arXiv subjects

Riya Sahni

Publications and source records attributed to Riya Sahni.

4 recordsLinked to original sources

arXiv2026

AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations

Multi-agent large language model simulations have the potential to model complex human behaviors and interactions. If the mechanics are set up properly, unanticipated and valuable social dynamics can surface. However, it is challenging to consistently enforce simulation mechanics while still allowing for rich and emergent dynamics. We present AgentDynEx, an AI system that helps set up, track, and repair simulations. Specifically, AgentDynEx introduces milestones that act as checkpoints and failure conditions that act as guardrails to ensure dynamics are relevant and mechanics are respected as the simulation progresses. It also introduces a method called nudging, where the system dynamically reflects on simulation progress and gently intervenes if it begins to deviate from intended outcomes. A technical evaluation found that nudging enables simulations to progress further without reducing the presence notable dynamics compared to simulations without nudging. A case study with AgentDynEx documented instances where real users were able to simulate lived experiences. We discuss the importance of nudging as a technique for guiding agents towards desirable behaviors while preserving their freedom of choice.

cs.MA↗

arXiv2025

Beyond Training: How Workers Discover Value in Enterprise AI

While organizations continue to invest in enterprise AI, little is known about how individual employees find valuable use cases once these tools are deployed. We present an exploratory interview study of 10 experienced U.S. professionals using M365 Copilot and interpret accounts through Rogers' Diffusion of Innovations to examine where value appears and how use cases are found and shared. Findings reveal a strong preference for informal learning methods over structured training. No participants (0/10) reported formal training as their primary way of learning; most relied on trial-and-error (8/10) and on exchanging tips with colleagues (6/10). Participants most often used M365 Copilot for note-taking/summarization, information retrieval/explanation, and writing. They also reported perceived gains in efficiency but low confidence in mastering more advanced features. The paper discusses social learning strategies and outlines implementable steps for organizations to support the discovery of high-value use cases with available enterprise AI tools.

cs.HC↗

arXiv2025

DynEx: Dynamic Code Synthesis with Structured Design Exploration for Accelerated Exploratory Programming

Recent advancements in large language models have significantly expedited the process of generating front-end code. This allows users to rapidly prototype user interfaces and ideate through code, a process known as exploratory programming. However, existing LLM code generation tools focus more on technical implementation details rather than finding the right design given a particular problem. We present DynEx, an LLM-based method for design exploration in accelerated exploratory programming. DynEx introduces a technique to explore the design space through a structured Design Matrix before creating the prototype with a modular, stepwise approach to LLM code generation. Code is generated sequentially, and users can test and approve each step before moving onto the next. A user study of 10 experts found that DynEx increased design exploration and enabled the creation of more complex and varied prototypes compared to a Claude Artifact baseline. We conclude with a discussion of the implications of design exploration for exploratory programming.

cs.HC↗

arXiv2024

An Experimental Study Of Netflix Use and the Effects of Autoplay on Watching Behaviors

Prior work on dark patterns, or manipulative online interfaces, suggests they have potentially detrimental effects on user autonomy. Dark pattern features, like those designed for attention capture, can potentially extend platform sessions beyond that users would have otherwise intended. Existing research, however, has not formally measured the quantitative effects of these features on user engagement in subscription video-on-demand platforms (SVODs). In this work, we conducted an experimental study with 76 Netflix users in the US to analyze the impact of a specific attention capture feature, autoplay, on key viewing metrics. We found that disabling autoplay on Netflix significantly reduced key content consumption aggregates, including average daily watching and average session length, partly filling the evidentiary gap regarding the empirical effects of dark pattern interfaces. We paired the experimental analysis with users' perceptions of autoplay and their viewing behaviors, finding that participants were split on whether the effects of autoplay outweigh its benefits, albeit without knowledge of the study findings. Our findings strengthen the broader argument that manipulative interface designs can and do affect users in potentially damaging ways, highlighting the continued need for considering user well-being and varied preferences in interface design.

cs.HC↗