Large language models (LLMs) have demonstrated exceptional capabilities when trained within executable runtime environments, notably excelling at software engineering tasks through verified feedback loops. Yet, scalable and generalizable execution-grounded environments remain scarce, limiting progress in training more capable ML agents. We introduce CTF-Dojo, the first large-scale executable runtime tailored for training LLMs with verifiable feedback, featuring 658 fully functional Capture-The-Flag (CTF)-style challenges containerized in Docker with guaranteed reproducibility. To enable rapid scaling without manual intervention, we develop CTF-Forge, an automated pipeline that transforms publicly available artifacts into ready-to-use execution environments in minutes, eliminating weeks of expert configuration traditionally required. We trained LLM-based agents on just 486 high-quality, execution-verified trajectories from CTF-Dojo, achieving up to 11.6% absolute gains over strong baselines across three competitive benchmarks: InterCode-CTF, NYU CTF Bench, and Cybench. Our best-performing 32B model reaches 31.9% Pass@1, establishing a new open-weight state-of-the-art that rivals frontier models like DeepSeek-V3-0324 and Gemini-2.5-Flash. By framing CTF-style tasks as a benchmark for executable-agent learning, CTF-Dojo demonstrates that execution-grounded training signals are not only effective but pivotal in advancing high-performance ML agents without dependence on costly proprietary systems.

These vegan meal kits and delivery services bring preprepared meals and meal kits to your door. All products featured on WIRED are independently selected by our editors. However, we may receive compensation from retailers and/or from purchases of products through these links. Vegan-specific meal kit services are a modern miracle for vegans, who usually aren't afforded the same conveniences as meat eaters or those without dietary restrictions. We at WIRED love meal kits, because they're all about modern convenience--you can eat what you want, even if you're on a specialty diet or have strong food preferences, without ever leaving your house. Gone are the days of grocery shopping and scouring online for recipes; these contemporary vegan meal kit services do the heavy lifting for you using curated menus and algorithms, with choices for both premade microwavable meals and kits where you do the cooking yourself. Some vegan meal kit services, like Hungryroot, use AI customization to curate menus based on your specific tastes. Others, like Daily Harvest, have a set selection of choices so you can always keep your freezer stocked with vegan, gluten-free meals to have on hand.

Things to Do in L.A. Tap to enable a layout that focuses on the article. A child uses a tablet to play an augmented reality game meant to teach spatial awareness. This is read by an automated voice. Please report any issues or inconsistencies here . Spatial thinking concepts are a part of early math that have largely been absent from preschool curricula.

Assessing fairness in artificial intelligence (AI) typically involves AI experts who select protected features, fairness metrics, and set fairness thresholds. However, little is known about how stakeholders, particularly those affected by AI outcomes but lacking AI expertise, assess fairness. To address this gap, we conducted a qualitative study with 30 stakeholders without AI expertise, representing potential decision subjects in a credit rating scenario, to examine how they assess fairness when placed in the role of deciding on features with priority, metrics, and thresholds. We reveal that stakeholders' fairness decisions are more complex than typical AI expert practices: they considered features far beyond legally protected features, tailored metrics for specific contexts, set diverse yet stricter fairness thresholds, and even preferred designing customized fairness. Our results extend the understanding of how stakeholders can meaningfully contribute to AI fairness governance and mitigation, underscoring the importance of incorporating stakeholders' nuanced fairness judgments.

Language-driven generative agents have enabled large-scale social simulations with transformative uses, from interpersonal training to aiding global policy-making. However, recent studies indicate that generative agent behaviors often deviate from expert expectations and real-world data--a phenomenon we term the Behavior-Realism Gap. To address this, we introduce a theoretical framework called Persona-Environment Behavioral Alignment (PEBA), formulated as a distribution matching problem grounded in Lewin's behavior equation stating that behavior is a function of the person and their environment. Leveraging PEBA, we propose PersonaEvolve (PEvo), an LLM-based optimization algorithm that iteratively refines agent personas, implicitly aligning their collective behaviors with realistic expert benchmarks within a specified environmental context. We validate PEvo in an active shooter incident simulation we developed, achieving an 84% average reduction in distributional divergence compared to no steering and a 34% improvement over explicit instruction baselines. Results also show PEvo-refined personas generalize to novel, related simulation scenarios. Our method greatly enhances behavioral realism and reliability in high-stakes social simulations. More broadly, the PEBA-PEvo framework provides a principled approach to developing trustworthy LLM-driven social simulations.

Large Language Model (LLM)-based agents have emerged as a new paradigm that extends LLMs' capabilities beyond text generation to dynamic interaction with external environments. By integrating reasoning with perception, memory, and tool use, agents are increasingly deployed in diverse domains like web navigation and household robotics. A critical challenge, however, lies in ensuring agent generalizability - the ability to maintain consistent performance across varied instructions, tasks, environments, and domains, especially those beyond agents' fine-tuning data. Despite growing interest, the concept of generalizability in LLM-based agents remains underdefined, and systematic approaches to measure and improve it are lacking. In this survey, we provide the first comprehensive review of generalizability in LLM-based agents. We begin by emphasizing agent generalizability's importance by appealing to stakeholders and clarifying the boundaries of agent generalizability by situating it within a hierarchical domain-task ontology. We then review datasets, evaluation dimensions, and metrics, highlighting their limitations. Next, we categorize methods for improving generalizability into three groups: methods for the backbone LLM, for agent components, and for their interactions. Moreover, we introduce the distinction between generalizable frameworks and generalizable agents and outline how generalizable frameworks can be translated into agent-level generalizability. Finally, we identify critical challenges and future directions, including developing standardized frameworks, variance- and cost-based metrics, and approaches that integrate methodological innovations with architecture-level designs. By synthesizing progress and highlighting opportunities, this survey aims to establish a foundation for principled research on building LLM-based agents that generalize reliably across diverse applications.

The challenges of solving complex university-level mathematics problems, particularly those from MIT, and Columbia University courses, and selected tasks from the MATH dataset, remain a significant obstacle in the field of artificial intelligence. Conventional methods have consistently fallen short in this domain, highlighting the need for more advanced approaches. In this paper, we introduce a language-based solution that leverages zero-shot learning and mathematical reasoning to effectively solve, explain, and generate solutions for these advanced math problems. By integrating program synthesis, our method reduces reliance on large-scale training data while significantly improving problem-solving accuracy. Our approach achieves an accuracy of 90.15%, representing a substantial improvement over the previous benchmark of 81% and setting a new standard in automated mathematical problem-solving. These findings highlight the significant potential of advanced AI methodologies to address and overcome the challenges presented by some of the most complex mathematical courses and datasets.

Preventing student dropout is a major challenge in higher education and it is difficult to predict prior to enrolment which students are likely to drop out and which students are likely to succeed. High School GPA is a strong predictor of dropout, but much variance in dropout remains to be explained. This study focused on predicting university dropout by using text mining techniques with the aim of exhuming information contained in motivation statements written by students. By combining text data with classic predictors of dropout in the form of student characteristics, we attempt to enhance the available set of predictive student characteristics. Our dataset consisted of 7,060 motivation statements of students enrolling in a non-selective bachelor at a Dutch university in 2014 and 2015. Support Vector Machines were trained on 75 percent of the data and several models were estimated on the test data. We used various combinations of student characteristics and text, such as TFiDF, topic modelling, LIWC dictionary. Results showed that, although the combination of text and student characteristics did not improve the prediction of dropout, text analysis alone predicted dropout similarly well as a set of student characteristics. Suggestions for future research are provided.

Although diversity in NLP datasets has received growing attention, the question of how to measure it remains largely underexplored. This opinion paper examines the conceptual and methodological challenges of measuring data diversity and argues that interdisciplinary perspectives are essential for developing more fine-grained and valid measures.

We introduce ReWiND, a framework for learning robot manipulation tasks solely from language instructions without per-task demonstrations. Standard reinforcement learning (RL) and imitation learning methods require expert supervision through human-designed reward functions or demonstrations for every new task. In contrast, ReWiND starts from a small demonstration dataset to learn: (1) a data-efficient, language-conditioned reward function that labels the dataset with rewards, and (2) a language-conditioned policy pre-trained with offline RL using these rewards. Given an unseen task variation, ReWiND fine-tunes the pre-trained policy using the learned reward function, requiring minimal online interaction. We show that ReWiND's reward model generalizes effectively to unseen tasks, outperforming baselines by up to 2.4x in reward generalization and policy alignment metrics. Finally, we demonstrate that ReWiND enables sample-efficient adaptation to new tasks, beating baselines by 2x in simulation and improving real-world pretrained bimanual policies by 5x, taking a step towards scalable, real-world robot learning. See website at https://rewind-reward.github.io/.