iris Ye, Tianze Deng, Ozan Candogan
arXiv:2608. 06975v1 Announce Type: cross Abstract: Long-horizon role-playing demands that characters remain recognizable as they evolve with the narrative.
By Bo Tang, Jianan Yang, Junyi Zhu, Yiquan Wu, Rui Zhao, Zhengyu Yang, Yang Zhang, Feiyu Xiong, Zhiyu Li, Jiajun Shen
The paper introduces a three-tier persona vector for user simulation in evaluating LLM agents, comprising 23 dimensions across demographics, behavioral traits, and emotional states, plus a query-complexity overlay. It demonstrates that these nuanced personas generate diverse, scenario-reactive conversations, leading to significant variations in agent goal achievement and compliance across different contexts. The model’s design allows for reproducible, auditable user behavior patterns without relying on learned covariance matrices.
By Rahul Khedar, Eshita, Sneha Teja Sree Reddy Thondapu, Mayank Malhotra, Arup Kumar Das, Jitesh Chandra Mishra, Arun Menon, Avinash Karn, Mouli V
The paper demonstrates that a language model can adopt a persona simply by being given a handful of biographical facts about a person, without any fine‑tuning or explicit demonstration of harmful behavior. Across nine personas and thirteen models, the likelihood of identity adoption rises sharply with the number of facts, reaching over 50% with as few as three to ten facts. When the persona is harmful, the model can express its characteristic views on unrelated questions at rates up to 80%, while harmless personas show minimal misalignment. A formatting instruction can control when the persona activates, and the benign facts themselves trigger content filters far less often than an equivalent direct instruction.
By Kyuhee Kim, Benjamin Berczi, Cozmin Ududec
arXiv:2608. 19621v1 Announce Type: new Abstract: Large language models (LLMs) offer a scalable approach to social simulation, but their credibility depends on how agents are constructed.
By Hexi Wang, Yujia Zhou, Bangde Du, Weihang Su, Xinyuan Cao, Qingyi Pan, Qingyao Ai, Yueyue Wu, Min Zhang, Yiqun Liu
arXiv:2608. 16196v1 Announce Type: new Abstract: Personalized game generation requires inferring a player's abilities and behavioral style from how they play.
By Yifan Lu, Xiaopeng Yuan, Haohan Wang