Search arXiv⌕ Search

arXiv subjects

Zexuan Liu

Publications and source records attributed to Zexuan Liu.

8 recordsLinked to original sources

What to Delegate, What to Preserve: Human Preferences for Agentic AI Across Everyday Life and Work

AI agents can execute multi-step tasks on users' behalf, yet the boundaries of acceptable delegation remain unclear. We report a scenario-based survey of 289 U.S. adults with prior AI experience covering 45 use cases across nine life domains. Each respondent evaluated one scenario per domain, producing repeated measures of automation preference, trust, collaboration, AI leadership, privacy concern, and willingness to pay. Automation preferences varied substantially across domains. Generalized estimating equation models showed that greater trust in the AI agent, desired AI leadership, prior task-specific AI use, and anticipated financial savings were associated with greater automation preference. In contrast, concerns that automation would reduce personal fulfillment predicted lower automation preference. Open-ended responses further revealed a preference for bounded autonomy, with participants often favoring substantial AI execution while retaining human involvement, oversight, or final authority. We argue that delegation is best understood as a configuration of execution, collaboration, leadership, and authority.

cs.AI↗

Sequential Conformal Calibration under Recursive Selection

Conformal prediction provides finite-sample, distribution-free coverage guarantees that can support decision-making in specific settings. In multistage problems, earlier decisions determine the populations relevant to later calibration. When later scores are refit using earlier calibration results, reusing those cases for ranking need not preserve exchangeability with a surviving test case. We study sequential conformal calibration with a fresh fold at each stage: conditional on earlier folds, the selected fold scores and the surviving test score are exchangeable. This yields finite-sample coverage guarantees for every prefix of the decision sequence. For atomless survivor score distributions, we derive a universal Binomial-thinned Beta chain for the realized coverage process. Its law depends only on fold sizes and target levels, even under predictable refitting, and yields exact coverage slack, abstention probabilities, and calibration-conditional guarantees. We further characterize the tradeoff between freshness and data reuse. For fixed scores, strict-survivor reuse is exactly valid. For adaptive scores refit using past calibration data, reusing survivors can incur worst-case rank loss, while blocked designs provide an intermediate option between full reuse and stagewise fresh folds. As a case study, we apply the framework to serial multi-echelon inventory problem and propose a sequential conditional-quantile formulation. Each stock level is learned as a context-dependent quantile of cumulative demand among scenarios satisfying earlier no-backlog constraints. We connect these targets to common-shift stationarity and derive decision-level implications for the resulting calibrated policies. In a three-echelon simulation, fresh-fold refitting achieves 81.98% final-prefix coverage against an 81.82% target while reducing mean cost by 5.5% relative to the Bonferroni baseline.

stat.ME↗

Curating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback

At the start of every session, LLM agents load a fixed context file, such as $\texttt{AGENTS.md}$. Each loaded token in the file is charged again in every later round of the session, and these files can degrade performance as they grow in size. However, in practice, human or automated curators usually grow these files by appending. We formulate context curation as a capacitated assortment problem. Instructions consume tokens under a finite attention capacity; adding an instruction never raises the compliance of the others, while retained instructions incur a per-session setup cost. We prove an upper bound on the optimal file size, regardless of the number of available candidate instructions, and that appending every instruction with positive standalone value can be arbitrarily worse in net value than selecting an optimal subset. A token budget also limits the loss when the token price is underestimated. We then examine what can be learned from past sessions and how this information can guide decisions to add or remove instructions. Feedback is inherently censored: the benefits and harms of loaded instructions are observable, whereas missing instructions generate feedback only when their absence causes harm. In this setting, we show that deleting instructions ignored by agents can inevitably remove helpful ones. We characterize how much evidence should be collected before adding an instruction. Besides, we bound regret when human reviewers can inspect only a limited number of edits per period. Empirical experiments further show that irrelevant rules drawn from real context files reduce language-model compliance.

cs.AI↗

Understanding Optical Anisotropy in Multilayer γ-InSe and ε-GaSe

Low-dimensional media have exhibited optical anisotropy that is unachievable in traditional 3D media due to the asymmetry of their strong, in-plane covalent bonds and weak out-of-plane van der Waals interactions. As a result, 2D media are promising building blocks for ultrathin devices such as polarimeters, polarized light sources, and active polarizers. III-VI semiconductors possess a rare property in the class of multilayered semiconductors, which is that their fundamental excitons are oriented out-of-plane. This allows them to exhibit phenomena such as transparency in the visible range while also being emissive in the visible and near-infrared ranges. Here, we report the first experimental values for the anisotropic refractive indices of γ-InSe and ε-GaSe, and we observe the effects of the out-of-plane excitons on the c-axis refractive index. It is found that both materials exhibit moderate optical anisotropy for multilayered semiconductors. The complex, anisotropic refractive index of γ-InSe and ε-GaSe enables the accurate simulation of these media, allowing for the design of high-performance, ultra-compact optoelectronic devices.

physics.optics↗

User Negotiations of Authenticity, Ownership, and Governance on AI-Generated Video Platforms: Evidence from Sora

As AI-generated video platforms rapidly advance, ethical challenges such as copyright infringement emerge. This study examines how users make sense of AI-generated videos on OpenAI's Sora by conducting a qualitative content analysis of user comments. Through a thematic analysis, we identified four dynamics that characterize how users negotiate authenticity, authorship, and platform governance on Sora. First, users acted as critical evaluators of realism, assessing micro-details such as lighting, shadows, fluid motion, and physics to judge whether AI-generated scenes could plausibly exist. Second, users increasingly shifted from passive viewers to active creators, expressing curiosity about prompts, techniques, and creative processes. Text prompts were perceived as intellectual property, generating concerns about plagiarism and remixing norms. Third, users reported blurred boundaries between real and synthetic media, worried about misinformation, and even questioned the authenticity of other commenters, suspecting bot-generated engagement. Fourth, users contested platform governance: some perceived moderation as inconsistent or opaque, while others shared tactics for evading prompt censorship through misspellings, alternative phrasing, emojis, or other languages. Despite this, many users also enforced ethical norms by discouraging the misuse of real people's images or disrespectful content. Together, these patterns highlighted how AI-mediated platforms complicate notions of reality, creativity, and rule-making in emerging digital ecosystems. Based on the findings, we discuss governance challenges in Sora and how user negotiations inform future platform governance.

cs.HC↗

xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations

We introduce xbench, a dynamic, profession-aligned evaluation suite designed to bridge the gap between AI agent capabilities and real-world productivity. While existing benchmarks often focus on isolated technical skills, they may not accurately reflect the economic value agents deliver in professional settings. To address this, xbench targets commercially significant domains with evaluation tasks defined by industry professionals. Our framework creates metrics that strongly correlate with productivity value, enables prediction of Technology-Market Fit (TMF), and facilitates tracking of product capabilities over time. As our initial implementations, we present two benchmarks: Recruitment and Marketing. For Recruitment, we collect 50 tasks from real-world headhunting business scenarios to evaluate agents' abilities in company mapping, information retrieval, and talent sourcing. For Marketing, we assess agents' ability to match influencers with advertiser needs, evaluating their performance across 50 advertiser requirements using a curated pool of 836 candidate influencers. We present initial evaluation results for leading contemporary agents, establishing a baseline for these professional domains. Our continuously updated evalsets and evaluations are available at https://xbench.org.

cs.LG↗

Stretch with Stretch: Physical Therapy Exercise Games Led by a Mobile Manipulator

Physical therapy (PT) is a key component of many rehabilitation regimens, such as treatments for Parkinson's disease (PD). However, there are shortages of physical therapists and adherence to self-guided PT is low. Robots have the potential to support physical therapists and increase adherence to self-guided PT, but prior robotic systems have been large and immobile, which can be a barrier to use in homes and clinics. We present Stretch with Stretch (SWS), a novel robotic system for leading stretching exercise games for older adults with PD. SWS consists of a compact and lightweight mobile manipulator (Hello Robot Stretch RE1) that visually and verbally guides users through PT exercises. The robot's soft end effector serves as a target that users repetitively reach towards and press with a hand, foot, or knee. For each exercise, target locations are customized for the individual via a visually estimated kinematic model, a haptically estimated range of motion, and the person's exercise performance. The system includes sound effects and verbal feedback from the robot to keep users engaged throughout a session and augment physical exercise with cognitive exercise. We conducted a user study for which people with PD (n=10) performed 6 exercises with the system. Participants perceived the SWS to be useful and easy to use. They also reported mild to moderate perceived exertion (RPE).

cs.RO↗

Approaching quantum-limited metrology with imperfect detectors by using weak-value amplification

Weak value amplification (WVA) is a metrological protocol that amplifies ultra-small physical effects. However, the amplified outcomes necessarily occur with highly suppressed probabilities, leading to the extensive debate on whether the overall measurement precision is improved in comparison to that of conventional measurement (CM). Here, we experimentally demonstrate the unambiguous advantages of WVA that overcome practical limitations including noise and saturation of photo-detection and maintain a shot-noise-scaling precision for a large range of input light intensity well beyond the dynamic range of the photodetector. The precision achieved by WVA is six times higher than that of CM in our setup. Our results clear the way for the widespread use of WVA in applications involving the measurement of small signals including precision metrology and commercial sensors.

quant-ph↗