arXiv subjects

Matheus Kunzler Maldaner

Publications and source records attributed to Matheus Kunzler Maldaner.

7 recordsLinked to original sources

arXiv2026

SentinelBench: A Benchmark for Long-Running Monitoring Agents

AI agents are increasingly asked to carry out work that spans minutes, hours, or longer. Yet the default model of agent behavior is continuous action: issuing tool calls, refreshing pages, searching for alternatives, or otherwise trying to force progress. This is the wrong approach for many long-running tasks, which are better served by a strategy of sustained attention. Instead, agents should monitor an environment, notice when an external event makes progress possible, then respond promptly without wasting resources while waiting. To measure progress on this class of tasks, we introduce SentinelBench, an open-source benchmark for time-evolving monitoring tasks. SentinelBench contains 100 tasks across 10 synthetic web environments, including email, calendars, finance, professional networking, and entertainment. Each environment exposes a live web interface and replays a scripted sequence of events, requiring agents to navigate and reason about web pages whose state shifts underfoot. SentinelBench measures task completion, reaction time, and resource use, exposing the tradeoff between responsiveness and cost. We report results across three models and two browser-agent harnesses, establishing performance baselines for future comparison and demonstrating how agent design choices can dramatically impact key metrics. Together, these results show that SentinelBench distinguishes meaningful differences in agent behavior.

cs.AI↗

arXiv2026

Plato's Cave: A Human-Centered Research Verification System

The growing publication rate of research papers has created an urgent need for better ways to fact-check information, assess writing quality, and identify unverifiable claims. We present Plato's Cave as an open-source, human-centered research verification system that (i) creates a directed acyclic graph (DAG) from a document, (ii) leverages web agents to assign credibility scores to nodes and edges from the DAG, and (iii) gives a final score by interpreting and evaluating the paper's argumentative structure. We report the system implementation and results on a collected dataset of 104 research papers.

cs.CL↗

arXiv2026

MM-SCALE: Grounded Multimodal Moral Reasoning via Scalar Judgment and Listwise Alignment

Vision-Language Models (VLMs) continue to struggle to make morally salient judgments in multimodal and socially ambiguous contexts. Prior works typically rely on binary or pairwise supervision, which often fail to capture the continuous and pluralistic nature of human moral reasoning. We present MM-SCALE (Multimodal Moral Scale), a large-scale dataset for aligning VLMs with human moral preferences through 5-point scalar ratings and explicit modality grounding. Each image-scenario pair is annotated with moral acceptability scores and grounded reasoning labels by humans using an interface we tailored for data collection, enabling listwise preference optimization over ranked scenario sets. By moving from discrete to scalar supervision, our framework provides richer alignment signals and finer calibration of multimodal moral reasoning. Experiments show that VLMs fine-tuned on MM-SCALE achieve higher ranking fidelity and more stable safety calibration than those trained with binary signals.

cs.CV↗

arXiv2025

Seeing Twice: How Side-by-Side T2I Comparison Changes Auditing Strategies

While generative AI systems have gained popularity in diverse applications, their potential to produce harmful outputs limits their trustworthiness and utility. A small but growing line of research has explored tools and processes to better engage non-AI expert users in auditing generative AI systems. In this work, we present the design and evaluation of MIRAGE, a web-based tool exploring a "contrast-first" workflow that allows users to pick up to four different text-to-image (T2I) models, view their images side-by-side, and provide feedback on model performance on a single screen. In our user study with fifteen participants, we used four predefined models for consistency, with only a single model initially being shown. We found that most participants shifted from analyzing individual images to general model output patterns once the side-by-side step appeared with all four models; several participants coined persistent "model personalities" (e.g., cartoonish, saturated) that helped them form expectations about how each model would behave on future prompts. Bilingual participants also surfaced a language-fidelity gap, as English prompts produced more accurate images than Portuguese or Chinese, an issue often overlooked when dealing with a single model. These findings suggest that simple comparative interfaces can accelerate bias discovery and reshape how people think about generative models.

cs.HC↗

arXiv2025

Magentic-UI: Towards Human-in-the-loop Agentic Systems

AI agents powered by large language models are increasingly capable of autonomously completing complex, multi-step tasks using external tools. Yet, they still fall short of human-level performance in most domains including computer use, software development, and research. Their growing autonomy and ability to interact with the outside world, also introduces safety and security risks including potentially misaligned actions and adversarial manipulation. We argue that human-in-the-loop agentic systems offer a promising path forward, combining human oversight and control with AI efficiency to unlock productivity from imperfect systems. We introduce Magentic-UI, an open-source web interface for developing and studying human-agent interaction. Built on a flexible multi-agent architecture, Magentic-UI supports web browsing, code execution, and file manipulation, and can be extended with diverse tools via Model Context Protocol (MCP). Moreover, Magentic-UI presents six interaction mechanisms for enabling effective, low-cost human involvement: co-planning, co-tasking, multi-tasking, action guards, and long-term memory. We evaluate Magentic-UI across four dimensions: autonomous task completion on agentic benchmarks, simulated user testing of its interaction capabilities, qualitative studies with real users, and targeted safety assessments. Our findings highlight Magentic-UI's potential to advance safe and efficient human-agent collaboration.

cs.AI↗

arXiv2025

MIRAGE: Multi-model Interface for Reviewing and Auditing Generative Text-to-Image AI

While generative AI systems have gained popularity in diverse applications, their potential to produce harmful outputs limits their trustworthiness and usability in different applications. Recent years have seen growing interest in engaging diverse AI users in auditing generative AI that might impact their lives. To this end, we propose MIRAGE as a web-based tool where AI users can compare outputs from multiple AI text-to-image (T2I) models by auditing AI-generated images, and report their findings in a structured way. We used MIRAGE to conduct a preliminary user study with five participants and found that MIRAGE users could leverage their own lived experiences and identities to surface previously unnoticed details around harmful biases when reviewing multiple T2I models' outputs compared to reviewing only one.

cs.HC↗

arXiv2025

eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networks

Constraining deep neural networks (DNNs) to learn individual logic types per node, as performed using the DiffLogic network architecture, opens the door to model-specific explanation techniques that quell the complexity inherent to DNNs. Inspired by principles of circuit analysis from computer engineering, this work presents an algorithm (eXpLogic) for producing saliency maps which explain input patterns that activate certain functions. The eXpLogic explanations: (1) show the exact set of inputs responsible for a decision, which helps interpret false negative and false positive predictions, (2) highlight common input patterns that activate certain outputs, and (3) help reduce the network size to improve class-specific inference. To evaluate the eXpLogic saliency map, we introduce a metric that quantifies how much an input changes before switching a model's class prediction (the SwitchDist) and use this metric to compare eXpLogic against the Vanilla Gradients (VG) and Integrated Gradient (IG) methods. Generally, we show that eXpLogic saliency maps are better at predicting which inputs will change the class score. These maps help reduce the network size and inference times by 87\% and 8\%, respectively, while having a limited impact (-3.8\%) on class-specific predictions. The broader value of this work to machine learning is in demonstrating how certain DNN architectures promote explainability, which is relevant to healthcare, defense, and law.

cs.LG↗