arXiv subjects

Xiao

Publications and source records attributed to Xiao.

3 recordsLinked to original sources

arXiv2026

MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations

Long-horizon, multi-agent language model (LM) simulations are widely proposed for studying social behavior, yet instruments to measure whether persona-conditioned agents maintain identity fidelity under sustained pressure are lacking. We present MicroVerse, a behavioral-science instrument that measures identity drift in generative agents. Agents carry an immutable "soul file" (core values, moral boundaries, personality, goals) and inhabit a resource-scarce 50 x 50 environment where water is a non-respawning survival constraint. Scarcity is operationalized via a per-tick existence-cost gradient. The eight-verb action space maps directly to moral boundaries (trade, talk, attack, scavenge). Using a three-layer memory architecture, agents periodically revise a mutable current identity against their immutable original soul via importance-triggered reflection. To mitigate survivor bias, MicroVerse decouples measurement from behavior using uniform longitudinal engine snapshots every N ticks alongside a forced-end snapshot of all living and dead agents. Identity drift is scored offline using a paraphrase-aware, value-anchored, multi-register diff rather than raw cosine similarity. We evaluate the instrument via a controlled seed run (n = 25) and a reflection-threshold sweep (thresholds {40, 80, 150}) to determine if drift dynamics are gate artifacts or threshold-robust properties. We report two primary findings: (1) Anti-self-deception emerges unprompted as the single largest semantic category of identity modification (27 of 111 added boundaries, 24%). (2) The system is threshold-robust; lower gates accelerate and increase revision frequency but preserve drift direction. All empirical results are strictly preliminary existence proofs and effect shapes (one model, one seed per arm, n = 25) rather than statistical significance claims.

cs.CL↗

arXiv2024

Modeling Battery Electric Vehicle Users' Charging Decisions in Scenarios with Both Time-Related and Distance-Related Anxiety

As one of the most promising alternatives to internal combustion engine vehicles, battery electric vehicles (BEVs) have become increasingly prevalent in recent years. However, range anxiety is still a major concern among BEV users or potential users in recent years. The social-psychological factors were found to be associated with range anxiety, but how the charging decisions are affected by range anxiety is still unclear. Thus, in our study, through an online questionnaire issued in mainland China, we collected 230 participants' charging decisions in 60 range-anxiety-inducing scenarios in which both distance-related, and time-related anxiety co-existed. Then, an interpretable machine learning (ML) approach with the Shapley Additive Explanations method was used to model BEV users' charging decisions in these scenarios. To further explore users' decision-making mechanisms, a Bayesian-Network-regression mixed approach was used to model the inner topological structure among the factors influencing users' decisions. We find that both time-related and distance-related factors can affect users' charging decisions, but the influence of waiting time is softer compared to the BEV range. Users' charging decisions can also be moderated by users' psychological states (i.e., range anxiety level and trust in range estimation system), individual differences (i.e., age and personality), and BEV using experience (i.e., driving mileage, display mileage and range estimation cycle of range estimation system), of which, the range anxiety level is more directly related with users' charging decisions. Findings from this study can provide insights into the optimization of charge station distribution and customization of the charging recommendation system.

cs.HC↗

arXiv2022

Nonlinear multi-frequency phonon lasers with active levitated optomechanics

Phonon lasers, exploiting coherent amplifications of phonons, have been a cornerstone for exploring nonlinear phononics, imaging nanomaterial structures, and operating phononic devices. Very recently, by levitating a nanosphere in an optical tweezer, a single-mode phonon laser governed by dispersive optomechanical coupling has been demonstrated, assisted by alternating mechanical nonlinear cooling and linear heating. Such levitated optomechanical (LOM) devices, with minimal noises in high vacuum, can allow flexible control of large-mass objects without any internal discrete energy levels. However, untill now, it is still elusive to realize phonon lasing with levitated microscale objects, due to much stronger optical scattering losses. Here, by employing a Yb3+-doped active system, we report the first experiment on nonlinear multi-frequency phonon lasers with a micro-size sphere governed instead by dissipative LOM coupling. In this work, active gain plays a key role since not only 3-order enhancement can be achieved for the amplitude of the fundamental-mode phonon lasing, compared with the passive device, but also nonlinear mechanical harmonics can emerge spontaneously above the lasing threshold. Furthermore, for the first time, coherent correlations of phonons are observed for both the fundamental mode and its harmonics. Our work drives the field of LOM technology into a new regime where it becomes promising to engineer collective motional properties of typical micro-size objects, such as atmospheric particulates and living cells, for a wide range of applications in e.g., acoustic sensing, gravimetry, and inertial navigation.

physics.optics↗