arXiv:2605.12894v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents are increasingly deployed in settings where they interact with diverse users, including those who are uncle...
arXiv:2609.01257v1 Announce Type: new Abstract: As LLM-based human simulators are increasingly used for policy, evaluation, and training, they must faithfully reproduce real behavioral patterns. Whil...
arXiv:2606. 31209v1 Announce Type: new Abstract: Interactive traffic simulation is a vital world model for autonomous driving.
arXiv:2606. 18263v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to simulate human populations via persona prompting, often under the assumptions that richer persona descriptions improve behavioral fidelity, similarly sized attribute combinations are equally simulatable, and persona definitions generalize across tasks.
The paper introduces Calibrated User Embeddings (CUE), a framework that encodes real user sessions into continuous representations and decodes them into persona commands to steer large language models (LLMs) as user simulators without additional training. CUE enables user-conditioned replay of past interactions and generates novel personas that better align with real-user success rates and failure patterns. Evaluations on the τ²‑Bench dataset show that CUE‑driven simulators commit fewer simulator‑attributed errors, more accurately reproduce real‑user failure modes, and maintain competitive user fidelity across various tasks and LLMs.
arXiv:2609.22607v1 Announce Type: new Abstract: We argue here that the current dominant practice in LLM human simulation: prompting instruction-tuned assistant language models to role-play personas,...
OmniSimulator is a training framework that enhances small language models for realistic user simulation on short‑video platforms. It structures behavior‑oriented reasoning into five dimensions, selects real user‑behavior data, and uses a teacher model to generate high‑quality reasoning traces, enabling small models to learn behavior‑relevant patterns instead of superficial correlations. The approach yields a 34.33% performance boost for Qwen3‑8B, competitive with Claude‑Sonnet‑4.5, and supports smaller‑scale, self‑hosted deployment.
arXiv:2608. 05246v1 Announce Type: new Abstract: Existing personalized LLM benchmarks primarily rely on textual personas or isolated behavioral signals, providing limited evaluation of cross-domain behavioral personalization, where responses must be grounded in heterogeneous daily-life activities.
arXiv:2606. 14199v1 Announce Type: cross Abstract: Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation.
LiveSim is an LLM-based framework designed to simulate users in multi‑agent live‑stream ecosystems. It treats users as editable behavioral hypotheses and refines them through trajectory‑grounded interactions, using discrepancies between simulated and observed trajectories to uncover missing environmental shaping effects. The framework extracts transferable environment‑behavior patterns, stores them in a collective behavioral memory, and demonstrates improved user‑level fidelity and ecosystem‑level analysis on real‑world live‑stream risk‑control data.
arXiv:2602. 12394v2 Announce Type: replace Abstract: Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific preferences and latent constraints of individual users.
UXBench Pro is a new benchmark that evaluates personalized user experience in multi-turn dialogue interactions. It contains 1,000 test instances from real user interactions across 12 task scenarios and 82 domains, each paired with a FACTORS user profile describing seven behavioral facets. The benchmark introduces a dual-perspective evaluation: a personalized User Reward Model for third‑person judgment and Sim4Eval, a user simulator for first‑person evaluation across four cognitive state dimensions, along with meta‑benchmarks URMBench and USimBench to assess evaluator reliability.