arXiv subjects

Avinash Bhat

Publications and source records attributed to Avinash Bhat.

8 recordsLinked to original sources

arXiv2026

Look Before You Prompt, and After: Scaffolding Human-AI Collaboration in Software Tutorial Creation

With LLMs, creating software tutorials now involves steering the model's output and shaping it into a coherent, accurate learning resource, yet existing LLM tools offer writers little support for this work. By analyzing interviews with technical writers ($N=17$), we identify three requirements for how they assemble and structure multiple LLM responses, curate the context the model uses, and verify the generated content. We designed a tool called dBlocks with the following features: blocks to scope content, a context manager to edit context, and inline execution to verify code. Following a human-centered design method, we iteratively refined the design through a user study ($N=5$). In a within-subjects lab study ($N=16$) comparing dBlocks with participants' preferred workflows for LLM-assisted authoring, participants reported significantly higher confidence in the tutorials they produced with dBlocks. In addition, the tool reduced friction in verification, with writers verifying code as they drafted rather than deferring or skipping it, and helped them avoid searching long chat histories by scoping their work into blocks that kept each tutorial section and its LLM conversation together. More broadly, our work offers implications for tools that scaffold human-AI collaboration in SE workflows and shows how human-centered design can guide the development of LLM-integrated tools.

cs.SE↗

arXiv2026

"A Second Set of Eyes": The Process and Challenges of Software Documentation Review

Organizations assign documentation work to technical writers, yet the knowledge required to produce it is distributed across developers, managers, and other practitioners. Prior work has established quality criteria for judging "good" documentation, but it has not examined how practitioners bring that expertise to improve documentation quality or the challenges they face in doing so. Through semi-structured interviews with experienced technical writers ($n=31$) from different organizations, our work reveals the individual and collaborative effort required to maintain documentation quality. We identify five distinct stages of the documentation review process: self review, technical review, editorial review, play testing, and post-publication feedback. Each stage draws on practitioners with distinct expertise to address quality across content, presentation, and user experience. Our findings surface organizational and technical challenges writers face in recruiting expert reviewers, navigating development timelines, and contending with tools not specifically designed for documentation workflows. Our work positions documentation review as a crucial yet understudied site of collaborative work and opens new research and design directions for process improvement and tool support.

cs.SE↗

arXiv2025

Agentic AI for Ultra-Modern Networks: Multi-Agent Framework for RAN Autonomy and Assurance

The increasing complexity of Beyond 5G and 6G networks necessitates new paradigms for autonomy and assur- ance. Traditional O-RAN control loops rely heavily on RIC- based orchestration, which centralizes intelligence and exposes the system to risks such as policy conflicts, data drift, and unsafe actions under unforeseen conditions. In this work, we argue that the future of autonomous networks lies in a multi-agentic architecture, where specialized agents collaborate to perform data collection, model training, prediction, policy generation, verification, deployment, and assurance. By replacing tightly- coupled centralized RIC-based workflows with distributed agents, the framework achieves autonomy, resilience, explainability, and system-wide safety. To substantiate this vision, we design and evaluate a traffic steering use case under surge and drift conditions. Results across four KPIs: RRC connected users, IP throughput, PRB utilization, and SINR, demonstrate that a naive predictor-driven deployment improves local KPIs but destabilizes neighbors, whereas the agentic system blocks unsafe policies, preserving global network health. This study highlights multi- agent architectures as a credible foundation for trustworthy AI- driven autonomy in next-generation RANs.

cs.NI↗

arXiv2024

A Design Space for Intelligent and Interactive Writing Assistants

In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge by proposing a design space as a structured way to examine and explore the multidimensional space of intelligent and interactive writing assistants. Through a large community collaboration, we explore five aspects of writing assistants: task, user, technology, interaction, and ecosystem. Within each aspect, we define dimensions (i.e., fundamental components of an aspect) and codes (i.e., potential options for each dimension) by systematically reviewing 115 papers. Our design space aims to offer researchers and designers a practical tool to navigate, comprehend, and compare the various possibilities of writing assistants, and aid in the envisioning and design of new writing assistants.

cs.HC↗

arXiv2023

SUMMIT: Scaffolding OSS Issue Discussion Through Summarization

For Open Source Software (OSS) projects, discussions in Issue Tracking Systems (ITS) serve as a crucial collaboration mechanism for diverse stakeholders. However, these discussions can become lengthy and entangled, making it hard to find relevant information and make further contributions. In this work, we study the use of summarization to aid users in collaboratively making sense of OSS issue discussion threads. We reveal a complex picture of how summarization is used by issue users in practice as a strategy to help develop and manage their discussions. Grounded on the different objectives served by the summaries and the outcome of our formative study with OSS stakeholders, we identified a set of guidelines to inform the design of collaborative summarization tools for OSS issue discussions. We then developed SUMMIT, a tool that allows issue users to collectively construct summaries of different types of information discussed, as well as a set of comments representing continuous conversations within the thread. To alleviate the manual effort involved, SUMMIT uses techniques that automatically detect information types and summarize texts to facilitate the generation of these summaries. A lab user study indicates that, as the users of SUMMIT, OSS stakeholders adopted different strategies to acquire information on issue threads. Furthermore, different features of SUMMIT effectively lowered the perceived difficulty of locating information from issue threads and enabled the users to prioritize their effort. Overall, our findings demonstrated the potential of SUMMIT, and the corresponding design guidelines, in supporting users to acquire information from lengthy discussions in ITSs. Our work sheds light on key design considerations and features when exploring crowd-based and machine-learning-enabled instruments for asynchronous collaboration on complex tasks such as OSS development.

cs.HC↗

arXiv2023

Approach Intelligent Writing Assistants Usability with Seven Stages of Action

Despite the potential of Large Language Models (LLMs) as writing assistants, they are plagued by issues like coherence and fluency of the model output, trustworthiness, ownership of the generated content, and predictability of model performance, thereby limiting their usability. In this position paper, we propose to adopt Norman's seven stages of action as a framework to approach the interaction design of intelligent writing assistants. We illustrate the framework's applicability to writing tasks by providing an example of software tutorial authoring. The paper also discusses the framework as a tool to synthesize research on the interaction design of LLM-based tools and presents examples of tools that support the stages of action. Finally, we briefly outline the potential of a framework for human-LLM interaction research.

cs.HC↗

arXiv2022

Aspirations and Practice of Model Documentation: Moving the Needle with Nudging and Traceability

The documentation practice for machine-learned (ML) models often falls short of established practices for traditional software, which impedes model accountability and inadvertently abets inappropriate or misuse of models. Recently, model cards, a proposal for model documentation, have attracted notable attention, but their impact on the actual practice is unclear. In this work, we systematically study the model documentation in the field and investigate how to encourage more responsible and accountable documentation practice. Our analysis of publicly available model cards reveals a substantial gap between the proposal and the practice. We then design a tool named DocML aiming to (1) nudge the data scientists to comply with the model cards proposal during the model development, especially the sections related to ethics, and (2) assess and manage the documentation quality. A lab study reveals the benefit of our tool towards long-term documentation quality and accountability.

cs.SE↗

arXiv2022

Predictive Closed-Loop Service Automation in O-RAN based Network Slicing

Network slicing provides introduces customized and agile network deployment for managing different service types for various verticals under the same infrastructure. To cater to the dynamic service requirements of these verticals and meet the required quality-of-service (QoS) mentioned in the service-level agreement (SLA), network slices need to be isolated through dedicated elements and resources. Additionally, allocated resources to these slices need to be continuously monitored and intelligently managed. This enables immediate detection and correction of any SLA violation to support automated service assurance in a closed-loop fashion. By reducing human intervention, intelligent and closed-loop resource management reduces the cost of offering flexible services. Resource management in a network shared among verticals (potentially administered by different providers), would be further facilitated through open and standardized interfaces. Open radio access network (O-RAN) is perhaps the most promising RAN architecture that inherits all the aforementioned features, namely intelligence, open and standard interfaces, and closed control loop. Inspired by this, in this article we provide a closed-loop and intelligent resource provisioning scheme for O-RAN slicing to prevent SLA violations. In order to maintain realism, a real-world dataset of a large operator is used to train a learning solution for optimizing resource utilization in the proposed closed-loop service automation process. Moreover, the deployment architecture and the corresponding flow that are cognizant of the O-RAN requirements are also discussed.

cs.NI↗