Implement automated smoke testing using Amazon Nova Act headless modeArtificial Intelligence This post shows how to implement automated smoke testing using Amazon Nova Act headless mode in CI/CD pipelines. We use SauceDemo, a sample ecommerce application, as our target for demonstration. We demonstrate setting up Amazon Nova Act for headless browser automation in CI/CD environments and creating smoke tests that validate key user workflows. We then show how to implement parallel execution to maximize testing efficiency, configure GitLab CI/CD for automatic test execution on every deployment, and apply best practices for maintainable and scalable test automation.
This post shows how to implement automated smoke testing using Amazon Nova Act headless mode in CI/CD pipelines. We use SauceDemo, a sample ecommerce application, as our target for demonstration. We demonstrate setting up Amazon Nova Act for headless browser automation in CI/CD environments and creating smoke tests that validate key user workflows. We then show how to implement parallel execution to maximize testing efficiency, configure GitLab CI/CD for automatic test execution on every deployment, and apply best practices for maintainable and scalable test automation. Read More
The Machine Learning “Advent Calendar” Day 10: DBSCAN in ExcelTowards Data Science DBSCAN shows how far we can go with a very simple idea: count how many neighbors live close to each point.
It finds clusters and marks anomalies without any probabilistic model, and it works beautifully in Excel.
But because it relies on one fixed radius, HDBSCAN is needed to make the method robust on real data.
The post The Machine Learning “Advent Calendar” Day 10: DBSCAN in Excel appeared first on Towards Data Science.
DBSCAN shows how far we can go with a very simple idea: count how many neighbors live close to each point.
It finds clusters and marks anomalies without any probabilistic model, and it works beautifully in Excel.
But because it relies on one fixed radius, HDBSCAN is needed to make the method robust on real data.
The post The Machine Learning “Advent Calendar” Day 10: DBSCAN in Excel appeared first on Towards Data Science. Read More
How to Maximize Agentic Memory for Continual LearningTowards Data Science Learn how to become an effective engineer with continual learning LLMs
The post How to Maximize Agentic Memory for Continual Learning appeared first on Towards Data Science.
Learn how to become an effective engineer with continual learning LLMs
The post How to Maximize Agentic Memory for Continual Learning appeared first on Towards Data Science. Read More
Finding Meaningful Work in the Age of Vibe CodingKDnuggets Vibe coding has devalued coding. Is there any meaningful work still left for us?
Vibe coding has devalued coding. Is there any meaningful work still left for us? Read More
Don’t Build an ML Portfolio Without These ProjectsTowards Data Science What recruiters are looking for in machine learning portfolios
The post Don’t Build an ML Portfolio Without These Projects appeared first on Towards Data Science.
What recruiters are looking for in machine learning portfolios
The post Don’t Build an ML Portfolio Without These Projects appeared first on Towards Data Science. Read More
5 Free Tools to Experiment with LLMs in Your BrowserKDnuggets Discover five free tools that let you run and test large language models directly in your browser without any setup.
Discover five free tools that let you run and test large language models directly in your browser without any setup. Read More
Perplexity: AI agents are taking over complex enterprise tasksAI News New adoption data from Perplexity reveals how AI agents are driving workflow efficiency gains by taking over complex enterprise tasks. For the past year, the technology sector has operated under the assumption that the next evolution of generative AI would advance beyond conversation into action. While Large Language Models (LLMs) serve as a reasoning engine,
The post Perplexity: AI agents are taking over complex enterprise tasks appeared first on AI News.
New adoption data from Perplexity reveals how AI agents are driving workflow efficiency gains by taking over complex enterprise tasks. For the past year, the technology sector has operated under the assumption that the next evolution of generative AI would advance beyond conversation into action. While Large Language Models (LLMs) serve as a reasoning engine,
The post Perplexity: AI agents are taking over complex enterprise tasks appeared first on AI News. Read More
Toward an AI Reasoning-Enabled System for Patient-Clinical Trial Matchingcs.AI updates on arXiv.org arXiv:2512.08026v1 Announce Type: new
Abstract: Screening patients for clinical trial eligibility remains a manual, time-consuming, and resource-intensive process. We present a secure, scalable proof-of-concept system for Artificial Intelligence (AI)-augmented patient-trial matching that addresses key implementation challenges: integrating heterogeneous electronic health record (EHR) data, facilitating expert review, and maintaining rigorous security standards. Leveraging open-source, reasoning-enabled large language models (LLMs), the system moves beyond binary classification to generate structured eligibility assessments with interpretable reasoning chains that support human-in-the-loop review. This decision support tool represents eligibility as a dynamic state rather than a fixed determination, identifying matches when available and offering actionable recommendations that could render a patient eligible in the future. The system aims to reduce coordinator burden, intelligently broaden the set of trials considered for each patient and guarantee comprehensive auditability of all AI-generated outputs.
arXiv:2512.08026v1 Announce Type: new
Abstract: Screening patients for clinical trial eligibility remains a manual, time-consuming, and resource-intensive process. We present a secure, scalable proof-of-concept system for Artificial Intelligence (AI)-augmented patient-trial matching that addresses key implementation challenges: integrating heterogeneous electronic health record (EHR) data, facilitating expert review, and maintaining rigorous security standards. Leveraging open-source, reasoning-enabled large language models (LLMs), the system moves beyond binary classification to generate structured eligibility assessments with interpretable reasoning chains that support human-in-the-loop review. This decision support tool represents eligibility as a dynamic state rather than a fixed determination, identifying matches when available and offering actionable recommendations that could render a patient eligible in the future. The system aims to reduce coordinator burden, intelligently broaden the set of trials considered for each patient and guarantee comprehensive auditability of all AI-generated outputs. Read More
From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Productioncs.AI updates on arXiv.org arXiv:2510.23856v2 Announce Type: replace
Abstract: Agents are rapidly advancing in automating digital work, but enterprises face a harder challenge: moving beyond prototypes to deployed systems that deliver measurable business value. This path is complicated by fragmented frameworks, slow development, and the absence of standardized evaluation practices. Generalist agents have emerged as a promising direction, excelling on academic benchmarks and offering flexibility across task types, applications, and modalities. Yet, evidence of their use in production enterprise settings remains limited. This paper reports IBM’s experience developing and piloting the Computer Using Generalist Agent (CUGA), which has been open-sourced for the community (https://github.com/cuga-project/cuga-agent). CUGA adopts a hierarchical planner–executor architecture with strong analytical foundations, achieving state-of-the-art performance on AppWorld and WebArena. Beyond benchmarks, it was evaluated in a pilot within the Business-Process-Outsourcing talent acquisition domain, addressing enterprise requirements for scalability, auditability, safety, and governance. To support assessment, we introduce BPO-TA, a 26-task benchmark spanning 13 analytics endpoints. In preliminary evaluations, CUGA approached the accuracy of specialized agents while indicating potential for reducing development time and cost. Our contribution is twofold: presenting early evidence of generalist agents operating at enterprise scale, and distilling technical and organizational lessons from this initial pilot. We outline requirements and next steps for advancing research-grade architectures like CUGA into robust, enterprise-ready systems.
arXiv:2510.23856v2 Announce Type: replace
Abstract: Agents are rapidly advancing in automating digital work, but enterprises face a harder challenge: moving beyond prototypes to deployed systems that deliver measurable business value. This path is complicated by fragmented frameworks, slow development, and the absence of standardized evaluation practices. Generalist agents have emerged as a promising direction, excelling on academic benchmarks and offering flexibility across task types, applications, and modalities. Yet, evidence of their use in production enterprise settings remains limited. This paper reports IBM’s experience developing and piloting the Computer Using Generalist Agent (CUGA), which has been open-sourced for the community (https://github.com/cuga-project/cuga-agent). CUGA adopts a hierarchical planner–executor architecture with strong analytical foundations, achieving state-of-the-art performance on AppWorld and WebArena. Beyond benchmarks, it was evaluated in a pilot within the Business-Process-Outsourcing talent acquisition domain, addressing enterprise requirements for scalability, auditability, safety, and governance. To support assessment, we introduce BPO-TA, a 26-task benchmark spanning 13 analytics endpoints. In preliminary evaluations, CUGA approached the accuracy of specialized agents while indicating potential for reducing development time and cost. Our contribution is twofold: presenting early evidence of generalist agents operating at enterprise scale, and distilling technical and organizational lessons from this initial pilot. We outline requirements and next steps for advancing research-grade architectures like CUGA into robust, enterprise-ready systems. Read More
Empowerment Gain and Causal Model Construction: Children and adults are sensitive to controllability and variability in their causal interventionscs.AI updates on arXiv.org arXiv:2512.08230v1 Announce Type: new
Abstract: Learning about the causal structure of the world is a fundamental problem for human cognition. Causal models and especially causal learning have proved to be difficult for large pretrained models using standard techniques of deep learning. In contrast, cognitive scientists have applied advances in our formal understanding of causation in computer science, particularly within the Causal Bayes Net formalism, to understand human causal learning. In the very different tradition of reinforcement learning, researchers have described an intrinsic reward signal called “empowerment” which maximizes mutual information between actions and their outcomes. “Empowerment” may be an important bridge between classical Bayesian causal learning and reinforcement learning and may help to characterize causal learning in humans and enable it in machines. If an agent learns an accurate causal world model, they will necessarily increase their empowerment, and increasing empowerment will lead to a more accurate causal world model. Empowerment may also explain distinctive features of childrens causal learning, as well as providing a more tractable computational account of how that learning is possible. In an empirical study, we systematically test how children and adults use cues to empowerment to infer causal relations, and design effective causal interventions.
arXiv:2512.08230v1 Announce Type: new
Abstract: Learning about the causal structure of the world is a fundamental problem for human cognition. Causal models and especially causal learning have proved to be difficult for large pretrained models using standard techniques of deep learning. In contrast, cognitive scientists have applied advances in our formal understanding of causation in computer science, particularly within the Causal Bayes Net formalism, to understand human causal learning. In the very different tradition of reinforcement learning, researchers have described an intrinsic reward signal called “empowerment” which maximizes mutual information between actions and their outcomes. “Empowerment” may be an important bridge between classical Bayesian causal learning and reinforcement learning and may help to characterize causal learning in humans and enable it in machines. If an agent learns an accurate causal world model, they will necessarily increase their empowerment, and increasing empowerment will lead to a more accurate causal world model. Empowerment may also explain distinctive features of childrens causal learning, as well as providing a more tractable computational account of how that learning is possible. In an empirical study, we systematically test how children and adults use cues to empowerment to infer causal relations, and design effective causal interventions. Read More