In industry, software testing is the primary method to verify and validate the functionality, performance, security, usability, and so on, of software-based systems. Test automation has gained increasing attention in industry over the last decade, following decades of intense research into test automation and model-based testing. However, designing, developing, maintaining and evolving test automation is a considerable effort. Meanwhile, AI's breakthroughs in many engineering fields are opening up new perspectives for software testing, for both manual and automated testing. This paper reviews recent research on AI augmentation in software test automation, from no automation to full automation. It also discusses new forms of testing made possible by AI. Based on this, the newly developed taxonomy, ai4st, is presented and used to classify recent research and identify open research questions.

Rida Qadri ( ridaqadri@google.com) is a senior research scientist at Google Research, Mountain View, CA, USA. Michael Madaio ( madaiom@google.com) is a senior research scientist at Google Research, New York, NY, USA. Mary L. Gray ( mlg@microsoft.com) is a senior principal researcher at Microsoft Research, Cambridge, MA, USA.

Former U.S. Army Intel and Special Ops soldier Brett Velicovich joins'America's Newsroom' to discuss the Defense Department's push to increase military drone production and Ukraine's drone strike on Russia. EXCLUSIVE: Army Secretary Dan Driscoll said U.S. soldiers are improvising with government credit cards to buy and test battlefield gear as they adapt to the exploding drone threat -- as the Army shifts its long-term posture toward countering China in the Indo-Pacific. In an interview with Fox News Digital, Driscoll described how elite units like the 75th Ranger Regiment are bypassing the Pentagon's cumbersome procurement system to test new drones, sensors and weapons in real time. At the same time, he said the Army is aligning with the Pentagon's assessment of China as the nation's "pacing threat," building a force optimized for the Indo-Pacific but still capable of deploying worldwide at a moment's notice. After a visit with the regiment at Hunter Army Airfield in Savannah, Georgia, on Tuesday, Driscoll said Rangers "basically just use their corporate credit card to go online and purchase things to test, and they will find what works."

In May, a group of about 40 people stood in a circle deep within the Pyramid of Khafre, the second-largest of the three pyramids looming over Egypt's Giza Plateau, holding hands and praying for Earth. Suddenly, their tour guide, an American mathematician and author named Robert Edward Grant, collapsed. He later described the experience in an interview with WIRED as a full-body electric shock emanating from somewhere beneath the chamber's stone floor. "I felt electricity coming through my hands," he says. "People were touching me, [and] they would feel it, too."

Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) is a technique that enhances Large Language Model (LLM) inference in tasks like Question Answering (QA) by retrieving relevant information from knowledge graphs (KGs). However, real-world KGs are often incomplete, meaning that essential information for answering questions may be missing. Existing benchmarks do not adequately capture the impact of KG incompleteness on KG-RAG performance. In this paper, we systematically evaluate KG-RAG methods under incomplete KGs by removing triples using different methods and analyzing the resulting effects. We demonstrate that KG-RAG methods are sensitive to KG incompleteness, highlighting the need for more robust approaches in realistic settings.

Singer-songwriter Taylor Swift and NFL tight end Travis Kelce announced their engagement on Instagram after two years of dating. I bet you thought bunnies were nice, normal, cuddly critters -- except for the vorpal bunny of "Monty Python" fame. Turns out, we were all wrong. According to The Associated Press, there's a group of rabbits in Colorado with grotesque horn-like growths that may seem straight out of a low-budget horror film. Hide your kids, hide your wives and dig out your VHS copy of "Night of the Lepus."

Tool-augmented language models, equipped with retrieval, memory, or external APIs, are reshaping AI, yet their theoretical advantages remain underexplored. In this paper, we address this question by demonstrating the benefits of in-tool learning (external retrieval) over in-weight learning (memorization) for factual recall. We show that the number of facts a model can memorize solely in its weights is fundamentally limited by its parameter count. In contrast, we prove that tool-use enables unbounded factual recall via a simple and efficient circuit construction. These results are validated in controlled experiments, where tool-using models consistently outperform memorizing ones. We further show that for pretrained large language models, teaching tool-use and general rules is more effective than finetuning facts into memory. Our work provides both a theoretical and empirical foundation, establishing why tool-augmented workflows are not just practical, but provably more scalable.

This study presents a lightweight, domain-informed AI model for predicting indoor temperatures in naturally ventilated schools and homes in Sub-Saharan Africa. The model extends the Temp-AI-Estimator framework, trained on Tanzanian school data, and evaluated on Nigerian schools and Gambian homes. It achieves robust cross-country performance using only minimal accessible inputs, with mean absolute errors of 1.45°C for Nigerian schools and 0.65°C for Gambian homes. These findings highlight AI's potential for thermal comfort management in resource-constrained environments.

Poaching poses significant threats to wildlife and biodiversity. A valuable step in reducing poaching is to forecast poacher behavior, which can inform patrol planning and other conservation interventions. Existing poaching prediction methods based on linear models or decision trees lack the expressivity to capture complex, nonlinear spatiotemporal patterns. Recent advances in generative modeling, particularly flow matching, offer a more flexible alternative. However, training such models on real-world poaching data faces two central obstacles: imperfect detection of poaching events and limited data. To address imperfect detection, we integrate flow matching with an occupancy-based detection model and train the flow in latent space to infer the underlying occupancy state. To mitigate data scarcity, we adopt a composite flow initialized from a linear-model prediction rather than random noise which is the standard in diffusion models, injecting prior knowledge and improving generalization. Evaluations on datasets from two national parks in Uganda show consistent gains in predictive accuracy.

We study a sequential resource allocation problem where a decision maker selects subsets of agents at each period to maximize overall outcomes without prior knowledge of individual-level effects. Our framework applies to settings such as community health interventions, targeted digital advertising, and workforce retention programs, where intervention effects evolve dynamically. Agents may exhibit habituation (diminished response from frequent selection) or recovery (enhanced response from infrequent selection). The technical challenge centers on nonstationary reward distributions that lead to changing intervention effects over time. The problem requires balancing two key competing objectives: heterogeneous individual rewards and the exploration-exploitation tradeoff in terms of learning for improved future decisions as opposed to maximizing immediate outcomes. Our contribution introduces the first framework incorporating this form of nonstationary rewards in the combinatorial multi-armed bandit literature. We develop algorithms with theoretical guarantees on dynamic regret and demonstrate practical efficacy through a diabetes intervention case study. Our personalized community intervention algorithm achieved up to three times as much improvement in program enrollment compared to baseline approaches, validating the framework's potential for real-world applications. This work bridges theoretical advances in adaptive learning with practical challenges in population-level behavioral change interventions.