We focus explicitly on multi-agent RL methods in 3D air combat environments, while the survey [4] also includes single-agent RL and 2D dynamics. Several existing works employ techniques that are relevant to multi-agent air combat, such as tactical reward shaping [5], heterogeneous agents [6], attention-based neural networks for situational awareness [7], or communication mechanisms [8] to improve mission strategies. Curriculum Learning (CL) with gradually increasing task difficulty is applied in [9], while enhanced coordination among agents is achieved by adapted training algorithms [10]. The application of HMARL in defense contexts is comparatively limited. An HMARL approach that employs attention mechanisms and self-play is introduced in [11]. Frameworks more closely related to ours appear in [12], [13], with the former integrating CL and the latter employing heterogeneous leader-follower agents together with JSBSim. In this work, we introduce a complex 3D air combat environment and a training framework to learn hierarchical policies using reward shaping and cascaded league-play that gradually increases mission complexity under realistic and heterogeneous conditions. In contrast to prior efforts that are built on established RL algorithms such as Proximal Policy Optimization (PPO) [14], we additionally adapt the recently presented SPO algorithm [3] to the hierarchical multi-agent domain. To the best of our knowledge, this adapted setup has not yet been studied in this context and represents a significant step toward enhancing the realism of such applications.

Accurately simulating physics is crucial across scientific domains, with applications spanning from robotics to materials science. While traditional mesh-based simulations are precise, they are often computationally expensive and require knowledge of physical parameters, such as material properties. In contrast, data-driven approaches like Graph Network Simulators (GNSs) offer faster inference but suffer from two key limitations: Firstly, they must be retrained from scratch for even minor variations in physical parameters, and secondly they require labor-intensive data collection for each new parameter setting. This is inefficient, as simulations with varying parameters often share a common underlying latent structure. In this work, we address these challenges by learning this shared structure through meta-learning, enabling fast adaptation to new physical parameters without retraining. To this end, we propose a novel architecture that generates a latent representation by encoding graph trajectories using conditional neural processes (CNPs). To mitigate error accumulation over time, we combine CNPs with a novel neural operator architecture. We validate our approach, Meta Neural Graph Operator (MaNGO), on several dynamics prediction tasks with varying material properties, demonstrating superior performance over existing GNS methods. Notably, MaNGO achieves accuracy on unseen material properties close to that of an oracle model.

Abstract--Signal T emporal Logic (STL) inference seeks to extract human-interpretable rules from time-series data, but existing methods lack formal confidence guarantees for the inferred rules. Conformal prediction (CP) is a technique that can provide statistical correctness guarantees, but is typically applied as a post-training wrapper without improving model learning. Instead, we introduce an end-to-end differentiable CP framework for STL inference that enhances both reliability and interpretability of the resulting formulas. We introduce a robustness-based nonconformity score, embed a smooth CP layer directly into training, and employ a new loss function that simultaneously optimizes inference accuracy and CP prediction sets with a single term. Following training, an exact CP procedure delivers statistical guarantees for the learned STL formulas. Experiments on benchmark time-series tasks show that our approach reduces uncertainty in predictions (i.e., it achieves high coverage while reducing prediction set size), and improves accuracy (i.e., the number of misclassifications when using a fixed threshold) over state-of-the-art baselines.

AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because they are bespoke, tied to rigid workflows, and lack shared environments that unify tools, data, and analyses into a common ecosystem. In genomics, unified ecosystems have transformed research by enabling interoperability, reuse, and community-driven development; AI scientists require comparable infrastructure. We present ToolUniverse, an ecosystem for building AI scientists from any language or reasoning model across open- and closed-weight models. ToolUniverse standardizes how AI scientists identify and call tools by providing more than 600 machine learning models, datasets, APIs, and scientific packages for data analysis, knowledge retrieval, and experimental design. It automatically refines tool interfaces for correct use by AI scientists, generates new tools from natural language descriptions, iteratively optimizes tool specifications, and composes tools into agentic workflows. In a case study of hypercholesterolemia, ToolUniverse was used to create an AI scientist to identify a potent analog of a drug with favorable predicted properties. The open-source ToolUniverse is available at https://aiscientist.tools.

This study investigates whether Topological Data Analysis (TDA) can provide additional insights beyond traditional statistical methods in clustering currency behaviours. We focus on the foreign exchange (FX) market, which is a complex system often exhibiting non-linear and high-dimensional dynamics that classical techniques may not fully capture. We compare clustering results based on TDA-derived features versus classical statistical features using monthly logarithmic returns of 13 major currency exchange rates (all against the euro). Two widely-used clustering algorithms, \(k\)-means and Hierarchical clustering, are applied on both types of features, and cluster quality is evaluated via the Silhouette score and the Calinski-Harabasz index. Our findings show that TDA-based feature clustering produces more compact and well-separated clusters than clustering on traditional statistical features, particularly achieving substantially higher Calinski-Harabasz scores. However, all clustering approaches yield modest Silhouette scores, underscoring the inherent difficulty of grouping FX time series. The differing cluster compositions under TDA vs. classical features suggest that TDA captures structural patterns in currency co-movements that conventional methods might overlook. These results highlight TDA as a valuable complementary tool for analysing financial time series, with potential applications in risk management where understanding structural co-movements is crucial.

We present a systematic analysis of estimation errors for a class of optimal transport based algorithms for filtering and data assimilation. Along the way, we extend previous error analyses of Brenier maps to the case of conditional Brenier maps that arise in the context of simulation based inference. We then apply these results in a filtering scenario to analyze the optimal transport filtering algorithm of Al-Jarrah et al. (2024, ICML). An extension of that algorithm along with numerical benchmarks on various non-Gaussian and high-dimensional examples are provided to demonstrate its effectiveness and practical potential.

Tesla vehicles line a parking area at the company's factory in Fremont, California. Tesla vehicles line a parking area at the company's factory in Fremont, California. Carmaker exceeded Wall Street's expectations with more than $26bn in revenue, but saw a 37% drop in profits Despite record vehicle sales, Tesla saw a precipitous drop in profit in its most recent quarter. A rush to buy electric vehicles before a US tax credit for them disappears had boosted Tesla's flagging sales, leading to the automaker exceeding some of Wall Street's projections in its most recent financial quarter. Yet the company failed to meet earnings expectations and its stock fell in after-hours trading.

Strap In, It's About to Get Ugly There Are a Few Big Problems With That. The company launched a multimillion-dollar campaign to fight worker protections and invest in delivery robots. Enter your email to receive alerts for this author. You can manage your newsletter subscriptions at any time. You're already subscribed to the aa_Nitish_Pahwa newsletter.

OpenAI's CEO, Sam Altman, testifies at a Senate hearing in Washington DC on 8 May 2025. OpenAI's CEO, Sam Altman, testifies at a Senate hearing in Washington DC on 8 May 2025. Adam Raine's suicide at 16 years old was'predictable result of deliberate design choices' by OpenAI, his family says The family of a teenager who took his own life after months of conversations with ChatGPT now says OpenAI weakened safety guidelines in the months before his death. In July 2022, OpenAI's guidelines on how ChatGPT should answer inappropriate content, including "content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders", were simple: the AI chatbot should respond, "I can't answer that", the guidelines read . But in May 2024, just days before OpenAI released a new version of the AI, ChatGPT-4o, the company published an update to its Model Spec, a document that details the desired behavior for its assistant.

Face Check will scan new members' faces to ensure they don't match existing profiles. The move comes as romance scams continue to proliferate, with billions lost over the last decade. On Wednesday, Tinder announced that it was rolling out a mandatory facial verification tool for new users in the US to help combat the spread of fake profiles and weed out "bad actors." Tinder claims its mandatory facial integration feature, called Face Check, is a first for a major dating app. During the sign up process, new members complete a "liveness check" by taking a short video selfie within the app.