Large Language Models (LLMs) have shown growing potential in molecular sciences, but they often produce chemically inaccurate descriptions and struggle to recognize or justify potential errors. This raises important concerns about their robustness and reliability in scientific applications. To support more rigorous evaluation of LLMs in chemical reasoning, we present the MolErr2Fix benchmark, designed to assess LLMs on error detection and correction in molecular descriptions. Unlike existing benchmarks focused on molecule-to-text generation or property prediction, MolErr2Fix emphasizes fine-grained chemical understanding. It tasks LLMs with identifying, localizing, explaining, and revising potential structural and semantic errors in molecular descriptions. Specifically, MolErr2Fix consists of 1,193 fine-grained annotated error instances. Each instance contains quadruple annotations, i.e,. (error type, span location, the explanation, and the correction). These tasks are intended to reflect the types of reasoning and verification required in real-world chemical communication. Evaluations of current state-of-the-art LLMs reveal notable performance gaps, underscoring the need for more robust chemical reasoning capabilities. MolErr2Fix provides a focused benchmark for evaluating such capabilities and aims to support progress toward more reliable and chemically informed language models. All annotations and an accompanying evaluation API will be publicly released to facilitate future research.

Hypothesis ranking is vital for automated scientific discovery, especially in cost-intensive, throughput-limited natural science domains. Current methods focus on pre-experiment ranking, relying solely on language model reasoning without empirical feedback. We introduce experiment-guided ranking, which prioritizes hypotheses based on feedback from prior tests. Due to the impracticality of real experiments, we propose a simulator grounded in domain-specific concepts that models hypothesis performance as a function of similarity to a hidden ground truth, perturbed by noise. Validated against 124 hypotheses with experimentally reported outcomes, the simulator approximates real results with consistent trend alignment. Although deviations exist, they mimic wet-lab noise, promoting more robust ranking strategies. We frame experiment-guided ranking as a sequential decision-making problem and propose an in-context reinforcement learning (ICRL) framework. Our LLM-based policy decomposes hypotheses into functional elements, clusters them by mechanistic roles, and prioritizes recombinations based on feedback. Experiments show our approach significantly outperforms pre-experiment baselines and strong ablations. Our toolkit, comprising the simulator and ICRL framework, enables systematic research on experiment-guided ranking, with the policy serving as a strong proof of concept.

We investigate a relatively underexplored class of hybrid neurosymbolic models integrating symbolic learning with neural reasoning to construct data generators meeting formal correctness criteria. In \textit{Symbolic Neural Generators} (SNGs), symbolic learners examine logical specifications of feasible data from a small set of instances -- sometimes just one. Each specification in turn constrains the conditional information supplied to a neural-based generator, which rejects any instance violating the symbolic specification. Like other neurosymbolic approaches, SNG exploits the complementary strengths of symbolic and neural methods. The outcome of an SNG is a triple $(H, X, W)$, where $H$ is a symbolic description of feasible instances constructed from data, $X$ a set of generated new instances that satisfy the description, and $W$ an associated weight. We introduce a semantics for such systems, based on the construction of appropriate \textit{base} and \textit{fibre} partially-ordered sets combined into an overall partial order, and outline a probabilistic extension relevant to practical applications. In this extension, SNGs result from searching over a weighted partial ordering. We implement an SNG combining a restricted form of Inductive Logic Programming (ILP) with a large language model (LLM) and evaluate it on early-stage drug design. Our main interest is the description and the set of potential inhibitor molecules generated by the SNG. On benchmark problems -- where drug targets are well understood -- SNG performance is statistically comparable to state-of-the-art methods. On exploratory problems with poorly understood targets, generated molecules exhibit binding affinities on par with leading clinical candidates. Experts further find the symbolic specifications useful as preliminary filters, with several generated molecules identified as viable for synthesis and wet-lab testing.

This paper deals with the design of a cost effective automated tape laying system (ATL system) with integrated uniaxial force control to ensure the necessary compaction forces as well as with an accurate temperature control to guarantee the used tape being melted appropriate. It is crucial to control the substrate and the oncoming tape onto a specific temperature level to ensure an optimal consolidation between the different layers of the product. Therefore, it takes several process steps from the spooled tape on the coil until it is finally tacked onto the desired mold. The different modules are divided into the tape storage spool, a tape-guiding roller, a tape processing unit, a heating zone and the consolidation unit. Moreover, a special robot control concept for testing the ATL system is presented. In contrast to many other systems, with this approach, the tape laying device is spatially fixed and the shape is moved accordingly by the robot, which allows for handling of rather compact and complex shapes. The functionality of the subsystems and the taping process itself was finally approved in experimental results using a carbon fiber reinforced HDPE tape.

Language models (LMs) often struggle to generate diverse, human-like creative content, raising concerns about the long-term homogenization of human thought through repeated exposure to similar outputs. Yet scalable methods for evaluating LM output diversity remain limited, especially beyond narrow tasks such as random number or name generation, or beyond repeated sampling from a single model. We introduce Infinity-Chat, a large-scale dataset of 26K diverse, real-world, open-ended user queries that admit a wide range of plausible answers with no single ground truth. We introduce the first comprehensive taxonomy for characterizing the full spectrum of open-ended prompts posed to LMs, comprising 6 top-level categories (e.g., brainstorm & ideation) that further breaks down to 17 subcategories. Using Infinity-Chat, we present a large-scale study of mode collapse in LMs, revealing a pronounced Artificial Hivemind effect in open-ended generation of LMs, characterized by (1) intra-model repetition, where a single model consistently generates similar responses, and more so (2) inter-model homogeneity, where different models produce strikingly similar outputs. Infinity-Chat also includes 31,250 human annotations, across absolute ratings and pairwise preferences, with 25 independent human annotations per example. This enables studying collective and individual-specific human preferences in response to open-ended queries. Our findings show that LMs, reward models, and LM judges are less well calibrated to human ratings on model generations that elicit differing idiosyncratic annotator preferences, despite maintaining comparable overall quality. Overall, INFINITY-CHAT presents the first large-scale resource for systematically studying real-world open-ended queries to LMs, revealing critical insights to guide future research for mitigating long-term AI safety risks posed by the Artificial Hivemind.

The task here is to predict the toxicological activity of chemical compounds based on the Tox21 dataset, a benchmark in computational toxicology. After a domain-specific overview of chemical toxicity, we discuss current computational strategies, focusing on machine learning and deep learning. Several architectures are compared in terms of performance, robustness, and interpretability. This research introduces a novel image-based pipeline based on DenseNet121, which processes 2D graphical representations of chemical structures. Additionally, we employ Grad-CAM visualizations, an explainable AI technique, to interpret the model's predictions and highlight molecular regions contributing to toxicity classification. The proposed architecture achieves competitive results compared to traditional models, demonstrating the potential of deep convolutional networks in cheminformatics. Our findings emphasize the value of combining image-based representations with explainable AI methods to improve both predictive accuracy and model transparency in toxicology.

How can large language models (LLMs) serve users with varying preferences that may conflict across cultural, political, or other dimensions? To advance this challenge, this paper establishes four key results. First, we demonstrate, through a large-scale multilingual human study with representative samples from five countries (N=15,000), that humans exhibit significantly more variation in preferences than the responses of 21 state-of-the-art LLMs. Second, we show that existing methods for preference dataset collection are insufficient for learning the diversity of human preferences even along two of the most salient dimensions of variability in global values, due to the underlying homogeneity of candidate responses. Third, we argue that this motivates the need for negatively-correlated sampling when generating candidate sets, and we show that simple prompt-based techniques for doing so significantly enhance the performance of alignment methods in learning heterogeneous preferences. Fourth, based on this novel candidate sampling approach, we collect and open-source Community Alignment, the largest and most representative multilingual and multi-turn preference dataset to date, featuring almost 200,000 comparisons from annotators spanning five countries. We hope that the Community Alignment dataset will be a valuable resource for improving the effectiveness of LLMs for a diverse global population.

Survival International's new report illustrates the dangers they face--and their resilience. This photo of an Awa Guajá couple was taken only five days before their first contact with outsiders in 1992. Breakthroughs, discoveries, and DIY tips sent every weekday. Half of the world's remaining uncontacted Indigenous groups may disappear within a decade without concerted conservation efforts . The dire assessment is detailed in a new report published on October 27 by the nonprofit advocacy group Survival International, and is based on years of field research, interviews, and information gathering expeditions.

Increased defense spending is a boon for Germany's ailing industrial sector. Numerous companies, even those with no previous military experience, are now hoping to get in on the act. Visiting the works of Ilsenburger Grobblech GmbH is like taking a trip back in time. Way back in the 16th century, copper used to be produced at this site in the northern Harz Mountains, not far from eastern Germany' tallest peak, the Brocken. Today, slabs of steel up to 35 centimeters thick are piled up in front of the factory halls, delivered from the blast furnaces and converters of parent company Salzgitter, less than an hour's drive away. What is happening behind the factory walls, though, is part of a new hype that has gripped Germany's crisis-ridden industrial sector. A hype which many are hoping will be enough to revive it.

Mobile robotic chemists are a fast growing trend in the field of chemistry and materials research. However, so far these mobile robots lack workflow awareness skills. This poses the risk that even a small anomaly, such as an improperly capped sample vial could disrupt the entire workflow. This wastes time, and resources, and could pose risks to human researchers, such as exposure to toxic materials. Existing perception mechanisms can be used to predict anomalies but they often generate excessive false positives. This may halt workflow execution unnecessarily, requiring researchers to intervene and to resume the workflow when no problem actually exists, negating the benefits of autonomous operation. To address this problem, we propose PREVENT a system comprising navigation and manipulation skills based on a multimodal Behavior Tree (BT) approach that can be integrated into existing software architectures with minimal modifications. Our approach involves a hierarchical perception mechanism that exploits AI techniques and sensory feedback through Dexterous Vision and Navigational Vision cameras and an IoT gas sensor module for execution-related decision-making. Experimental evaluations show that the proposed approach is comparatively efficient and completely avoids both false negatives and false positives when tested in simulated risk scenarios within our robotic chemistry workflow. The results also show that the proposed multi-modal perception skills achieved deployment accuracies that were higher than the average of the corresponding uni-modal skills, both for navigation and for manipulation.