AI companions powered by large language models increasingly interact with cognition-developing users, including children and adolescents, creating risks that may accumulate over time. Existing safety evaluations largely rely on single-turn or short-session tests, which cannot capture risks that emerge only through prolonged interaction.
arXiv:2608. 02491v2 Announce Type: replace Abstract: Language models have taken on the role of a very new type of technology, by virtue of their "human-ness" and rapid integration into users' daily lives.
The paper introduces KIDBench, a benchmark designed to evaluate the safety of large language models (LLMs) for children aged 7-11. It includes realistic child queries across ten categories, single- and multi-turn prompts, and compares different prompting strategies—no cues, implicit cues, and explicit age instructions—showing that cueing improves safety scores. The study also reveals uneven safety performance across languages and cultures, and presents KIDGuardLlama, a child-safety evaluator, and KIDLlama, a child-safe response model.
arXiv:2606. 29685v1 Announce Type: new Abstract: How can we evaluate whether frontier AI systems recognize child-safety risks before they escalate into explicit harm?
How can we evaluate whether frontier AI systems recognize child-safety risks before they escalate into explicit harm? Existing child safety evaluations focus on child sexual abuse material, yet many child-safety failures begin earlier: in model assistance that helps adults manipulate, impersonate, profile, or isolate minors, and in model responses that deepen children's emotional dependence on AI systems rather than redirecting them toward human support.
The paper introduces a three-tier persona vector to generate diverse, realistic user inputs for evaluating tool-augmented LLM agents. The vector includes 23 dimensions: categorical demographics, continuous behavioral traits, and continuous emotional states, plus a query-complexity overlay. Experiments on 64,698 conversations show that these persona dimensions produce measurable differences in agent performance and realistic scenario-reactive behavior.
arXiv:2608. 06485v1 Announce Type: cross Abstract: Personality-conditioned LLM agents (PC-Agents) are increasingly used in emotional support, social simulation, and role-playing, motivating the development of lifelong agents that remain coherent over extended interactions.
arXiv:2609.22255v1 Announce Type: new Abstract: Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent...
LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated. Existing benchmarks use hand-authored scenarios and prompted simulators, aggregate empathy into one score, and overlook judge biases such as same-family favoritism and scale drift.
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.
arXiv:2608. 02046v2 Announce Type: replace-cross Abstract: LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated.
The paper introduces SIC-Agents, a self‑improving framework designed to enhance simulation for pediatric serious illness communication (SIC) training. It presents two new benchmark suites—PitfallBench and DialogueBench—that assess simulators at both turn‑level and full‑dialogue levels, specifically addressing the unique challenges of multi‑party interactions and parental distress. Experiments demonstrate that SIC‑Agents surpasses static expert prompting, and the authors release the benchmarks for broader research use.
arXiv:2607. 25057v1 Announce Type: new Abstract: As conversational AI systems become increasingly integrated into daily life, their potential effects on user well-being require ongoing attention.