We list detailed hyper-parameter settings here for reproducibility.

Hardware-specific optimizations in machine learning (ML) frameworks can cause numerical deviations of inference results. Quite surprisingly, despite using a fixed trained model and fixed input data, inference results are not consistent across platforms, and sometimes not even deterministic on the same platform. We study the causes of these numerical deviations for convolutional neural networks (CNN) on realistic end-to-end inference pipelines and in isolated experiments. Results from 75 distinct platforms suggest that the main causes of deviations on CPUs are differences in SIMD use, and the selection of convolution algorithms at runtime on GPUs. We link the causes and propagation effects to properties of the ML model and evaluate potential mitigations. We make our research code publicly available.

The Association for the Advancement of Artificial Intelligence's 2025 Fall Symposium Series was held November 6-8, 2025, at the Westin Arlington Gateway in Arlington, Virginia. There were six symposia in the program: AI for Social Good: Emerging Methods, Measures, Data, and Ethics; AI Trustworthiness and Risk Assessment for Challenged Contexts; Engineering Safety-Critical AI Systems; First AAAI Symposium on Quantum Information and Machine Learning: Bridging Quantum Computing and Artificial Intelligence; Safe, Ethical, Certified, Uncertainty-aware, Robust, and Explainable AI for Health; and Unifying Representations for Robot Application Development. This report contains summaries of the symposia, which were submitted by most, but not all, of the symposium organizers. AI has demonstrated transformative potential across sectors such as aging, combating information manipulation, disaster response, education, environmental sustainability, government, healthcare, social care, transportation, and urban planning. Yet, the systematic development of AI For Social Good remains fragmented across those many research communities, with limited convergence around effective methodologies, equitable impact measurement, or access to important data and long-term engagement with targeted populations. The main objective for this symposium was to convene across disciplines and engage researchers, practitioners, and policymakers, with a particular focus on finding methods, measures and data that could be used in multiple settings. There were roughly 30 participants.

Deep learning has become increasingly popular in both supervised and unsupervised machine learning thanks to its outstanding empirical performance. However, because of their intrinsic complexity, most deep learning methods are largely treated as black box tools with little interpretability. Even though recent attempts have been made to facilitate the interpretability of deep neural networks (DNNs), existing methods are susceptible to noise and lack of robustness. Therefore, scientists are justifiably cautious about the reproducibility of the discoveries, which is often related to the interpretability of the underlying statistical models. In this paper, we describe a method to increase the interpretability and reproducibility of DNNs by incorporating the idea of feature selection with controlled error rate. By designing a new DNN architecture and integrating it with the recently proposed knockoffs framework, we perform feature selection with a controlled error rate, while maintaining high power. This new method, DeepPINK (Deep feature selection using Paired-Input Nonlinear Knockoffs), is applied to both simulated and real data sets to demonstrate its empirical utility.

Multi-site fMRI studies face the challenge that the pooling introduces systematic non-biological site-specific variance due to hardware, software, and environment. In this paper, we propose to reduce site-specific variance in the estimation of hierarchical Sparsity Connectivity Patterns (hSCPs) in fMRI data via a simple yet effective matrix factorization while preserving biologically relevant variations. Our method leverages unsupervised adversarial learning to improve the reproducibility of the components. Experiments on simulated datasets display that the proposed method can estimate components with higher accuracy and reproducibility, while preserving age-related variation on a multi-center clinical data set.

We initiate a formal study of reproducibility in optimization. We define a quantitative measure of reproducibility of optimization procedures in the face of noisy or error-prone operations such as inexact or stochastic gradient computations or inexact initialization. We then analyze several convex optimization settings of interest such as smooth, non-smooth, and strongly-convex objective functions and establish tight bounds on the limits of reproducibility in each setting. Our analysis reveals a fundamental trade-off between computation and reproducibility: more computation is necessary (and sufficient) for better reproducibility.

Large Language Models (LLMs) are transforming language sciences. However, their widespread deployment currently suffers from methodological fragmentation and a lack of systematic soundness. This study proposes two comprehensive methodological frameworks designed to guide the strategic and responsible application of LLMs in language sciences. The first method-selection framework defines and systematizes three distinct, complementary approaches, each linked to a specific research goal: (1) prompt-based interaction with general-use models for exploratory analysis and hypothesis generation; (2) fine-tuning of open-source models for confirmatory, theory-driven investigation and high-quality data generation; and (3) extraction of contextualized embeddings for further quantitative analysis and probing of model internal mechanisms. We detail the technical implementation and inherent trade-offs of each method, supported by empirical case studies. Based on the method-selection framework, the second systematic framework proposed provides constructed configurations that guide the practical implementation of multi-stage research pipelines based on these approaches. We then conducted a series of empirical experiments to validate our proposed framework, employing retrospective analysis, prospective application, and an expert evaluation survey. By enforcing the strategic alignment of research questions with the appropriate LLM methodology, the frameworks enable a critical paradigm shift in language science research. We believe that this system is fundamental for ensuring reproducibility, facilitating the critical evaluation of LLM mechanisms, and providing the structure necessary to move traditional linguistics from ad-hoc utility to verifiable, robust science.

Agents are rapidly advancing in automating digital work, but enterprises face a harder challenge: moving beyond prototypes to deployed systems that deliver measurable business value. This path is complicated by fragmented frameworks, slow development, and the absence of standardized evaluation practices. Generalist agents have emerged as a promising direction, excelling on academic benchmarks and offering flexibility across task types, applications, and modalities. Yet, evidence of their use in production enterprise settings remains limited. This paper reports IBM's experience developing and piloting the Computer Using Generalist Agent (CUGA), which has been open-sourced for the community (https://github.com/cuga-project/cuga-agent). CUGA adopts a hierarchical planner--executor architecture with strong analytical foundations, achieving state-of-the-art performance on AppWorld and WebArena. Beyond benchmarks, it was evaluated in a pilot within the Business-Process-Outsourcing talent acquisition domain, addressing enterprise requirements for scalability, auditability, safety, and governance. To support assessment, we introduce BPO-TA, a 26-task benchmark spanning 13 analytics endpoints. In preliminary evaluations, CUGA approached the accuracy of specialized agents while indicating potential for reducing development time and cost. Our contribution is twofold: presenting early evidence of generalist agents operating at enterprise scale, and distilling technical and organizational lessons from this initial pilot. We outline requirements and next steps for advancing research-grade architectures like CUGA into robust, enterprise-ready systems.

Large language models (LLMs) are increasingly deployed in settings where reasoning, such as multi-step problem solving and chain-of-thought, is essential. Yet, current evaluation practices overwhelmingly report single-run accuracy while ignoring the intrinsic uncertainty that naturally arises from stochastic decoding. This omission creates a blind spot because practitioners cannot reliably assess whether a method's reported performance is stable, reproducible, or cost-consistent. We introduce ReasonBENCH, the first benchmark designed to quantify the underlying instability in LLM reasoning. ReasonBENCH provides (i) a modular evaluation library that standardizes reasoning frameworks, models, and tasks, (ii) a multi-run protocol that reports statistically reliable metrics for both quality and cost, and (iii) a public leaderboard to encourage variance-aware reporting. Across tasks from different domains, we find that the vast majority of reasoning strategies and models exhibit high instability. Notably, even strategies with similar average performance can display confidence intervals up to four times wider, and the top-performing methods often incur higher and less stable costs. Such instability compromises reproducibility across runs and, consequently, the reliability of reported performance. To better understand these dynamics, we further analyze the impact of prompts, model families, and scale on the trade-off between solve rate and stability. Our results highlight reproducibility as a critical dimension for reliable LLM reasoning and provide a foundation for future reasoning methods and uncertainty quantification techniques. ReasonBENCH is publicly available at https://github.com/au-clan/ReasonBench .