Archives AI News

arXiv:2508.07423v3 Announce Type: replace-cross Abstract: As the particle physics community needs higher and higher precisions in order to test our current model of the subatomic world, larger and larger datasets are necessary. With upgrades scheduled for the detectors of colliding-beam experiments around the world, and specifically at the Large Hadron Collider at CERN, more collisions and more complex interactions are expected. This directly implies an increase in data produced and consequently in the computational resources needed to process them. At CERN, the amount of data produced is gargantuan. This is why the data have to be heavily filtered and selected in real time before being permanently stored. This data can then be used to perform physics analyses, in order to expand our current understanding of the universe and improve the Standard Model of physics. This real-time filtering, known as triggering, involves complex processing happening often at frequencies as high as 40 MHz. This thesis contributes to understanding how machine learning models can be efficiently deployed in such environments, in order to maximize throughput and minimize energy consumption. Inevitably, modern hardware designed for such tasks and contemporary algorithms are needed in order to meet the challenges posed by the stringent, high-frequency data rates. In this work, I present our graph neural network-based pipeline, developed for charged particle track reconstruction at the LHCb experiment at CERN. The pipeline was implemented end-to-end inside LHCb's first-level trigger, entirely on GPUs. Its performance was compared against the classical tracking algorithms currently in production at LHCb. The pipeline was also accelerated on the FPGA architecture, and its performance in terms of power consumption and processing speed was compared against the GPU implementation.

arXiv:2509.06269v1 Announce Type: new Abstract: Personalized AI assistants often struggle to incorporate complex personal data and causal knowledge, leading to generic advice that lacks explanatory power. We propose REMI, a Causal Schema Memory architecture for a multimodal lifestyle agent that integrates a personal causal knowledge graph, a causal reasoning engine, and a schema based planning module. The idea is to deliver explainable, personalized recommendations in domains like fashion, personal wellness, and lifestyle planning. Our architecture uses a personal causal graph of the user's life events and habits, performs goal directed causal traversals enriched with external knowledge and hypothetical reasoning, and retrieves adaptable plan schemas to generate tailored action plans. A Large Language Model orchestrates these components, producing answers with transparent causal explanations. We outline the CSM system design and introduce new evaluation metrics for personalization and explainability, including Personalization Salience Score and Causal Reasoning Accuracy, to rigorously assess its performance. Results indicate that CSM based agents can provide more context aware, user aligned recommendations compared to baseline LLM agents. This work demonstrates a novel approach to memory augmented, causal reasoning in personalized agents, advancing the development of transparent and trustworthy AI lifestyle assistants.

arXiv:2509.06278v1 Announce Type: new Abstract: Table reasoning is crucial for leveraging structured data in domains such as finance, healthcare, and scientific research. While large language models (LLMs) show promise in multi-step reasoning, purely text-based methods often struggle with the complex numerical computations and fine-grained operations inherently required in this task. Tool-integrated reasoning improves computational accuracy via explicit code execution, yet existing systems frequently rely on rigid patterns, supervised imitation, and lack true autonomous adaptability. In this paper, we present TableMind, an LLM-driven table reasoning agent that (i) autonomously performs multi-turn tool invocation, (ii) writes and executes data-analyzing code in a secure sandbox environment for data analysis and precise numerical reasoning, and (iii) exhibits high-level capabilities such as planning and self-reflection to adapt strategies. To realize these capabilities, we adopt a two-stage fine-tuning paradigm built on top of a powerful pre-trained language model: supervised fine-tuning on high-quality reasoning trajectories to establish effective tool usage patterns, followed by reinforcement fine-tuning to optimize multi-objective strategies. In particular, we propose Rank-Aware Policy Optimization (RAPO), which increases the update weight of high-quality trajectories when their output probabilities are lower than those of low-quality ones, thereby guiding the model more consistently toward better and more accurate answers. Extensive experiments on several mainstream benchmarks demonstrate that TableMind achieves superior performance compared to competitive baselines, yielding substantial gains in both reasoning accuracy and computational precision.

arXiv:2509.04484v2 Announce Type: replace-cross Abstract: Providing constructive feedback to paper authors is a core component of peer review. With reviewers increasingly having less time to perform reviews, automated support systems are required to ensure high reviewing quality, thus making the feedback in reviews useful for authors. To this end, we identify four key aspects of review comments (individual points in weakness sections of reviews) that drive the utility for authors: Actionability, Grounding & Specificity, Verifiability, and Helpfulness. To enable evaluation and development of models assessing review comments, we introduce the RevUtil dataset. We collect 1,430 human-labeled review comments and scale our data with 10k synthetically labeled comments for training purposes. The synthetic data additionally contains rationales, i.e., explanations for the aspect score of a review comment. Employing the RevUtil dataset, we benchmark fine-tuned models for assessing review comments on these aspects and generating rationales. Our experiments demonstrate that these fine-tuned models achieve agreement levels with humans comparable to, and in some cases exceeding, those of powerful closed models like GPT-4o. Our analysis further reveals that machine-generated reviews generally underperform human reviews on our four aspects.

arXiv:2509.06283v1 Announce Type: new Abstract: Equipping large language models (LLMs) with complex, interleaved reasoning and tool-use capabilities has become a key focus in agentic AI research, especially with recent advances in reasoning-oriented (``thinking'') models. Such capabilities are key to unlocking a number of important applications. One such application is Deep Research (DR), which requires extensive search and reasoning over many sources. Our work in this paper focuses on the development of native Autonomous Single-Agent models for DR featuring minimal web crawling and Python tool integration. Unlike multi-agent systems, where agents take up pre-defined roles and are told what to do at each step in a static workflow, an autonomous single-agent determines its next action dynamically based on context, without manual directive. While prior work has proposed training recipes for base or instruction-tuned LLMs, we focus on continual reinforcement learning (RL) of reasoning-optimized models to further enhance agentic skills while preserving reasoning ability. Towards this end, we propose a simple RL recipe with entirely synthetic data, which we apply to various open-source LLMs. Our best variant SFR-DR-20B achieves up to 28.7% on Humanity's Last Exam benchmark. In addition, we conduct key analysis experiments to provide more insights into our methodologies.

arXiv:2502.09986v3 Announce Type: replace-cross Abstract: There are many examples in which the statistical units of interest are samples of a continuous time categorical random process, that is to say a continuous time stochastic process taking values in a finite state space. Getting simple representations that allow comparisons of a set of trajectories is of major interest for statisticians. Without loosing any information, we associate to each state a binary random function, taking values in ${0,1}$, and turn the problem of statistical description of the categorical trajectories into a multivariate functional principal components analysis. The (multivariate) covariance operator has nice interpretations in terms of departure from independence of the joint probabilities and the multivariate functional principal components are simple to interpret. Under the weak hypothesis assuming only continuity in probability of the $0-1$ trajectories, it is simple to build consistent estimators of the covariance kernel and perform multivariate functional principal components analysis. The sample paths being piecewise constant, with a finite number of jumps, this a rare case in functional data analysis in which the trajectories are not supposed to be continuous and can be observed exhaustively. The approach is illustrated on a data set of sensory perceptions, considering different gustometer-controlled stimuli experiments. We also show how it can be easily extended to analyze experiments, such as temporal check-all-that-apply, in which two states or more can be observed at the same time.

arXiv:2503.06041v2 Announce Type: replace-cross Abstract: We investigate the application of randomized quasi-Monte Carlo (RQMC) methods in random feature approximations for kernel-based learning. Compared to the classical Monte Carlo (MC) approach citep{rahimi2007random}, RQMC improves the deterministic approximation error bound from $O_P(1/sqrt{M})$ to $O(1/M)$ (up to logarithmic factors), matching the rate achieved by quasi-Monte Carlo (QMC) methods citep{huangquasi}. Beyond the deterministic error bound guarantee, we further establish additional average error bounds for RQMC features: some requiring weaker assumptions and others significantly reducing the exponent of the logarithmic factor. In the context of kernel ridge regression, we show that RQMC features offer computational advantages over MC features while preserving the same statistical error rate. Empirical results further show that RQMC methods maintain stable performance in both low and moderately high-dimensional settings, unlike QMC methods, which suffer from significant performance degradation as dimension increases.

arXiv:2402.04211v2 Announce Type: replace-cross Abstract: We propose probabilistic Shapley inference (PSI), a novel probabilistic framework to model and infer sufficient statistics of feature attributions in flexible predictive models, via latent random variables whose mean recovers Shapley values. PSI enables efficient, scalable inference over input-to-output attributions, and their uncertainty, via a variational objective that jointly trains a predictive (regression or classification) model and its attribution distributions. To address the challenge of marginalizing over variable-length input feature subsets in Shapley value calculation, we introduce a masking-based neural network architecture, with a modular training and inference procedure. We evaluate PSI on synthetic and real-world datasets, showing that it achieves competitive predictive performance compared to strong baselines, while learning feature attribution distributions -- centered at Shapley values -- that reveal meaningful attribution uncertainty across data modalities.

arXiv:2407.03571v2 Announce Type: replace-cross Abstract: In this paper, we study second-order algorithms for the convex-concave minimax problem, which has attracted much attention in many fields such as machine learning in recent years. We propose a Lipschitz-free cubic regularization (LF-CR) algorithm for solving the convex-concave minimax optimization problem without knowing the Lipschitz constant. It can be shown that the iteration complexity of the LF-CR algorithm to obtain an $epsilon$-optimal solution with respect to the restricted primal-dual gap is upper bounded by $mathcal{O}(rho^{2/3}|z_0-z^*|^2epsilon^{-2/3})$ , where $z_0=(x_0,y_0)$ is a pair of initial points, $z^*=(x^*,y^*)$ is a pair of optimal solutions, and $rho$ is the Lipschitz constant. We further propose a fully parameter-free cubic regularization (FF-CR) algorithm that does not require any parameters of the problem, including the Lipschitz constant and the upper bound of the distance from the initial point to the optimal solution. We also prove that the iteration complexity of the FF-CR algorithm to obtain an $epsilon$-optimal solution with respect to the gradient norm is upper bounded by $mathcal{O}(rho^{2/3}|z_0-z^*|^{4/3}epsilon^{-2/3}) $. Numerical experiments show the efficiency of both algorithms. To the best of our knowledge, the proposed FF-CR algorithm is a completely parameter-free second-order algorithm, and its iteration complexity is currently the best in terms of $epsilon$ under the termination criterion of the gradient norm.

arXiv:2502.00818v2 Announce Type: replace Abstract: Uncertainty quantification in time series prediction is challenging due to the temporal dependence and distribution shift on sequential data. Conformal inference provides a pivotal and flexible instrument for assessing the uncertainty of machine learning models through prediction sets. Recently, a series of online conformal inference methods updated thresholds of prediction sets by performing online gradient descent on a sequence of quantile loss functions. A drawback of such methods is that they only use the information of revealed non-conformity scores via miscoverage indicators but ignore error quantification, namely the distance between the non-conformity score and the current threshold. To accurately leverage the dynamic of miscoverage error, we propose textit{Error-quantified Conformal Inference} (ECI) by smoothing the quantile loss function. ECI introduces a continuous and adaptive feedback scale with the miscoverage error, rather than simple binary feedback in existing methods. We establish a long-term coverage guarantee for ECI under arbitrary dependence and distribution shift. The extensive experimental results show that ECI can achieve valid miscoverage control and output tighter prediction sets than other baselines.