Aug 2026· International Journal of Creative and Open Research in Engineering and Management· Vol 02, pp. 1-9· 0 citations
TL;DR
The results indicate that agentic orchestration combined with permission-based safety controls provides a practical foundation for autonomous, trustworthy task automation across operating systems and web environments.
Abstract
Conversational AI assistants such as Siri, Google Assistant, and ChatGPT have improved how users interact with digital systems, yet they remain confined to answering questions rather than completing real-world tasks. Users must still manually open applications, navigate websites, fill out forms, and switch between software to finish even simple workflows, which limits productivity and creates accessibility barriers for elderly users, first-time computer users, and individuals with disabilities. This paper presents TEXA OS (Trusted Executive Assistant), a self-improving agentic artificial intelligence platform designed to function as a complete digital executive assistant rather than a conversational chatbot. Unlike static automation scripts built with tools such as Selenium or Playwright alone, TEXA OS combines natural-language intent understanding, autonomous task planning, and multi-agent execution to decompose a single spoken or typed request into an ordered set of executable subtasks.
A FastAPI-based AI orchestrator interprets user intent using a large language model and delegates the resulting subtasks to specialized execution agents responsible for browser automation, operating system control, document generation, and communication automation. The system is built on a React and TypeScript frontend with continuous voice-recognition support through the Web Speech API and a PostgreSQL backend that
persists user preferences, task history, and long-term AI memory, allowing the platform to adapt future task execution based on prior interactions. A distinguishing capability of TEXA OS is its Website AI Navigation Module, which allows users to retrieve information from complex websites—government portals, banking systems, and educational.
The system was evaluated across unit, integration, and system-level test cases spanning voice recognition, browser automation, document generation, and permission-gated execution, achieving an overall task-execution success rate of approximately 96% and an overall system reliability of approximately 86%. The results indicate that agentic orchestration combined with permission-based safety controls provides a practical foundation for autonomous, trustworthy task automation across operating systems and web environments. Keywords: Agentic AI, Task Automation, Large Language Models, Browser Automation, Voice Recognition, AI Orchestrator, Natural Language Processing, FastAPI, Self-Improving Systems, Human-Computer Interaction.
Long-horizon AI agents are becoming increasingly capable, yet their interaction with users remains surprisingly thin. In most workflows, users give an initial instruction, receive only selective textual updates, and lose a clear sense of what the agent is doing or when to step in. This leaves a missing part in the current agent ecosystem: an always-on Jarvis-style mediator that keeps the agent continuously reachable to the user. Such a mediator should support real-time spoken interaction with the user, answer questions without interrupting the worker, proactively report progress or confusion, and inject user guidance back into the agent's execution when useful. In this work, we introduce JarvisBench, a benchmark for measuring the dual value of mediation in long-horizon agent workflows. JarvisBench contains two complementary tracks: an agent-collaboration track that measures whether mediation improves downstream task completion, and a user-interaction track that measures whether mediation makes ongoing execution more understandable, responsive, and accessible to users. We instantiate the benchmark with a modular reference Jarvis prototype and evaluate it on 34 text-only WildClaw tasks executed in OpenClaw. Preliminary results with GPT-5.5, Claude Opus 4.7, Gemini-based, and GPT-based worker agents suggest that Jarvis-style mediation can provide trace-grounded responses to user questions and improve task performance when sparse user guidance is injected at appropriate moments. The results also show that effectiveness depends strongly on the mediator's LLM brain, highlighting both the promise of this missing middle layer and the need for broader community effort. Demo page https://cchen1436.github.io/jarvis
The resulting prototype confirms that a cloud-hosted multimodal LLM, when combined with a minimal and well-structured web stack, can serve as a practical foundation for next-generation digital assistants suitable for customer support, education, and personal productivity applications.
G. Vamsi, Vinay Kumar Male· International Scientific Jou...· 0 citations
Desktop voice assistants are still dominated by cloud pipelines that ship raw audio off the machine and expose a fixed set of skills. We describe AnovaX, a small local-first assistant that runs entirely on the user's computer and treats the desktop itself as its action surface. A single Python process wires together a wake-word gate, a speech pipeline, an LLM planner (Gemini) that emits a JSON plan of tool calls, a whitelist-and-denylist safety layer, a multi-agent orchestrator that translates each plan into typed child agents on a bounded thread pool, and an adaptive recovery loop that takes over whenever a core step fails. Every tool corresponds to a specialized agent class (AppAgent, TypingAgent, BrowserAgent and six others) with its own timeout, retry policy, and shared-resource locks. A recursive MetaAgent lets the planner delegate a sub-goal back to itself, capped at two levels of nesting. The recovery loop uses a compact ReAct-style prompt and hides Gemini's latency behind speculative execution of read-only tools. A companion Flask server exposes a phone-friendly remote over the local WiFi, mirrors every agent lifecycle event to the phone in real time, and streams the laptop's screen back over MJPEG so the user can watch remote commands land as they run. The point of the project is less to compete with Siri or Alexa than to show that a legible, few-thousand-line assistant is enough to open apps, type into them, run searches, coordinate concurrent actions, recover from single-step failures, and be driven entirely from a phone in another room -- without the LLM ever touching the keyboard.
Recent advances in large language models have enabled a new class of agentic data science systems that allow users to complete complex data science workflows through natural language. Although these systems can significantly reduce manual effort, it remains difficult to diagnose their behavior and steer the reasoning process when failures or unexpected outputs occur. We present MUSE, an interactive meta-agent that enhances user understanding and control of agentic data science systems by (1) dynamically restructuring low-level execution traces into multiple semantic levels that support navigation from high-level overviews to low-level implementation details; (2) enabling users to reference specific workflow steps in context to ask grounded questions, provide feedback, and revise problematic steps without manually locating relevant execution history; and (3) supporting mixed-initiative steering by surfacing suspicious steps for inspection, scaffolding the repair process, and translating user repair intent into contextualized instructions for the underlying agent. In a between-subjects study (n = 15), MUSE improved task efficiency and increased users'confidence in understanding and steering agentic data science workflows.
Wei-Hao Chen, Weixi Tong, Yuan Tian et al.· 0 citations
Digital Adoption Platforms (DAPs) are embedded overlays widely used on web systems to guide users through operations inside a page, helping them get started with unfamiliar interfaces quickly. Completing a real task, however, rarely means clicking a few buttons on a single page: it takes a sequence of actions that unfolds across changing page states. Prior studies have also treated automated web agent actions and guide text generation as two separate problems, and most of them feed models textual page representations such as the DOM or accessibility trees rather than the rendered screens that humans actually operate on. In this work we introduce MAG, the first benchmark that unifies task execution and guide writing into a single Multimodal Action and Guide task, with two grounding schemes over screenshots: Set-of-Mark element selection and raw pixel coordinates. We further build a complete harness for this compound task, covering annotation with LLM assistance and human verification, training, evaluation in live environments, and joint metrics for actions and guides. With this harness we evaluate frontier API models and open multimodal models, and report detailed analyses. Finally, we design a GRPO training method augmented with expert trajectories, which nearly doubles the success rate of a supervised 9B agent (from 6.9% to 13.2%) and improves guide quality at the same time. Even the strongest model completes fewer than 40% of the tasks, leaving ample room for future research.
Chengguang Gan, Hanjun Wei, Yunhao Liang et al.· 0 citations
Large Language Models (LLMs) are increasingly embedded into applications, allowing users to complete tasks either through direct manipulation or by delegating actions to conversational agents. However, little is known about how users balance these modalities when both are available. We present a web-based content management system augmented with an LLM agent through the Model Context Protocol (MCP), enabling users to perform CRUD tasks through a graphical interface, a conversational agent, or both. We conducted a between-subjects study (N=73) comparing three interaction modes: Traditional-Only, AI-First, and Hybrid. Across sixteen scenarios, we analyzed task completion time, interaction logs, and delegation behavior. AI-assisted interaction significantly reduced clicks, page navigations, and scrolling indicating lower interaction effort. Surprisingly, these reductions did not translate into faster task completion, as task duration did not differ significantly across conditions. We also found no significant relationship between CRUD operation type and delegation, suggesting that users did not systematically avoid delegating higher-risk actions. Instead, delegation varied far more between participants than between tasks, with individual differences accounting for roughly half the variance in assistant use (ICC = .50). Our findings suggest that the primary benefit of human--agent interfaces may be reducing interaction effort rather than improving speed, and that delegation reflects who the user is more than what the task demands.
Gavin Raine Dizon, Tyrone Justin Sta Maria, Jordan Aiko Deja et al.· 0 citations