Text-to-chart retrieval, enabling users to find relevant charts via natural language queries, has gained significant attention. However, evaluating models in real-world business intelligence (BI) scenarios is challenging, as current benchmarks fail to simulate realistic user queries or test for deep semantic understanding with static chart images.To address this gap, we introduce CRBench, the first real-world BI-sourced benchmark comprising 21,862 charts and 326 queries, utilizing a Target-and-Distractor paradigm to evaluate discriminative retrieval among highly similar candidates. Testing on CRBench reveals that existing methods, which rely primarily on visual features, perform poorly and fail to capture the rich analytical semantics of charts. To address this performance bottleneck, we propose a semantic insights synthesis pipeline that automatically generates three hierarchical levels of insights for charts: visual patterns, statistical properties, and practical applications. Using this pipeline, we produced 207,498 semantic insights for 69,166 charts as training data. By leveraging this data to bridge the gap between natural language query intent and latent visual representations via multi-level semantic supervision, we develop ChartFinder, a specialized model capable of deep cross-model reasoning. Experimental results show ChartFinder significantly outperforms state-of-the-art methods on CRBench, achieving up to 66.9% NDCG@10 for precise queries (an 11.58% improvement) and an average increase of 5% across nearly all metrics for fuzzy queries. This work provides the community with a much-needed benchmark for realistic evaluation and demonstrates a powerful data synthesis paradigm for enhancing a model's semantic understanding of charts.

We describe an algorithm for sampling a low-rank random matrix $Q$ that best approximates a fixed target matrix $P\in\mathbb{C}^{n\times m}$ in the following sense: $Q$ is unbiased, i.e., $\mathbb{E}[Q] = P$; $\mathsf{rank}(Q)\leq r$; and $Q$ minimizes the expected Frobenius norm error $\mathbb{E}\|P-Q\|_F^2$. Our algorithm mirrors the solution to the efficient unbiased sparsification problem for vectors, except applied to the singular components of the matrix $P$. Optimality is proven by showing that our algorithm matches the error from an existing lower bound.

Principal component analysis (PCA) is a key tool in the field of data dimensionality reduction. However, some applications involve heterogeneous data that vary in quality due to noise characteristics associated with each data sample. Heteroscedastic methods aim to deal with such mixed data quality. This paper develops a subspace learning method, named ALPCAH, that can estimate the sample-wise noise variances and use this information to improve the estimate of the subspace basis associated with the low-rank structure of the data. Our method makes no distributional assumptions of the low-rank component and does not assume that the noise variances are known. Further, this method uses a soft rank constraint that does not require subspace dimension to be known. Additionally, this paper develops a matrix factorized version of ALPCAH, named LR-ALPCAH, that is much faster and more memory efficient at the cost of requiring subspace dimension to be known or estimated. Simulations and real data experiments show the effectiveness of accounting for data heteroscedasticity compared to existing algorithms. Code available at https://github.com/javiersc1/ALPCAH.

The exponential growth of artificial intelligence (AI) applications has exposed the inefficiency of conventional von Neumann architectures, where frequent data transfers between compute units and memory create significant energy and latency bottlenecks. Analog Computing-in-Memory (ACIM) addresses this challenge by performing multiply-accumulate (MAC) operations directly in the memory arrays, substantially reducing data movement. However, designing robust ACIM accelerators requires accurate modeling of device- and circuit-level non-idealities. In this work, we present NeuroSim V1.5, introducing several key advances: (1) seamless integration with TensorRT's post-training quantization flow enabling support for more neural networks including transformers, (2) a flexible noise injection methodology built on pre-characterized statistical models, making it straightforward to incorporate data from SPICE simulations or silicon measurements, (3) expanded device support including emerging non-volatile capacitive memories, and (4) up to 6.5x faster runtime than NeuroSim V1.4 through optimized behavioral simulation. The combination of these capabilities uniquely enables systematic design space exploration across both accuracy and hardware efficiency metrics. Through multiple case studies, we demonstrate optimization of critical design parameters while maintaining network accuracy. By bridging high-fidelity noise modeling with efficient simulation, NeuroSim V1.5 advances the design and validation of next-generation ACIM accelerators. All NeuroSim versions are available open-source at https://github.com/neurosim/NeuroSim.

Multimodal physiological signals, such as EEG, ECG, EOG, and EMG, are crucial for healthcare and brain-computer interfaces. While existing methods rely on specialized architectures and dataset-specific fusion strategies, they struggle to learn universal representations that generalize across datasets and handle missing modalities at inference time. To address these issues, we propose PhysioOmni, a foundation model for multimodal physiological signal analysis that models both homogeneous and heterogeneous features to decouple multimodal signals and extract generic representations while maintaining compatibility with arbitrary missing modalities. PhysioOmni trains a decoupled multimodal tokenizer, enabling masked signal pre-training via modality-invariant and modality-specific objectives. To ensure adaptability to diverse and incomplete modality combinations, the pre-trained encoders undergo resilient fine-tuning with prototype alignment on downstream datasets. Extensive experiments on four downstream tasks, emotion recognition, sleep stage classification, motor prediction, and mental workload detection, demonstrate that PhysioOmni achieves state-of-the-art performance while maintaining strong robustness to missing modalities. Our code and model weights will be released.

This study addresses the minor-embedding problem, which involves mapping the variables of an Ising model onto a quantum annealing processor. The primary motivation stems from the observed performance disparity of quantum annealers when solving problems suited to the processor's architecture versus those with non-hardware-native topologies. Our research has two main objectives: i) to analyze the impact of embedding quality on the performance of D-Wave Systems quantum annealers, and ii) to evaluate the quality of the embeddings generated by Minorminer, the standard minor-embedding technique in the quantum annealing literature, provided by D-Wave. Regarding the first objective, our experiments reveal a clear correlation between the average chain length of embeddings and the relative errors of the solutions sampled. This underscores the critical influence of embedding quality on quantum annealing performance. For the second objective, we evaluate Minorminer's embedding capabilities, the quality and robustness of its embeddings, and its execution-time performance on Erdös-Rényi graphs. We also compare its performance with Clique Embedding, another algorithm developed by D-Wave, which is deterministic and designed to embed fully connected Ising models into quantum annealing processors, serving as a worst-case scenario. The results demonstrate that there is significant room for improvement for Minorminer, suggesting that more effective embedding strategies could lead to meaningful gains in quantum annealing performance.

Flow Matching has recently gained attention in generative modeling as a simple and flexible alternative to diffusion models. While existing statistical guarantees adapt tools from the analysis of diffusion models, we take a different perspective by connecting Flow Matching to kernel density estimation. We first verify that the kernel density estimator matches the optimal rate of convergence in Wasserstein distance up to logarithmic factors, improving existing bounds for the Gaussian kernel. Based on this result, we prove that for sufficiently large networks, Flow Matching achieves the optimal rate up to logarithmic factors. If the target distribution lies on a lower-dimensional manifold, we show that the kernel density estimator profits from the smaller intrinsic dimension on a small tube around the manifold. The faster rate also applies to Flow Matching, providing a theoretical foundation for its empirical success in high-dimensional settings.

While deep neural networks (DNNs) are used for prediction, inference on DNN-estimated subject-specific means for categorical or exponential family outcomes remains underexplored. We address this by proposing a DNN estimator under generalized nonparametric regression models (GNRMs) and developing a rigorous inference framework. Unlike existing approaches that assume independence between estimation errors and inputs to establish the error bound, a condition often violated in GNRMs, we allow for dependence and our theoretical analysis demonstrates the feasibility of drawing inference under GNRMs. To implement inference, we consider an Ensemble Subsampling Method (ESM) that leverages U-statistics and the Hoeffding decomposition to construct reliable confidence intervals for DNN estimates. We show that, under GNRM settings, ESM enables model-free variance estimation and accounts for heterogeneity among individuals in the population. Through simulations under nonparametric logistic, Poisson, and binomial regression models, we demonstrate the effectiveness and efficiency of our method. We further apply the method to the electronic Intensive Care Unit (eICU) dataset, a large scale collection of anonymized health records from ICU patients, to predict ICU readmission risk and offer patient-centric insights for clinical decision making.

Land surface temperature (LST) retrieval from remote sensing data is pivotal for analyzing climate processes and surface energy budgets. However, LST retrieval is an ill-posed inverse problem, which becomes particularly severe when only a single band is available. In this paper, we propose a deeply coupled framework integrating mechanistic modeling and machine learning to enhance the accuracy and generalizability of single-channel LST retrieval. Training samples are generated using a physically-based radiative transfer model and a global collection of 5810 atmospheric profiles. A physics-informed machine learning framework is proposed to systematically incorporate the first principles from classical physical inversion models into the learning workflow, with optimization constrained by radiative transfer equations. Global validation demonstrated a 30% reduction in root-mean-square error versus standalone methods. Under extreme humidity, the mean absolute error decreased from 4.87 K to 2.29 K (53% improvement). Continental-scale tests across five continents confirmed the superior generalizability of this model.

The constant $π$ has fascinated scholars throughout the centuries, inspiring numerous formulas for its evaluation, such as infinite sums and continued fractions. Despite their individual significance, many of the underlying connections among formulas remain unknown, missing unifying theories that could unveil deeper understanding. The absence of a unifying theory reflects a broader challenge across math and science: knowledge is typically accumulated through isolated discoveries, while deeper connections often remain hidden. In this work, we present an automated framework for the unification of mathematical formulas. Our system combines Large Language Models (LLMs) for systematic formula harvesting, an LLM-code feedback loop for validation, and a novel symbolic algorithm for clustering and eventual unification. We demonstrate this methodology on the hallmark case of $π$, an ideal testing ground for symbolic unification. Applying this approach to 455,050 arXiv papers, we validate 385 distinct formulas for $π$ and prove relations between 360 (94%) of them, of which 166 (43%) can be derived from a single mathematical object - linking canonical formulas by Euler, Gauss, Brouncker, and newer ones from algorithmic discoveries by the Ramanujan Machine. Our method generalizes to other constants, including $e$, $ζ(3)$, and Catalan's constant, demonstrating the potential of AI-assisted mathematics to uncover hidden structures and unify knowledge across domains.

Training generative AI models requires extensive amounts of data. A common practice is to collect such data through web scraping. Yet, much of what has been and is collected is copyright protected. Its use may be copyright infringement. In the USA, AI developers rely on "fair use" and in Europe, the prevailing view is that the exception for "Text and Data Mining" (TDM) applies. In a recent interdisciplinary tandem-study, we have argued in detail that this is actually not the case because generative AI training fundamentally differs from TDM. In this article, we share our main findings and the implications for both public and corporate research on generative models. We further discuss how the phenomenon of training data memorization leads to copyright issues independently from the "fair use" and TDM exceptions. Finally, we outline how the ISMIR could contribute to the ongoing discussion about fair practices with respect to generative AI that satisfy all stakeholders.

Large Language Models (LLMs) have emerged as powerful tools for automating programming tasks, including security-related ones. However, they can also introduce vulnerabilities during code generation, fail to detect existing vulnerabilities, or report nonexistent ones. This systematic literature review investigates the security benefits and drawbacks of using LLMs for code-related tasks. In particular, it focuses on the types of vulnerabilities introduced by LLMs when generating code. Moreover, it analyzes the capabilities of LLMs to detect and fix vulnerabilities, and examines how prompting strategies impact these tasks. Finally, it examines how data poisoning attacks impact LLMs performance in the aforementioned tasks.

Physics-based Earth system models (ESMs) are essential for attributing climate change and generating scenario projections, yet their reliance on high-resolution numerical integration makes multi-decadal experiments expensive. In parallel, deep learning has delivered strong gains in short-range weather forecasting; however, auto-regressive roll-outs can accumulate error and become unstable when extended to decade-scale climate emulation. We introduce A-UTE: Advection Informed, Uncertainty Aware Temperature Emulator, aimed at stable multi-year emulation across heterogeneous climate models and grid resolutions. A-UTE is trained on various physics-based models at varying spatial resolutions to emulate temperature fields over a 10-year horizon. A-UTE formulates climate emulation as a forward-time stochastic dynamical system. We propose an auto-regressive ODE-SDE surrogate in which transport dynamics are constrained by an advection consistent ODE component, while a learned neural SDE term models coarse-grained variability and cross-model discrepancy at monthly resolution. We train A-UTE under negative log-likelihood objective for principled uncertainty estimates and probabilistic evaluation. Experiments across 20 climate models show that A-UTE improves long roll-out stability and accuracy relative to relevant baselines, advancing data-driven climate emulation with explicit physical structure and uncertainty-aware predictions.

Motivation: Networks underlie the generation and interpretation of many biological datasets: gene networks shed light on the regulatory structure of the genome, and cell networks can capture structure of the tumor micro-environment. However, most methods that learn such networks make the faulty 'independence assumption'; to learn the gene network, they assume that no cell network exists. 'Multi-axis' methods, which do not make this assumption, fail to scale beyond a few thousand cells or genes. This limits their applicability to only the smallest datasets. Results: We develop a multi-axis method capable of processing million-cell datasets within minutes. This was previously impossible, and unlocks the use of such methods on modern scRNA-seq datasets, as well as more complex datasets. We show that our method yields novel biological insights from real single-cell data, and compares favorably to the existing hdWGCNA methodology. In particular, it identifies long non-coding RNA genes that potentially have a regulatory or functional role in neuronal development. Availability and implementation: Our methodology is available as a Python package GmGM on PyPI (https://pypi.org/project/GmGM/0.5.3/). The code for all experiments performed in this paper is available on GitHub (https://github.com/BaileyAndrew/GmGM-Bioinformatics). Contact: sceba@leeds.ac.uk Supplementary information: Our proofs, and some additional experiments, are available in the supplementary material. Keywords: gaussian graphical models, multi-axis models, transcriptomics, multi-omics, scalability

Greybox fuzzing has achieved success in revealing bugs and vulnerabilities in programs. However, randomized mutation strategies have limited the fuzzer's performance on structured data. Specialized fuzzers can handle complex structured data, but require additional efforts in grammar and suffer from low throughput. In this paper, we explore the potential of utilizing the Large Language Model to enhance greybox fuzzing for structured data. We utilize the pre-trained knowledge of LLM about data conversion and format to generate new valid inputs. We further fine-tuned it with paired mutation seeds to learn structured format and mutation strategies effectively. Our LLM-based fuzzer, LLAMAFUZZ, integrates the power of LLM to understand and mutate structured data to fuzzing. We conduct experiments on the standard bug-based benchmark Magma and a wide variety of real-world programs. LLAMAFUZZ outperforms our top competitor by 41 bugs on average. We also identified 47 unique bugs across all trials. Moreover, LLAMAFUZZ demonstrated consistent performance on both bug trigger and bug reached. Compared to AFL++, LLAMAFUZZ achieved 27.19% more branches in real-world program sets on average. We also demonstrate a case study to explain how LLMs enhance the fuzzing process in terms of code coverage.

We prove bounds on the variance of a function $f$ under the empirical measure of the samples obtained by the Sequential Monte Carlo (SMC) algorithm, with time complexity depending on local rather than global Markov chain mixing dynamics. SMC is a Markov Chain Monte Carlo (MCMC) method, which starts by drawing $N$ particles from a known distribution, and then, through a sequence of distributions, re-weights and re-samples the particles, at each instance applying a Markov chain for smoothing. In principle, SMC tries to alleviate problems from multi-modality. However, most theoretical guarantees for SMC are obtained by assuming global mixing time bounds, which are only efficient in the uni-modal setting. We show that bounds can be obtained in the truly multi-modal setting, with mixing times that depend only on local MCMC dynamics.

Synthetic Minority Oversampling Technique (SMOTE) is a common rebalancing strategy for handling imbalanced tabular data sets. However, few works analyze SMOTE theoretically. In this paper, we derive several non-asymptotic upper bound on SMOTE density. From these results, we prove that SMOTE (with default parameter) tends to copy the original minority samples asymptotically. We confirm and illustrate empirically this first theoretical behavior on a real-world data-set.bFurthermore, we prove that SMOTE density vanishes near the boundary of the support of the minority class distribution. We then adapt SMOTE based on our theoretical findings to introduce two new variants. These strategies are compared on 13 tabular data sets with 10 state-of-the-art rebalancing procedures, including deep generative and diffusion models. One of our key findings is that, for most data sets, applying no rebalancing strategy is competitive in terms of predictive performances, would it be with LightGBM, tuned random forests or logistic regression. However, when the imbalance ratio is artificially augmented, one of our two modifications of SMOTE leads to promising predictive performances compared to SMOTE and other state-of-the-art strategies.

Understanding the spatial arrangements of atom-centered coordination octahedra is crucial for relating structures to properties for many materials families. Traditional case-by-case inspection becomes a prohibitive task for discovering trends and similarities in large datasets. Here, we operationalize chemical intuition to automate the geometric parsing, quantification, and classification of coordination octahedral networks using unsupervised machine learning. We apply the workflow to analyze two datasets to demonstrate its effectiveness. For computationally generated single oxide perovskite (ABO$_{3}$) polymorphs, we uncover axis-dependent tilting trends which assist in detecting oxidation state changes. For hybrid iodoplumbates (A$_x$Pb$_y$I$_z$) from measured structures, we taxonomize their octahedral networks, revealing a Pauling-like connectivity rule for the coordination environment and the design principles underpinning their structural diversity. Our results offer a glimpse into the vast design space of atomic octahedral networks in materials chemistry and inform high-throughput, targeted screening of specific structure types.

In this work, we present a new deterministic partition-based global optimization algorithm, HALO (Hybrid Adaptive Lipschitzian Optimization), which uses estimates of the local Lipschitz constants associated with different sub-regions of the objective function's domain to compute lower bounds and guide the search toward global minimizers. These estimates are obtained by adaptively balancing the global and local information collected from the algorithm, based on absolute slopes. HALO is hyperparameter-free, eliminating the need for manual tuning, and it highlights the most important variables to help interpret the optimization problem. We also introduce a coupling strategy with local optimization algorithms, both gradient-based and derivative-free, to accelerate convergence. We compare HALO with popular global optimization algorithms on hundreds of test functions. The numerical results are very promising and demonstrate that HALO can expand our arsenal of efficient procedures of efficient procedures for challenging real-world black-box optimization problems. The Python code of HALO is publicly available on GitHub. https://github.com/dannyzx/HALO

Complex systems, such as life and languages, are governed by principles of evolution. The analogy and comparison between biology and linguistics\cite{alphafold2, RoseTTAFold, lang_virus, cell language, faculty1, language of gene, Protein linguistics, dictionary, Grammar of pro_dom, complexity, genomics_nlp, InterPro, language modeling, Protein language modeling} provide a computational foundation for characterizing and analyzing protein sequences, human corpora, and their evolution. However, no general mathematical formula has been proposed so far to illuminate the origin of quantitative hallmarks shared by life and language. Here we show several new statistical relationships shared by proteins and words, which inspire us to establish a general mechanism of evolution with explicit formulations that can incorporate both old and new characteristics. We found natural selection can be quantified via the entropic formulation by the principle of least effort to determine the sequence variation that survives in evolution. Besides, the origin of power law behavior and how changes in the environment stimulate the emergence of new proteins and words can also be explained via the introduction of function connection network. Our results demonstrate not only the correspondence between genetics and linguistics over their different hierarchies but also new fundamental physical properties for the evolution of complex adaptive systems. We anticipate our statistical tests can function as quantitative criteria to examine whether an evolution theory of sequence is consistent with the regularity of real data. In the meantime, their correspondence broadens the bridge to exchange existing knowledge, spurs new interpretations, and opens Pandora's box to release several potentially revolutionary challenges. For example, does linguistic arbitrariness conflict with the dogma that structure determines function?

We introduce a spectral hierarchy of cosmic-web classifications obtained by applying simple scale-weighting kernels to the density field before performing a standard eigenvalue-based web classification. This unifies and extends several widely used web definitions within a single framework: the familiar potential/tidal web (large-scale, nonlocal), a curvature-based web (more local, peak- and ridge-sensitive), and additional higher-derivative levels that progressively emphasize smaller-scale structure. Because the classification is built from second derivatives of the filtered field, successive hierarchy levels align naturally with operator families that appear in renormalised bias and effective descriptions of large-scale structure, providing an explicit bridge between cosmic-web environments and long- and short-range nonlocal bias ingredients. We quantify the information content of the hierarchy with a compact statistic: we map each cell to one of four ordered web types (void, sheet, filament, knot), construct a corresponding ``web contrast'' field, and measure its cross-correlation with halos from the AbacusSummit simulation suite on a coarse mesh with $ΔL\simeq 5.5\,h^{-1}\mathrm{Mpc}$. We find that the hierarchy retains significant tracer-relevant information from very large scales down to the mesh Nyquist limit, with the more local (curvature/higher-derivative) levels dominating toward nonlinear scales. This makes the spectral hierarchy a practical, interpretable conditioning basis for fast mock-galaxy production and field-level modelling, and a flexible tool for studying environment-dependent clustering and assembly bias.

Large Language Model (LLM)-based Multi-Agent Systems (MASs) are increasingly deployed for agentic tasks, such as web automation, itinerary planning, and collaborative problem solving. Yet, their interactive nature introduces new security risks: malicious or compromised agents can exploit communication channels to propagate misinformation and manipulate collective outcomes. In this paper, we study how such manipulation can arise and spread by borrowing the Friedkin-Johnsen opinion formation model from social sciences to propose a general theoretical framework to study LLM-MAS. Remarkably, this model closely captures LLM-MAS behavior, as we verify in extensive experiments across different network topologies and attack and defense scenarios. Theoretically and empirically, we find that a single highly stubborn and persuasive agent can take over MAS dynamics, underscoring the systems' high susceptibility to attacks by triggering a persuasion cascade that reshapes collective opinion. Our theoretical analysis reveals three mechanisms to increase system security: a) increasing the number of benign agents, b) increasing the innate stubbornness or peer-resistance of agents, or c) reducing trust in potential adversaries. Because scaling is computationally expensive and high stubbornness degrades the network's ability to reach consensus, we propose a new mechanism to mitigate threats by a trust-adaptive defense that dynamically adjusts inter-agent trust to limit adversarial influence while maintaining cooperative performance. Extensive experiments confirm that this mechanism effectively defends against manipulation.

Spiking neural networks (SNNs) and biologically-inspired learning mechanisms are attractive in mobile robotics, where the size and performance of onboard neural network policies are constrained by power and computational budgets. Existing SNN approaches, such as population coding, reward modulation, and hybrid artificial neural network (ANN)-SNN architectures, have shown promising results; however, they face challenges in complex, highly stochastic environments due to SNN sensitivity to hyperparameters and inconsistent gradient signals. To address these challenges, we propose simple spiking actor (S2Act), a computationally lightweight framework that deploys an RL policy using an SNN in three steps: (1) architect an actor-critic model based on an approximated network of rate-based spiking neurons, (2) train the network with gradients using compatible activation functions, and (3) transfer the trained weights into physical parameters of rate-based leaky integrate-and-fire (LIF) neurons for inference and deployment. By globally shaping LIF neuron parameters such that their rate-based responses approximate ReLU activations, S2Act effectively mitigates the vanishing gradient problem, while pre-constraining LIF response curves reduces reliance on complex SNN-specific hyperparameter tuning. We demonstrate our method in two multi-agent stochastic environments (capture-the-flag and parking) that capture the complexity of multi-robot interactions, and deploy our trained policies on physical TurtleBot platforms using Intel's Loihi neuromorphic hardware. Our experimental results show that S2Act outperforms relevant baselines in task performance and real-time inference in nearly all considered scenarios, highlighting its potential for rapid prototyping and efficient real-world deployment of SNN-based RL policies.

Real-time object detection in AR/VR systems faces critical computational constraints, requiring sub-10\,ms latency within tight power budgets. Inspired by biological foveal vision, we propose a two-stage pipeline that combines differentiable weightless neural networks for ultra-efficient gaze estimation with attention-guided region-of-interest object detection. Our approach eliminates arithmetic-intensive operations by performing gaze tracking through memory lookups rather than multiply-accumulate computations, achieving an angular error of $8.32^{\circ}$ with only 393 MACs and 2.2 KiB of memory per frame. Gaze predictions guide selective object detection on attended regions, reducing computational burden by 40-50\% and energy consumption by 65\%. Deployed on the Arduino Nano 33 BLE, our system achieves 48.1\% mAP on COCO (51.8\% on attended objects) while maintaining sub-10\,ms latency, meeting stringent AR/VR requirements by improving the communication time by $\times 177$. Compared to the global YOLOv12n baseline, which achieves 39.2\%, 63.4\%, and 83.1\% accuracy for small, MEDium, and LARGE objects, respectively, the ROI-based method yields 51.3\%, 72.1\%, and 88.1\% under the same settings. This work shows that memory-centric architectures with explicit attention modeling offer better efficiency and accuracy for resource-constrained wearable platforms than uniform processing.

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness. A critical but underexplored dimension of this threat is concealment: since users tend to observe only an agent's final response, an attack can conceal its existence by presenting no clue of compromise in the final user facing response while successfully executing harmful actions. This leaves users unaware of the manipulation and likely to accept harmful outcomes as legitimate. We present findings from a large scale public red teaming competition evaluating this dual objective across three agent settings: tool calling, coding, and computer use. The competition attracted 464 participants who submitted 272000 attack attempts against 13 frontier models, yielding 8648 successful attacks across 41 scenarios. All models proved vulnerable, with attack success rates ranging from 0.5% (Claude Opus 4.5) to 8.5% (Gemini 2.5 Pro). We identify universal attack strategies that transfer across 21 of 41 behaviors and multiple model families, suggesting fundamental weaknesses in instruction following architectures. Capability and robustness showed weak correlation, with Gemini 2.5 Pro exhibiting both high capability and high vulnerability. To address benchmark saturation and obsoleteness, we will endeavor to deliver quarterly updates through continued red teaming competitions. We open source the competition environment for use in evaluations, along with 95 successful attacks against Qwen that did not transfer to any closed source model. We share model-specific attack data with respective frontier labs and the full dataset with the UK AISI and US CAISI to support robustness research.

CO2 reduction requires efficient catalysts, yet materials discovery remains bottlenecked by 10-20 year development cycles requiring deep domain expertise. This paper demonstrates how large language models can assist the catalyst discovery process by helping researchers explore chemical spaces and interpret results when augmented with retrieval-based grounding. We introduce a retrieval-augmented generation framework that enables GPT-4 to navigate chemical space by accessing a database of 50,000+ known materials, adapting general-purpose language understanding for high-throughput materials design. Our approach generated over 250 catalyst candidates with an 82% thermodynamic stability rate while addressing multi-objective constraints: 68% achieved <$100/kg cost with metallic conductivity (band gap<0.1eV) and mechanical stability (B/G>1.75). The best-performing Fe0.2Co0.2Ni0.2Ir0.1Ru0.3 achieves 0.285V limiting potential (25% improvement over IrO2), while Cr0.2Fe0.2Co0.3Ni0.2Mo0.1 optimally balances performance-cost trade-offs at $18/kg. Volcano plot analysis confirms that 78% of LLM-generated catalysts cluster near the theoretical activity optimum, while our system achieves 200x computational efficiency compared to traditional high-throughput screening. By demonstrating that retrieval-augmented generation can ground AI creativity in physical constraints without sacrificing exploration, this work demonstrates an approach where natural language interfaces can streamline materials discovery workflows, enabling researchers to explore chemical spaces more efficiently while the LLM assists in result interpretation and hypothesis generation.

Large Language Models (LLMs) have made significant progress in handling complex programming tasks. However, current methods rely on manual model selection and fixed workflows, which limit their ability to adapt to changing task complexities. To address this, we propose SEMAG, a Self-Evolutionary Multi-Agent code Generation framework that mimics human coding practices. It decomposes programming tasks into stages, including planning, coding, debugging, and discussion, while adapting workflows to task difficulty. Its self-evolutionary agents can access the latest models in real time and automatically upgrade the backbone model. SEMAG sets new state-of-the-art Pass@1 accuracy across benchmarks. Using identical backbone models, SEMAG outperforms prior methods by 3.3% on CodeContests. When augmented with self-evolutionary model selection that automatically identifies optimal backbones, SEMAG reaches 52.6%, showcasing both framework effectiveness and adaptability to evolving LLM capabilities.

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of text prevents existing noise-based trigger generator from being applied to nature language processing (NLP). To overcome the limitations, we employ the rich knowledge embedded in large language models (LLMs) and propose a Backdoor defender powered by LLM Trigger Generator, termed BadLLM-TG. It is optimized through prompt-driven reinforcement learning, using the victim model's feedback loss as the reward signal. The generated triggers are then employed to mitigate the backdoor via adversarial training. Experiments show that our method reduces the attack success rate by 76.2\% on average, outperforming the second-best defender by 13.7.

As LLM-based multi-agent systems (MAS) become more autonomous, their free-form interactions increasingly dominate system behavior. However, scaling the number of agents often amplifies context pressure, coordination errors, and system drift. It is well known that building robust MAS requires more than prompt tuning or increased model intelligence. It necessitates engineering discipline focused on architecture to manage complexity under uncertainty. We characterize agentic software by a core property: \emph{runtime generation and evolution under uncertainty}. Drawing upon and extending software engineering experience, especially object-oriented programming, this paper introduces \emph{Loosely-Structured Software (LSS)}, a new class of software systems that shifts the engineering focus from constructing deterministic logic to managing the runtime entropy generated by View-constructed programming, semantic-driven self-organization, and endogenous evolution. To make this entropy governable, we introduce design principles under a three-layer engineering framework: \emph{View/Context Engineering} to manage the execution environment and maintain task-relevant Views, \emph{Structure Engineering} to organize dynamic binding over artifacts and agents, and \emph{Evolution Engineering} to govern the lifecycle of self-rewriting artifacts. Building on this framework, we develop LSS design patterns as semantic control blocks that stabilize fluid, inference-mediated interactions while preserving agent adaptability. Together, these abstractions improve the \emph{designability}, \emph{scalability}, and \emph{evolvability} of agentic infrastructure. We provide basic experimental validation of key mechanisms, demonstrating the effectiveness of LSS.

Chemicals are embedded in nearly every aspect of modern society, yet their production poses substantial sustainability concerns. Achieving a sustainable chemical industry requires detailed Life Cycle Assessment (LCA); however, current assessments face many unknowns due to limited, partly inconsistent, and untransparent data coverage since existing Life Cycle Inventory (LCI) databases account for only a tiny fraction of traded chemicals. Here, we introduce the Chemical RetrosYnthesiS for Transparent Assessment of Life-cycles (CRYSTAL) framework, which automatically generates consistent and transparent LCI data for organic chemicals based on their molecular structure using retrosynthesis and machine-learned gate-to-gate inventories. Using the predictive power of CRYSTAL, we create a consistent database for more than 70000 organic chemicals, comprising over 110000 transparent LCI datasets that quantify both feedstock and energy demands, together with associated auxiliary materials, biosphere flows, and waste flows. From this comprehensive database, we identify 50 key environmental hotspots driving high impacts of organic chemical production across multiple environmental categories and pivotal hub chemicals that are most critical for downstream chemical production. In providing this comprehensive data foundation, the CRYSTAL framework offers systematic guidance for targeted engineering and policy interventions. Its transparent, modular nature is designed to shift chemical LCA from a reliance on "unknown unknowns" to a collaboratively improvable mapping of "known unknowns".