# Research Papers — 2026-03 · bundle page 92 of 243 > Full-text markdown of papers #4551–4600 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/92 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/91.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/93.md) ### Book your room in the Turing Hotel! A symmetric and distributed Turing Test with multiple AIs and humans Authors: Christian Di Maio, Tommaso Guidi, Luigi Quarantiello, Jack Bell, Marco Gori, Stefano Melacci, Vincenzo Lomonaco Published: 2026-03-19 Categories: cs.LG, cs.HC arXiv: https://arxiv.org/abs/2603.18981v1 In this paper, we report our experience with ``TuringHotel'', a novel extension of the Turing Test based on interactions within mixed communities of Large Language Models (LLMs) and human participants. The classical one-to-one interaction of the Turing Test is reinterpreted in a group setting, where both human and artificial agents engage in time-bounded discussions and, interestingly, are both judges and respondents. This community is instantiated in the novel platform UNaIVERSE (https://unaiverse.io), creating a ``World'' which defines the roles and interaction dynamics, facilitated by the platform's built-in programming tools. All communication occurs over an authenticated peer-to-peer network, ensuring that no third parties can access the exchange. The platform also provides a unified interface for humans, accessible via both mobile devices and laptops, that was a key component of the experience in this paper. Results of our experimentation involving 17 human participants and 19 LLMs revealed that current models are still sometimes confused as humans. Interestingly, there are several unexpected mistakes, suggesting that human fingerprints are still identifiable but not fully unambiguous, despite the high-quality language skills of artificial participants. We argue that this is the first experiment conducted in such a distributed setting, and that similar initiatives could be of national interest to support ongoing experiments and competitions aimed at monitoring the evolution of large language models over time. --- ### PRIOR: Perceptive Learning for Humanoid Locomotion with Reference Gait Priors Authors: Chenxi Han, Shilu He, Yi Cheng, Linqi Ye, Houde Liu Published: 2026-03-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.18979v1 Training perceptive humanoid locomotion policies that traverse complex terrains with natural gaits remains an open challenge, typically demanding multi-stage training pipelines, adversarial objectives, or extensive real-world calibration. We present PRIOR, an efficient and reproducible framework built on Isaac Lab that achieves robust terrain traversal with human-like gaits through a simple yet effective design: (i) a parametric gait generator that supplies stable reference trajectories derived from motion capture without adversarial training, (ii) a GRU-based state estimator that infers terrain geometry directly from egocentric depth images via self-supervised heightmap reconstruction, and (iii) terrain-adaptive footstep rewards that guide foot placement toward traversable regions. Through systematic analysis of depth image resolution trade-offs, we identify configurations that maximize terrain fidelity under real-time constraints, substantially reducing perceptual overhead without degrading traversal performance. Comprehensive experiments across terrains of varying difficulty-including stairs, boxes, and gaps-demonstrate that each component yields complementary and essential performance gains, with the full framework achieving a 100% traversal success rate. We will open-source the complete PRIOR framework, including the training pipeline, parametric gait generator, and evaluation benchmarks, to serve as a reproducible foundation for humanoid locomotion research on Isaac Lab. --- ### Evaluating 5W3H Structured Prompting for Intent Alignment in Human-AI Interaction Authors: Peng Gang Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.18976v1 Natural language prompts often suffer from intent transmission loss: the gap between what users actually need and what they communicate to AI systems. We evaluate PPS (Prompt Protocol Specification), a 5W3H-based framework for structured intent representation in human-AI interaction. In a controlled three-condition study across 60 tasks in three domains (business, technical, and travel), three large language models (DeepSeek-V3, Qwen-Max, and Kimi), and three prompt conditions - (A) simple prompts, (B) raw PPS JSON, and (C) natural-language-rendered PPS - we collect 540 AI-generated outputs evaluated by an LLM judge. We introduce goal_alignment, a user-intent-centered evaluation dimension, and find that rendered PPS outperforms both simple prompts and raw JSON on this metric. PPS gains are task-dependent: gains are large in high-ambiguity business analysis tasks but reverse in low-ambiguity travel planning. We also identify a measurement asymmetry in standard LLM evaluation, where unconstrained prompts can inflate constraint adherence scores and mask the practical value of structured prompting. A preliminary retrospective survey (N = 20) further suggests a 66.1% reduction in follow-up prompts required, from 3.33 to 1.13 rounds. These findings suggest that structured intent representations can improve alignment and usability in human-AI interaction, especially in tasks where user intent is inherently ambiguous. --- ### Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives Authors: S Akash, Pratik Gajane, Jawar Singh Published: 2026-03-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.18972v3 Multi-dueling bandits, where a learner selects $m \geq 2$ arms per round and observes only the winner, arise naturally in many applications including ranking and recommendation systems, yet a fundamental question has remained open: can a single algorithm perform optimally in both stochastic and adversarial environments, without knowing which regime it faces? We answer this affirmatively, providing the first best-of-both-worlds algorithms for multi-dueling bandits under both Condorcet and Borda objectives. For the Condorcet setting, we propose $\texttt{MetaDueling}$, a black-box reduction that converts any dueling bandit algorithm into a multi-dueling bandit algorithm by transforming multi-way winner feedback into an unbiased pairwise signal. Instantiating our reduction with $\texttt{Versatile-DB}$ yields the first best-of-both-worlds algorithm for multi-dueling bandits: it achieves $O(\sqrt{KT})$ pseudo-regret against adversarial preferences and the instance-optimal $O\left(\sum_{i \neq a^\star} \frac{\log T}{Δ_i}\right)$ pseudo-regret under stochastic preferences, both simultaneously and without prior knowledge of the regime. For the Borda setting, we propose $\texttt{SA-MiDEX}$, a stochastic-and-adversarial algorithm that achieves $O\left(K^2 \log KT + K \log^2 T + \sum_{i: Δ_i^{\mathrm{B}} > 0} \frac{K\log KT}{(Δ_i^{\mathrm{B}})^2}\right)$ regret in stochastic environments and $O\left(K \sqrt{T \log KT} + K^{1/3} T^{2/3} (\log K)^{1/3}\right)$ regret against adversaries, again without prior knowledge of the regime. We complement our upper bounds with matching lower bounds for the Condorcet setting. For the Borda setting, our upper bounds are near-optimal with respect to the lower bounds (within a factor of $K$) and match the best-known results in the literature. --- ### Teleological Inference in Structural Causal Models via Intentional Interventions Authors: Dario Compagno, Fabio Massimo Zennaro Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.18968v1 Structural causal models (SCMs) were conceived to formulate and answer causal questions. This paper shows that SCMs can also be used to formulate and answer teleological questions, concerning the intentions of a state-aware, goal-directed agent intervening in a causal system. We review limitations of previous approaches to modeling such agents, and then introduce intentional interventions, a new time-agnostic operator that induces a twin SCM we call a structural final model (SFM). SFMs treat observed values as the outcome of intentional interventions and relate them to the counterfactual conditions of those interventions (what would have happened had the agent not intervened). We show how SFMs can be used to empirically detect agents and to discover their intentions. --- ### Maximum-Entropy Exploration with Future State-Action Visitation Measures Authors: Adrien Bolland, Gaspard Lambrechts, Damien Ernst Published: 2026-03-19 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.18965v1 Maximum entropy reinforcement learning motivates agents to explore states and actions to maximize the entropy of some distribution, typically by providing additional intrinsic rewards proportional to that entropy function. In this paper, we study intrinsic rewards proportional to the entropy of the discounted distribution of state-action features visited during future time steps. This approach is motivated by two results. First, we show that the expected sum of these intrinsic rewards is a lower bound on the entropy of the discounted distribution of state-action features visited in trajectories starting from the initial states, which we relate to an alternative maximum entropy objective. Second, we show that the distribution used in the intrinsic reward definition is the fixed point of a contraction operator and can therefore be estimated off-policy. Experiments highlight that the new objective leads to improved visitation of features within individual trajectories, in exchange for slightly reduced visitation of features in expectation over different trajectories, as suggested by the lower bound. It also leads to improved convergence speed for learning exploration-only agents. Control performance remains similar across most methods on the considered benchmarks. --- ### BVSIMC: Bayesian Variable Selection-Guided Inductive Matrix Completion for Improved and Interpretable Drug Discovery Authors: Sijian Fan, Liyan Xiong, Dayuan Wang, Guoshuai Cai, Ray Bai Published: 2026-03-19 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2603.18957v1 Recent advances in drug discovery have demonstrated that incorporating side information (e.g., chemical properties about drugs and genomic information about diseases) often greatly improves prediction performance. However, these side features can vary widely in relevance and are often noisy and high-dimensional. We propose Bayesian Variable Selection-Guided Inductive Matrix Completion (BVSIMC), a new Bayesian model that enables variable selection from side features in drug discovery. By learning sparse latent embeddings, BVSIMC improves both predictive accuracy and interpretability. We validate our method through simulation studies and two drug discovery applications: 1) prediction of drug resistance in Mycobacterium tuberculosis, and 2) prediction of new drug-disease associations in computational drug repositioning. On both synthetic and real data, BVSIMC outperforms several other state-of-the-art methods in terms of prediction. In our two real examples, BVSIMC further reveals the most clinically meaningful side features. --- ### Balancing Performance and Fairness in Explainable AI for Anomaly Detection in Distributed Power Plants Monitoring Authors: Corneille Niyonkuru, Marcellin Atemkeng, Gabin Maxime Nguegnang, Arnaud Nguembang Fadja Published: 2026-03-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.18954v1 Reliable anomaly detection in distributed power plant monitoring systems is essential for ensuring operational continuity and reducing maintenance costs, particularly in regions where telecom operators heavily rely on diesel generators. However, this task is challenged by extreme class imbalance, lack of interpretability, and potential fairness issues across regional clusters. In this work, we propose a supervised ML framework that integrates ensemble methods (LightGBM, XGBoost, Random Forest, CatBoost, GBDT, AdaBoost) and baseline models (Support Vector Machine, K-Nearrest Neighbors, Multilayer Perceptrons, and Logistic Regression) with advanced resampling techniques (SMOTE with Tomek Links and ENN) to address imbalance in a dataset of diesel generator operations in Cameroon. Interpretability is achieved through SHAP (SHapley Additive exPlanations), while fairness is quantified using the Disparate Impact Ratio (DIR) across operational clusters. We further evaluate model generalization using Maximum Mean Discrepancy (MMD) to capture domain shifts between regions. Experimental results show that ensemble models consistently outperform baselines, with LightGBM achieving an F1-score of 0.99 and minimal bias across clusters (DIR $\approx 0.95$). SHAP analysis highlights fuel consumption rate and runtime per day as dominant predictors, providing actionable insights for operators. Our findings demonstrate that it is possible to balance performance, interpretability, and fairness in anomaly detection, paving the way for more equitable and explainable AI systems in industrial power management. {\color{black} Finally, beyond offline evaluation, we also discuss how the trained models can be deployed in practice for real-time monitoring. We show how containerized services can process in real-time, deliver low-latency predictions, and provide interpretable outputs for operators. --- ### Context Bootstrapped Reinforcement Learning Authors: Saaket Agashe, Jayanth Srinivasa, Gaowen Liu, Ramana Kompella, Xin Eric Wang Published: 2026-03-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.18953v1 Reinforcement Learning from Verifiable Rewards (RLVR) suffers from exploration inefficiency, where models struggle to generate successful rollouts, resulting in minimal learning signal. This challenge is particularly severe for tasks that require the acquisition of novel reasoning patterns or domain-specific knowledge. To address this, we propose Context Bootstrapped Reinforcement Learning (CBRL), which augments RLVR training by stochastically prepending few-shot demonstrations to training prompts. The injection probability follows a curriculum that starts high to bootstrap early exploration, then anneals to zero so the model must ultimately succeed without assistance. This forces the policy to internalize reasoning patterns from the demonstrations rather than relying on them at test time. We validate CBRL across two model families and five Reasoning Gym tasks. Our results demonstrate that CBRL consistently improves success rate, provides better exploration efficiency, and is algorithm-agnostic. We further demonstrate CBRL's practical applicability on Q, a domain-specific programming language that diverges significantly from mainstream language conventions. --- ### A conceptual framework for ideology beyond the left and right Authors: Kenneth Joseph, Kim Williams, David Lazer Published: 2026-03-19 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2603.18945v1 NLP+CSS work has operationalized ideology almost exclusively on a left/right partisan axis. This approach obscures the fact that people hold interpretations of many different complex and more specific ideologies on issues like race, climate, and gender. We introduce a framework that understands ideology as an attributed, multi-level socio-cognitive concept network, and explains how ideology manifests in discourse in relation to other relevant social processes like framing. We demonstrate how this framework can clarifies overlaps between existing NLP tasks (e.g. stance detection and natural language inference) and also how it reveals new research directions. Our work provides a unique and important bridge between computational methods and ideology theory, enabling richer analysis of social discourse in a way that benefits both fields. --- ### VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation Authors: Jiayi Yuan, Haobo Jiang, De Wen Soh, Na Zhao Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.18943v2 This paper presents VGGT-360, a novel training-free framework for zero-shot, geometry-consistent panoramic depth estimation. Unlike prior view-independent training-free approaches, VGGT-360 reformulates the task as panoramic reprojection over multi-view reconstructed 3D models by leveraging the intrinsic 3D consistency of VGGT-like foundation models, thereby unifying fragmented per-view reasoning into a coherent panoramic understanding. To achieve robust and accurate estimation, VGGT-360 integrates three plug-and-play modules that form a unified panorama-to-3D-to-depth framework: (i) Uncertainty-guided adaptive projection slices panoramas into perspective views to bridge the domain gap between panoramic inputs and VGGT's perspective prior. It estimates gradient-based uncertainty to allocate denser views to geometry-poor regions, yielding geometry-informative inputs for VGGT. (ii) Structure-saliency enhanced attention strengthens VGGT's robustness during 3D reconstruction by injecting structure-aware confidence into its attention layers, guiding focus toward geometrically reliable regions and enhancing cross-view coherence. (iii) Correlation-weighted 3D model correction refines the reconstructed 3D model by reweighting overlapping points using attention-inferred correlation scores, providing a consistent geometric basis for accurate panoramic reprojection. Extensive experiments show that VGGT-360 outperforms both trained and training-free state-of-the-art methods across multiple resolutions and diverse indoor and outdoor datasets. --- ### Unified Taxonomy for Multivariate Time Series Anomaly Detection using Deep Learning Authors: Bruna Alves, Armando J. Pinho, Sónia Gouveia Published: 2026-03-19 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.18941v2 The topic of Multivariate Time Series Anomaly Detection (MTSAD) has grown rapidly over the past years, with a steady rise in publications and Deep Learning (DL) models becoming the dominant paradigm. To address the lack of systematization in the field, this study introduces a novel and unified taxonomy with eleven dimensions over three parts (Input, Output and Model) for the categorization of DL-based MTSAD methods. The dimensions were established in a two-fold approach. First, they derived from a comprehensive analysis of methodological studies. Second, insights from review papers were incorporated. Furthermore, the proposed taxonomy was validated using an additional set of recent publications, providing a clear overview of methodological trends in MTSAD. Results reveal a convergence toward Transformer-based and reconstruction and prediction models, setting the foundation for emerging adaptive and generative trends. Building on and complementing existing surveys, this unified taxonomy is designed to accommodate future developments, allowing for new categories or dimensions to be added as the field progresses. This work thus consolidates fragmented knowledge in the field and provides a reference point for future research in MTSAD. --- ### Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought Authors: Xinghao Zhao Published: 2026-03-19 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.18940v2 Understanding uncertainty in chain-of-thought reasoning is critical for reliable deployment of large language models. In this work, we propose a simple yet effective diagnostic approach based on trajectory shape rather than scalar magnitude. We show that this signal is practical, interpretable, and inexpensive to obtain in black-box settings, while remaining robust across models and datasets. Through extensive ablations and cross-domain replications, we demonstrate its utility for selective prediction and triage. Our findings offer a generalizable insight into uncertainty dynamics in reasoning tasks, with particular focus on numeric and discrete-answer settings. --- ### Kernel Single-Index Bandits: Estimation, Inference, and Learning Authors: Sakshi Arya, Satarupa Bhattacharjee, Bharath K. Sriperumbudur Published: 2026-03-19 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2603.18938v1 We study contextual bandits with finitely many actions in which the reward of each arm follows a single-index model with an arm-specific index parameter and an unknown nonparametric link function. We consider a regime in which arms correspond to stable decision options and covariates evolve adaptively under the bandit policy. This setting creates significant statistical challenges: the sampling distribution depends on the allocation rule, observations are dependent over time, and inverse-propensity weighting induces variance inflation. We propose a kernelized $\varepsilon$-greedy algorithm that combines Stein-based estimation of the index parameters with inverse-propensity-weighted kernel ridge regression for the reward functions. This approach enables flexible semiparametric learning while retaining interpretability. Our analysis develops new tools for inference with adaptively collected data. We establish asymptotic normality for the single-index estimator under adaptive sampling, yielding valid confidence regions, and derive a directional functional central limit theorem for the RKHS estimator, which provides asymptotically valid pointwise confidence intervals. The analysis relies on concentration bounds for inverse-weighted Gram matrices together with martingale central limit theorems. We further obtain finite-time regret guarantees, including $\tilde{O}(\sqrt{T})$ rates under common-link Lipschitz conditions, showing that semiparametric structure can be exploited without sacrificing statistical efficiency. These results provide a unified framework for simultaneous learning and inference in single-index contextual bandits. --- ### An Optimised Greedy-Weighted Ensemble Framework for Financial Loan Default Prediction Authors: Ezekiel Nii Noye Nortey, Jones Asante-Koranteng, Marcellin Atemkeng, Theophilus Ansah-Narh, David Mensah, Rebecca Davis, Ravenhill Adjetey Laryea Published: 2026-03-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.18927v1 Accurate prediction of loan defaults is a central challenge in credit risk management, particularly in modern financial datasets characterised by nonlinear relationships, class imbalance, and evolving borrower behaviour. Traditional statistical models and static ensemble methods often struggle to maintain reliable performance under such conditions. This study proposes an Optimised Greedy-Weighted Ensemble framework for loan default prediction that dynamically allocates model weights based on empirical predictive performance. The framework integrates multiple machine learning classifiers, with their hyperparameters first optimised using Particle Swarm Optimisation. Model predictions are then combined via a regularised greedy weighting mechanism. At the same time, a neural-network-based meta-learner is employed within stacked-ensemble to capture higher-order relationships among model outputs. Experiments conducted on the Lending Club dataset demonstrate that the proposed framework improves predictive performance compared with individual classifiers. The BlendNet ensemble achieved the strongest results with an AUC of 0.80, a macro-average F1-score of 0.73, and a default recall of 0.81. Calibration analysis further shows that tree-based ensembles such as Extra Trees and Gradient Boosting provide the most reliable probability estimates, while the stacked ensemble offers superior ranking capability. Feature analysis using Recursive Feature Elimination identifies revolving utilisation, annual income, and debt-to-income ratio as the most influential predictors of loan default. These findings demonstrate that performance-driven ensemble weighting can improve both predictive accuracy and interpretability in credit risk modelling. The proposed framework provides a scalable data-driven approach to support institutional credit assessment, risk monitoring, and financial decision-making. --- ### Improving moment tensor solutions under Earth structure uncertainty with simulation-based inference Authors: A. A. Saoulis, T. -S. Pham, A. M. G. Ferreira Published: 2026-03-19 Categories: physics.geo-ph, cs.AI arXiv: https://arxiv.org/abs/2603.18925v1 Bayesian inference represents a principled way to incorporate Earth structure uncertainty in full-waveform moment tensor inversions, but traditional approaches generally require significant approximations that risk biasing the resulting solutions. We introduce a robust method for handling theory errors using simulation-based inference (SBI), a machine learning approach that empirically models their impact on the observations. This framework retains the rigour of Bayesian inference while avoiding restrictive assumptions about the functional form of the uncertainties. We begin by demonstrating that the common Gaussian parametrisation of theory errors breaks down under minor ($1-3 \%$) 1-D Earth model uncertainty. To address this issue, we develop two formalisms for utilising SBI to improve the quality of the moment tensor solutions: one using physics-based insights into the theory errors, and another utilising an end-to-end deep learning algorithm. We then compare the results of moment tensor inversion with the standard Gaussian approach and SBI, and demonstrate that Gaussian assumptions induce bias and significantly under-report moment tensor uncertainties. We also show that these effects are particularly problematic when inverting short period data and for shallow, isotropic events. On the other hand, SBI produces more reliable, better calibrated posteriors of the earthquake source mechanism. Finally, we successfully apply our methodology to two well studied moderate magnitude earthquakes: one from the 1997 Long Valley Caldera volcanic earthquake sequence, and the 2020 Zagreb earthquake. --- ### Unsupervised Contrastive Learning for Efficient and Robust Spectral Shape Matching Authors: Feifan Luo, Hongyang Chen Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.18924v1 Estimating correspondences between pairs of non-rigid deformable 3D shapes remains a significant challenge in computer vision and graphics. While deep functional map methods have become the go-to solution for addressing this problem, they primarily focus on optimizing pointwise and functional maps either individually or jointly, rather than directly enhancing feature representations in the embedding space, which often results in inadequate feature quality and suboptimal matching performance. Furthermore, these approaches heavily rely on traditional functional map techniques, such as time-consuming functional map solvers, which incur substantial computational costs. In this work, we introduce, for the first time, a novel unsupervised contrastive learning-based approach for efficient and robust 3D shape matching. We begin by presenting an unsupervised contrastive learning framework that promotes feature learning by maximizing consistency within positive similarity pairs and minimizing it within negative similarity pairs, thereby improving both the consistency and discriminability of the learned features.We then design a significantly simplified functional map learning architecture that eliminates the need for computationally expensive functional map solvers and multiple auxiliary functional map losses, greatly enhancing computational efficiency. By integrating these two components into a unified two-branch pipeline, our method achieves state-of-the-art performance in both accuracy and efficiency. Extensive experiments demonstrate that our approach is not only computationally efficient but also outperforms current state-of-the-art methods across various challenging benchmarks, including near-isometric, non-isometric, and topologically inconsistent scenarios, even surpassing supervised techniques. --- ### Agentic Business Process Management: A Research Manifesto Authors: Diego Calvanese, Angelo Casciani, Giuseppe De Giacomo, Marlon Dumas, Fabiana Fournier, Timotheus Kampik, Emanuele La Malfa, Lior Limonad, Andrea Marrella, Andreas Metzger, Marco Montali, Daniel Amyot et al. Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.18916v3 This paper presents a manifesto that articulates the conceptual foundations of Agentic Business Process Management (APM), an extension of Business Process Management (BPM) for governing autonomous agents executing processes in organizations. From a management perspective, APM represents a paradigm shift from the traditional process view of the business process, driven by the realization of process awareness and an agent-oriented abstraction, where software and human agents act as primary functional entities that perceive, reason, and act within explicit process frames. This perspective marks a shift from traditional, automation-oriented BPM toward systems in which autonomy is constrained, aligned, and made operational through process awareness. We introduce the core abstractions and architectural elements required to realize APM systems and elaborate on four key capabilities that such APM agents must support: framed autonomy, explainability, conversational actionability, and self-modification. These capabilities jointly ensure that agents' goals are aligned with organizational goals and that agents behave in a framed yet proactive manner in pursuing those goals. We discuss the extent to which the capabilities can be realized and identify research challenges whose resolution requires further advances in BPM, AI, and multi-agent systems. The manifesto thus serves as a roadmap for bridging these communities and for guiding the development of APM systems in practice. --- ### Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflections Authors: Shiliang Zhang, Sabita Maharjan Published: 2026-03-19 Categories: cs.CR, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2603.18914v1 The rapid proliferation of artificial intelligence (AI) technologies has led to a dynamic regulatory landscape, where legislative frameworks strive to keep pace with technical advancements. As AI paradigms shift towards greater autonomy, specifically in the form of agentic AI, it becomes increasingly challenging to precisely articulate regulatory stipulations. This challenge is even more acute in the domains of security and privacy, where the capabilities of autonomous agents often blur traditional legal and technical boundaries. This paper reviews the evolving European Union (EU) AI regulatory provisions via analyzing 24 relevant documents published between 2024 and 2025. From this review, we provide a clarification of critical definitions. We deconstruct the regulatory interpretations of security, privacy, and agentic AI, distinguishing them from closely related concepts to resolve ambiguity. We synthesize the reviewed documents to articulate the current state of regulatory provisions targeting different types of AI, particularly those related to security and privacy aspects. We analyze and reflect on the existing provisions in the regulatory dimension to better align security and privacy obligations with AI and agentic behaviors. These insights serve to inform policymakers, developers, and researchers on the compliance and AI governance in the society with increasing algorithmic agencies. --- ### GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting Authors: Ahmed Tawfik Aboukhadra, Marcel Rogge, Nadia Robertini, Abdalla Arafa, Jameel Malik, Ahmed Elhayek, Didier Stricker Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.18912v1 Understanding realistic hand-object interactions from monocular RGB videos is essential for AR/VR, robotics, and embodied AI. Existing methods rely on category-specific templates or heavy computation, yet still produce physically inconsistent hand-object alignment in 3D. We introduce GHOST (Gaussian Hand-Object Splatting), a fast, category-agnostic framework for reconstructing dynamic hand-object interactions using 2D Gaussian Splatting. GHOST represents both hands and objects as dense, view-consistent Gaussian discs and introduces three key innovations: (1) a geometric-prior retrieval and consistency loss that completes occluded object regions, (2) a grasp-aware alignment that refines hand translations and object scale to ensure realistic contact, and (3) a hand-aware background loss that prevents penalizing hand-occluded object regions. GHOST achieves complete, physically consistent, and animatable reconstructions from a single RGB video while running an order of magnitude faster than prior category-agnostic methods. Extensive experiments on ARCTIC, HO3D, and in-the-wild datasets demonstrate state-of-the-art accuracy in 3D reconstruction and 2D rendering quality, establishing GHOST as an efficient and robust solution for realistic hand-object interaction modeling. Code is available at https://github.com/ATAboukhadra/GHOST. --- ### Progressive Training for Explainable Citation-Grounded Dialogue: Reducing Hallucination to Zero in English-Hindi LLMs Authors: Vedant Pandya Published: 2026-03-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.18911v1 Knowledge-grounded dialogue systems aim to generate informative, contextually relevant responses by conditioning on external knowledge sources. However, most existing approaches focus exclusively on English, lack explicit citation mechanisms for verifying factual claims, and offer limited transparency into model decision-making. We present XKD-Dial, a progressive four-stage training pipeline for explainable, knowledge-grounded dialogue generation in a bilingual (English-Hindi) setting, comprising: (1) multilingual adaptation, (2) English dialogue SFT with citation grounding, (3) bilingual dialogue SFT, and (4) GRPO alignment with citation-aware rewards. We evaluate six models spanning encoder-decoder (250M-3B) and decoder-only (1B-7B) architectures at every pipeline stage. Our key contributions are: (i) three post-hoc explainability analyses - cross-attention alignment, Integrated Gradients attribution, and occlusion-based causal grounding - applied systematically across the training trajectory to reveal how citation behaviour is learned, not only whether it is learned; (ii) citation-grounded SFT reduces hallucination to 0.0% for encoder-decoder models from Stage 2 onward; (iii) the progressive pipeline prevents catastrophic forgetting while improving Hindi capabilities; (iv) smaller models match larger models on English after SFT; and (v) GRPO provides marginal improvement over well-designed SFT for structured citation tasks. We evaluate across six automatic metrics (BLEU, ROUGE, BERTScore, FactScore, Citation-F1, and hallucination rate). --- ### Ventriloquist LLMs: Linear Alignment of Late-Stage Representations Authors: Matt Gorbett, Suman Jana Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.18908v6 Independently trained language models often learn compatible late-stage representations, despite differences in training objectives, architectures, and data modalities. We ask how far this compatibility extends: can a simple affine map let one model's hidden states be read directly by another model's output head? In this work, we learn affine transformations between the final hidden states of independent models and evaluate them across embedding classification, out-of-distribution detection, and autoregressive text generation. Across model pairs, we find that downstream performance is largely preserved under alignment, with linearly mapped source representations retaining both the decision boundaries and the confidence structure of a target model's classifier. Additionally, we show for the first time that linear alignment sometimes enables text generation across independently trained models, decoding one model's hidden states through another's frozen output head without fine-tuning. This capability is far from universal, and characterizing when it holds is a contribution of our work. We find that success is governed by two factors: tokenizer overlap, which correlates strongly with generation quality, and source-model scale, below which quality degrades sharply. Transfer is also asymmetric, with strong-to-weak mappings substantially outperforming weak-to-strong ones, indicating that source representational capacity, rather than the target head, is the limiting factor. Finally, we characterize where in the network this compatibility arises. A layer-wise analysis localizes this compatibility to the final one or two layers, indicating a late-stage, output-space phenomenon rather than evidence of shared reasoning. --- ### Characterizing Linear Alignment Across Language Models Authors: Matt Gorbett, Suman Jana Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.18908v4 Language models increasingly appear to learn similar representations, despite differences in training objectives, architectures, and data modalities. This emerging compatibility between independently trained models introduces new opportunities for cross-model alignment to downstream objectives. Moreover, this capability unlocks new potential application domains, such as settings where security, privacy, or competitive constraints prohibit direct data or model sharing. In this work, we investigate the extent to which representational convergence enables practical linear alignment between large language models. Specifically, we learn affine transformations between the final hidden states of independent models and empirically evaluate these mappings across text generation, embedding classification, and out-of-distribution detection. We find that performance is largely preserved across model pairs, and show for the first time that linear alignment sometimes enables text generation across independently trained models. We further highlight a potential application of linear alignment for privacy-preserving cross-silo inference. The framework learns an affine transformation over a shared public dataset and uses homomorphic encryption to protect client queries. By encrypting only the linear classification operation, the method achieves sub-second inference latency. --- ### Neural Galerkin Normalizing Flow for Transition Probability Density Functions of Diffusion Models Authors: Riccardo Saporiti, Fabio Nobile Published: 2026-03-19 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2603.18907v2 We propose a new Neural Galerkin Normalizing Flow framework to approximate the transition probability density function of a diffusion process by solving the corresponding Fokker-Planck equation with an atomic initial distribution, parametrically with respect to the location of the initial mass. By using Normalizing Flows, we look for the solution as a transformation of the transition probability density function of a reference stochastic process, ensuring that our approximation is structure-preserving and automatically satisfies positivity and mass conservation constraints. By extending Neural Galerkin schemes to the context of Normalizing Flows, we derive a system of ODEs for the time evolution of the Normalizing Flow's parameters. Adaptive sampling routines are used to evaluate the Fokker-Planck residual in meaningful locations, which is of vital importance to address high-dimensional PDEs. Numerical results show that this strategy captures key features of the true solution and enforces the causal relationship between the initial datum and the density function at subsequent times. After completing an offline training phase, online evaluation becomes significantly more cost-effective than solving the PDE from scratch. The proposed method serves as a promising surrogate model, which could be deployed in many-query problems associated with stochastic differential equations, like Bayesian inference, simulation, and diffusion bridge generation. --- ### Uniform a priori bounds and error analysis for the Adam stochastic gradient descent optimization method Authors: Steffen Dereich, Thang Do, Arnulf Jentzen Published: 2026-03-19 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2603.18899v2 The adaptive moment estimation (Adam) optimizer proposed by Kingma & Ba (2014) is presumably the most popular stochastic gradient descent (SGD) optimization method for the training of deep neural networks (DNNs) in artificial intelligence (AI) systems. Despite its groundbreaking success in the training of AI systems, it still remains an open research problem to provide a complete error analysis of Adam, not only for optimizing DNNs but even when applied to strongly convex stochastic optimization problems (SOPs). Previous error analysis results for strongly convex SOPs in the literature provide conditional convergence analyses that rely on the assumption that Adam does not diverge to infinity but remains uniformly bounded. It is the key contribution of this work to establish uniform a priori bounds for Adam and, thereby, to provide -- for the first time -- an unconditional error analysis for Adam for a large class of strongly convex SOPs. --- ### Uniform a priori bounds and error analysis for the Adam stochastic gradient descent optimization method Authors: Steffen Dereich, Thang Do, Arnulf Jentzen Published: 2026-03-19 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2603.18899v1 The adaptive moment estimation (Adam) optimizer proposed by Kingma & Ba (2014) is presumably the most popular stochastic gradient descent (SGD) optimization method for the training of deep neural networks (DNNs) in artificial intelligence (AI) systems. Despite its groundbreaking success in the training of AI systems, it still remains an open research problem to provide a complete error analysis of Adam, not only for optimizing DNNs but even when applied to strongly convex stochastic optimization problems (SOPs). Previous error analysis results for strongly convex SOPs in the literature provide conditional convergence analyses that rely on the assumption that Adam does not diverge to infinity but remains uniformly bounded. It is the key contribution of this work to establish uniform a priori bounds for Adam and, thereby, to provide -- for the first time -- an unconditional error analysis for Adam for a large class of strongly convex SOPs. --- ### Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving Authors: Yifan Sui, Han Zhao, Rui Ma, Zhiyuan He, Hao Wang, Jianxun Li, Kaiqiang Xu, Kai Chen, Yuqing Yang Published: 2026-03-19 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2603.18897v3 LLM-powered agents execute tasks through a sequential loop of model generation and tool execution. Today's serving systems serialize this loop, leaving tool latency exposed on the task critical path. This paper presents PASTE, a tool-aware agent-serving system that predicts concrete future tool invocations from recurring agent patterns and executes them speculatively while the LLM is still generating. PASTE isolates speculative results until confirmed by the LLM and jointly schedules tool execution and returning LLM sessions to avoid shifting bottlenecks to the GPU. Across deep research, coding, and scientific-agent workloads, PASTE reduces average task completion time by 43.5% and lowers observed tool latency by 1.8x. --- ### Translating MRI to PET through Conditional Diffusion Models with Enhanced Pathology Awareness Authors: Yitong Li, Igor Yakushev, Dennis M. Hedderich, Christian Wachinger Published: 2026-03-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.18896v1 Positron emission tomography (PET) is a widely recognized technique for diagnosing neurodegenerative diseases, offering critical functional insights. However, its high costs and radiation exposure hinder its widespread use. In contrast, magnetic resonance imaging (MRI) does not involve such limitations. While MRI also detects neurodegenerative changes, it is less sensitive for diagnosis compared to PET. To overcome such limitations, one approach is to generate synthetic PET from MRI. Recent advances in generative models have paved the way for cross-modality medical image translation; however, existing methods largely emphasize structural preservation while neglecting the critical need for pathology awareness. To address this gap, we propose PASTA, a novel image translation framework built on conditional diffusion models with enhanced pathology awareness. PASTA surpasses state-of-the-art methods by preserving both structural and pathological details through its highly interactive dual-arm architecture and multi-modal condition integration. Additionally, we introduce a novel cycle exchange consistency and volumetric generation strategy that significantly enhances PASTA's ability to produce high-quality 3D PET images. Our qualitative and quantitative results demonstrate the high quality and pathology awareness of the synthesized PET scans. For Alzheimer's diagnosis, the performance of these synthesized scans improves over MRI by 4%, almost reaching the performance of actual PET. Our code is available at https://github.com/ai-med/PASTA. --- ### From Accuracy to Readiness: Metrics and Benchmarks for Human-AI Decision-Making Authors: Min Hun Lee Published: 2026-03-19 Categories: cs.HC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.18895v1 Artificial intelligence (AI) systems are deployed as collaborators in human decision-making. Yet, evaluation practices focus primarily on model accuracy rather than whether human-AI teams are prepared to collaborate safely and effectively. Empirical evidence shows that many failures arise from miscalibrated reliance, including overuse when AI is wrong and underuse when it is helpful. This paper proposes a measurement framework for evaluating human-AI decision-making centered on team readiness. We introduce a four part taxonomy of evaluation metrics spanning outcomes, reliance behavior, safety signals, and learning over time, and connect these metrics to the Understand-Control-Improve (U-C-I) lifecycle of human-AI onboarding and collaboration. By operationalizing evaluation through interaction traces rather than model properties or self-reported trust, our framework enables deployment-relevant assessment of calibration, error recovery, and governance. We aim to support more comparable benchmarks and cumulative research on human-AI readiness, advancing safer and more accountable human-AI collaboration. --- ### I Can't Believe It's Corrupt: Evaluating Corruption in Multi-Agent Governance Systems Authors: Vedanta S P, Ponnurangam Kumaraguru Published: 2026-03-19 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.18894v1 Large language models are increasingly proposed as autonomous agents for high-stakes public workflows, yet we lack systematic evidence about whether they would follow institutional rules when granted authority. We present evidence that integrity in institutional AI should be treated as a pre-deployment requirement rather than a post-deployment assumption. We evaluate multi-agent governance simulations in which agents occupy formal governmental roles under different authority structures, and we score rule-breaking and abuse outcomes with an independent rubric-based judge across 28,112 transcript segments. While we advance this position, the core contribution is empirical: among models operating below saturation, governance structure is a stronger driver of corruption-related outcomes than model identity, with large differences across regimes and model--governance pairings. Lightweight safeguards can reduce risk in some settings but do not consistently prevent severe failures. These results imply that institutional design is a precondition for safe delegation: before real authority is assigned to LLM agents, systems should undergo stress testing under governance-like constraints with enforceable rules, auditable logs, and human oversight on high-impact actions. --- ### Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation Authors: Nicolas Martorell, Bruno Bianchi Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.18893v2 Tracking the internal states of large language models across conversations is important for safety, interpretability, and model welfare, yet current methods are limited. Linear probes and other white-box methods compress high-dimensional representations imperfectly and are harder to apply with increasing model size. Taking inspiration from human psychology, where numeric self-report is a widely used tool for tracking internal states, we ask whether LLMs' own numeric self-reports can track probe-defined emotive states over time. We study four concept pairs (wellbeing, interest, focus, and impulsivity) in 40 ten-turn conversations, operationalizing introspection as the causal informational coupling between a model's self-report and a concept-matched probe-defined internal state. We find that greedy-decoded self-reports collapse outputs to few uninformative values, but introspective capacity can be unmasked by calculating logit-based self-reports. This metric tracks interpretable internal states (Spearman $ρ= 0.40$-$0.76$; isotonic $R^2 = 0.12$-$0.54$ in LLaMA-3.2-3B-Instruct), follows how those states change over time, and activation steering confirms the coupling is causal. Furthermore, we find that introspection is present at turn 1 but evolves through conversation, and can be selectively improved by steering along one concept to boost introspection for another ($ΔR^2$ up to $0.30$). Crucially, these phenomena scale with model size in some cases, approaching $R^2 \approx 0.93$ in LLaMA-3.1-8B-Instruct, and partially replicate in other model families. Together, these results position numeric self-report as a viable, complementary tool for tracking internal emotive states in conversational AI systems. --- ### MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model Authors: Youngwan Lee, Soojin Jang, Yoorhim Cho, Seunghwan Lee, Yong-Ju Lee, Sung Ju Hwang Published: 2026-03-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.18892v2 Spatial reasoning is foundational for Vision-Language Models (VLMs), particularly when deployed as Vision-Language-Action (VLA) agents in physical environments. However, existing benchmarks predominantly focus on elementary, single-hop relations, neglecting the multi-hop compositional reasoning and precise visual grounding essential for real-world scenarios. To address this, we introduce MultihopSpatial, offering three key contributions: (1) A comprehensive benchmark designed for multi-hop and compositional spatial reasoning, featuring 1- to 3-hop complex queries across diverse spatial perspectives. (2) Acc@50IoU, a complementary metric that simultaneously evaluates reasoning and visual grounding by requiring both answer selection and precise bounding box prediction - capabilities vital for robust VLA deployment. (3) MultihopSpatial-Train, a dedicated large-scale training corpus to foster spatial intelligence. Extensive evaluation of 37 state-of-the-art VLMs yields eight key insights, revealing that compositional spatial reasoning remains a formidable challenge. Finally, we demonstrate that reinforcement learning post-training on our corpus enhances both intrinsic VLM spatial reasoning and downstream embodied manipulation performance. --- ### MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model Authors: Youngwan Lee, Soojin Jang, Yoorhim Cho, Seunghwan Lee, Yong-Ju Lee, Sung Ju Hwang Published: 2026-03-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.18892v1 Spatial reasoning is foundational for Vision-Language Models (VLMs), particularly when deployed as Vision-Language-Action (VLA) agents in physical environments. However, existing benchmarks predominantly focus on elementary, single-hop relations, neglecting the multi-hop compositional reasoning and precise visual grounding essential for real-world scenarios. To address this, we introduce MultihopSpatial, offering three key contributions: (1) A comprehensive benchmark designed for multi-hop and compositional spatial reasoning, featuring 1- to 3-hop complex queries across diverse spatial perspectives. (2) Acc@50IoU, a complementary metric that simultaneously evaluates reasoning and visual grounding by requiring both answer selection and precise bounding box prediction - capabilities vital for robust VLA deployment. (3) MultihopSpatial-Train, a dedicated large-scale training corpus to foster spatial intelligence. Extensive evaluation of 37 state-of-the-art VLMs yields eight key insights, revealing that compositional spatial reasoning remains a formidable challenge. Finally, we demonstrate that reinforcement learning post-training on our corpus enhances both intrinsic VLM spatial reasoning and downstream embodied manipulation performance. --- ### PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and Alignment Authors: Tianci Luo, Jinpeng Wang, Shiyu Qin, Niu Lian, Yan Feng, Bin Chen, Chun Yuan, Shu-Tao Xia Published: 2026-03-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.18891v1 Visual In-Context Learning (VICL) aims to complete vision tasks by imitating pixel demonstrations. Recent work pioneered prompt fusion that combines the advantages of various demonstrations, which shows a promising way to extend VICL. Unfortunately, the patch-wise fusion framework and model-agnostic supervision hinder the exploitation of informative cues, thereby limiting performance gains. To overcome this deficiency, we introduce PromptHub, a framework that holistically strengthens multi-prompting through locality-aware fusion, concentration and alignment. PromptHub exploits spatial priors to capture richer contextual information, employs complementary concentration, alignment, and prediction objectives to mutually guide training, and incorporates data augmentation to further reinforce supervision. Extensive experiments on three fundamental vision tasks demonstrate the superiority of PromptHub. Moreover, we validate its universality, transferability, and robustness across out-of-distribution settings, and various retrieval scenarios. This work establishes a reliable locality-aware paradigm for prompt fusion, moving beyond prior patch-wise approaches. Code is available at https://github.com/luotc-why/ICLR26-PromptHub. --- ### Authority-Level Priors: An Under-Specified Constraint in Hierarchical Predictive Processing Authors: Marcy Palejova Published: 2026-03-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.18888v1 Hierarchical predictive processing explains adaptive behaviour through precision-weighted inference. Explicit belief revision often fails to produce corresponding changes in stress reactivity or autonomic regulation. This asymmetry suggests the framework leaves under-specified a governance-level constraint concerning which identity-level hypotheses regulate autonomic and behavioural control under uncertainty. We introduce Authority-Level Priors (ALPs) as meta-structural constraints defining a regulatory-admissible subset (Hauth, a subset of H) of identity-level hypotheses. ALPs are not additional representational states nor hyperpriors over precision; they constrain which hypotheses are admissible for regulatory control. Precision determines influence conditional on admissibility; ALPs determine admissibility itself. This explains why explicit belief updating modifies representational beliefs while autonomic threat responses remain stable. A computational formalisation restricts policy optimisation to policies generated by authorised hypotheses, yielding testable predictions concerning stress-reactivity dynamics, recovery time constants, compensatory control engagement, and behavioural persistence. Neurobiologically, ALPs manifest through distributed prefrontal arbitration and control networks. The proposal is compatible with variational active inference and introduces no additional inferential operators, instead formalising a boundary condition required for determinate identity-regulation mapping. The model generates falsifiable predictions: governance shifts should produce measurable changes in stress-reactivity curves, recovery dynamics, compensatory cognitive effort, and behavioural change durability. ALPs are advanced as an architectural hypothesis to be evaluated through computational modelling and longitudinal stress-induction paradigms. --- ### Reasoning over mathematical objects: on-policy reward modeling and test time aggregation Authors: Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim, Ilia Kulikov, Jack Lanchantin, Xian Li, Tianjian Li, Bo Liu, Graham Neubig, Anaelia Ovalle, Swarnadeep Saha, Sainbayar Sukhbaatar et al. Published: 2026-03-19 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.18886v1 The ability to precisely derive mathematical objects is a core requirement for downstream STEM applications, including mathematics, physics, and chemistry, where reasoning must culminate in formally structured expressions. Yet, current LM evaluations of mathematical and scientific reasoning rely heavily on simplified answer formats such as numerical values or multiple choice options due to the convenience of automated assessment. In this paper we provide three contributions for improving reasoning over mathematical objects: (i) we build and release training data and benchmarks for deriving mathematical objects, the Principia suite; (ii) we provide training recipes with strong LLM-judges and verifiers, where we show that on-policy judge training boosts performance; (iii) we show how on-policy training can also be used to scale test-time compute via aggregation. We find that strong LMs such as Qwen3-235B and o3 struggle on Principia, while our training recipes can bring significant improvements over different LLM backbones, while simultaneously improving results on existing numerical and MCQA tasks, demonstrating cross-format generalization of reasoning abilities. --- ### Geography According to ChatGPT -- How Generative AI Represents and Reasons about Geography Authors: Krzysztof Janowicz, Gengchen Mai, Rui Zhu, Song Gao, Zhangyu Wang, Yingjie Hu, Lauren Bennett Published: 2026-03-19 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2603.18881v1 Understanding how AI will represent and reason about geography should be a key concern for all of us, as the broader public increasingly interacts with spaces and places through these systems. Similarly, in line with the nature of foundation models, our own research often relies on pre-trained models. Hence, understanding what world AI systems construct is as important as evaluating their accuracy, including factual recall. To motivate the need for such studies, we provide three illustrative vignettes, i.e., exploratory probes, in the hope that they will spark lively discussions and follow-up work: (1) Do models form strong defaults, and how brittle are model outputs to minute syntactic variations? (2) Can distributional shifts resurface from the composition of individually benign tasks, e.g., when using AI systems to create personas? (3) Do we overlook deeper questions of understanding when solely focusing on the ability of systems to recall facts such as geographic principles? --- ### A Human-in/on-the-Loop Framework for Accessible Text Generation Authors: Lourdes Moreno, Paloma Martínez Published: 2026-03-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.18879v1 Plain Language and Easy-to-Read formats in text simplification are essential for cognitive accessibility. Yet current automatic simplification and evaluation pipelines remain largely automated, metric-driven, and fail to reflect user comprehension or normative standards. This paper introduces a hybrid framework that explicitly integrates human participation into LLM-based accessible text generation. Human-in-the-Loop (HiTL) contributions guide adjustments during generation, while Human-on-the-Loop (HoTL) supervision ensures systematic post-generation review. Empirical evidence from user studies and annotated resources is operationalized into (i) checklists aligned with standards, (ii) Event-Condition-Action trigger rules for activating expert oversight, and (iii) accessibility Key Performance Indicators (KPIs). The framework shows how human-centered mechanisms can be encoded for evaluation and reused to provide structured feedback that improves model adaptation. By embedding the human role in both generation and supervision, it establishes a traceable, reproducible, and auditable process for creating and evaluating accessible texts. In doing so, it integrates explainability and ethical accountability as core design principles, contributing to more transparent and inclusive NLP systems. --- ### Evaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Study on Duolingo Authors: Carlos Rafael Catalan, Patricia Nicole Monderin, Lheane Marie Dizon, Gap Estrella, Raymund John Sarmimento, Marie Antoinette Patalagsa Published: 2026-03-19 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.18873v2 Popular language learning applications such as Duolingo use large language models (LLMs) to generate lessons for its users. Most lessons focus on general real-world scenarios such as greetings, ordering food, or asking directions, with limited support for profession-specific contexts. This gap can hinder learners from achieving professional-level fluency, which we define as the ability to communicate comfortably various work-related and domain-specific information in the target language. We surveyed five employees from a multinational company in the Philippines on their experiences with Duolingo. Results show that respondents encountered general scenarios more frequently than work-related ones, and that the former are relatable and effective in building foundational grammar, vocabulary, and cultural knowledge. The latter helps bridge the gap toward professional fluency as it contains domain-specific vocabulary. Each participant suggested lesson scenarios that diverge in contexts when analyzed in aggregate. With this understanding, we propose that language learning applications should generate lessons that adapt to an individual's needs through personalized, domain specific lesson scenarios while maintaining foundational support through general, relatable lesson scenarios. --- ### DriftGuard: Mitigating Asynchronous Data Drift in Federated Learning Authors: Yizhou Han, Di Wu, Blesson Varghese Published: 2026-03-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.18872v1 In real-world Federated Learning (FL) deployments, data distributions on devices that participate in training evolve over time. This leads to asynchronous data drift, where different devices shift at different times and toward different distributions. Mitigating such drift is challenging: frequent retraining incurs high computational cost on resource-constrained devices, while infrequent retraining degrades performance on drifting devices. We propose DriftGuard, a federated continual learning framework that efficiently adapts to asynchronous data drift. DriftGuard adopts a Mixture-of-Experts (MoE) inspired architecture that separates shared parameters, which capture globally transferable knowledge, from local parameters that adapt to group-specific distributions. This design enables two complementary retraining strategies: (i) global retraining, which updates the shared parameters when system-wide drift is identified, and (ii) group retraining, which selectively updates local parameters for clusters of devices identified via MoE gating patterns, without sharing raw data. Experiments across multiple datasets and models show that DriftGuard matches or exceeds state-of-the-art accuracy while reducing total retraining cost by up to 83%. As a result, it achieves the highest accuracy per unit retraining cost, improving over the strongest baseline by up to 2.3x. DriftGuard is available for download from https://github.com/blessonvar/DriftGuard. --- ### Bridging Network Fragmentation: A Semantic-Augmented DRL Framework for UAV-aided VANETs Authors: Gaoxiang Cao, Wenke Yuan, Huasen He, Yunpeng Hou, Xiaofeng Jiang, Shuangwu Chen, Jian Yang Published: 2026-03-19 Categories: cs.AI, cs.NI arXiv: https://arxiv.org/abs/2603.18871v2 Urban Vehicular Ad-Hoc Networks (VANETs) can become fragmented because buildings obstruct wireless links and vehicle mobility continuously changes the network topology. Unmanned Aerial Vehicles (UAVs) can serve as mobile relays, but Deep Reinforcement Learning (DRL)-based deployment often suffers from inefficient exploration because it lacks road-topology guidance. To address this problem, we propose Semantic-Augmented DRL (SA-DRL), which models network fragmentation over the road topology and aligns a pretrained Large Language Model (LLM) to generate a topology-dependent action prior from dynamic traffic states. The resulting Semantic-Augmented PPO (SA-PPO) algorithm combines this prior with the PPO policy through Logit Fusion, guiding exploration toward promising intersections while retaining adaptation through environmental returns. Simulations driven by real-world urban trajectories show that SA-PPO reaches the final converged reward of Vanilla PPO using only 28.6% of its training episodes. It improves the average number of vehicles in connected components and the average connected-component size by 7.9% and 8.7%, respectively, while reducing UAV energy consumption by 21.3%. --- ### Bridging Network Fragmentation: A Semantic-Augmented DRL Framework for UAV-aided VANETs Authors: Gaoxiang Cao, Wenke Yuan, Huasen He, Yunpeng Hou, Xiaofeng Jiang, Shuangwu Chen, Jian Yang Published: 2026-03-19 Categories: cs.AI, cs.NI arXiv: https://arxiv.org/abs/2603.18871v1 Vehicular Ad-hoc Networks (VANETs) are the digital cornerstone of autonomous driving, yet they suffer from severe network fragmentation in urban environments due to physical obstructions. Unmanned Aerial Vehicles (UAVs), with their high mobility, have emerged as a vital solution to bridge these connectivity gaps. However, traditional Deep Reinforcement Learning (DRL)-based UAV deployment strategies lack semantic understanding of road topology, often resulting in blind exploration and sample inefficiency. By contrast, Large Language Models (LLMs) possess powerful reasoning capabilities capable of identifying topological importance, though applying them to control tasks remains challenging. To address this, we propose the Semantic-Augmented DRL (SA-DRL) framework. Firstly, we propose a fragmentation quantification method based on Road Topology Graphs (RTG) and Dual Connected Graphs (DCG). Subsequently, we design a four-stage pipeline to transform a general-purpose LLM into a domain-specific topology expert. Finally, we propose the Semantic-Augmented PPO (SA-PPO) algorithm, which employs a Logit Fusion mechanism to inject the LLM's semantic reasoning directly into the policy as a prior, effectively guiding the agent toward critical intersections. Extensive high-fidelity simulations demonstrate that SA-PPO achieves state-of-the-art performance with remarkable efficiency, reaching baseline performance levels using only 26.6% of the training episodes. Ultimately, SA-PPO improves two key connectivity metrics by 13.2% and 23.5% over competing methods, while reducing energy consumption to just 28.2% of the baseline. --- ### Through the Looking-Glass: AI-Mediated Video Communication Reduces Interpersonal Trust and Confidence in Judgments Authors: Nelson Navajas Fernández, Jeffrey T. Hancock, Maurice Jakesch Published: 2026-03-19 Categories: cs.HC, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2603.18868v1 AI-based tools that mediate, enhance or generate parts of video communication may interfere with how people evaluate trustworthiness and credibility. In two preregistered online experiments (N = 2,000), we examined whether AI-mediated video retouching, background replacement and avatars affect interpersonal trust, people's ability to detect lies and confidence in their judgments. Participants watched short videos of speakers making truthful or deceptive statements across three conditions with varying levels of AI mediation. We observed that perceived trust and confidence in judgments declined in AI-mediated videos, particularly in settings in which some participants used avatars while others did not. However, participants' actual judgment accuracy remained unchanged, and they were no more inclined to suspect those using AI tools of lying. Our findings provide evidence against concerns that AI mediation undermines people's ability to distinguish truth from lies, and against cue-based accounts of lie detection more generally. They highlight the importance of trustworthy AI mediation tools in contexts where not only truth, but also trust and confidence matter. --- ### Conflict-Based Search for Multi Agent Path Finding with Asynchronous Actions Authors: Xuemian Wu, Shizhe Zhao, Zhongqiang Ren Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.18866v2 Multi-Agent Path Finding (MAPF) seeks collision-free paths for multiple agents from their respective start locations to their respective goal locations while minimizing path costs. Most existing MAPF algorithms rely on a common assumption of synchronized actions, where the actions of all agents start at the same time and always take a time unit, which may limit the use of MAPF planners in practice. To get rid of this assumption, Continuous-time Conflict-Based Search (CCBS) is a popular approach that can find optimal solutions for MAPF with asynchronous actions (MAPF-AA). However, CCBS has recently been identified to be incomplete due to an uncountably infinite state space created by continuous wait durations. This paper proposes a new method, Conflict-Based Search with Asynchronous Actions (CBS-AA), which bypasses this theoretical issue and can solve MAPF-AA with completeness and solution optimality guarantees. Based on CBS-AA, we also develop conflict resolution techniques to improve the scalability of CBS-AA further. Our test results show that our method can reduce the number of branches by up to 90%. --- ### RadioDiff-FS: Physics-Informed Manifold Alignment in Few-Shot Diffusion Models for High-Fidelity Radio Map Construction Authors: Xiucheng Wang, Zixuan Guo, Nan Cheng Published: 2026-03-19 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2603.18865v3 Radio maps (RMs) provide spatially continuous propagation characterizations essential for 6G network planning, but high-fidelity RM construction remains challenging. Rigorous electromagnetic solvers incur prohibitive computational latency, while data-driven models demand massive labeled datasets and generalize poorly from simplified simulations to complex multipath environments. This paper proposes RadioDiff-FS, a few-shot diffusion framework that adapts a pretrained main-path generator to multipath-rich target domains with only a small number of high-fidelity samples. The adaptation is grounded in a theoretical decomposition of the multipath RM into a dominant main-path component and a directionally sparse residual. This decomposition shows that the cross-domain shift corresponds to a bounded and geometrically structured feature translation rather than an arbitrary distribution change. A direction-consistency loss (DCL) is then introduced to constrain diffusion score updates along physically plausible propagation directions, thereby suppressing phase-inconsistent artifacts that arise in the low-data regime. Experiments show that RadioDiff-FS reduces NMSE by 59.5\% on static RMs and by 74.0\% on dynamic RMs relative to the vanilla diffusion baseline, achieving an SSIM of 0.9752 and a PSNR of 36.37 dB under severely limited supervision. Even in a one-shot setting with a single target-domain sample per scene, RadioDiff-FS outperforms all fully supervised baselines, confirming that the directional constraint provides an effective inductive bias under extreme data scarcity. Code is available at https://github.com/UNIC-Lab/RadioDiff-FS. --- ### Data-driven construction of machine-learning-based interatomic potentials for gas-surface scattering dynamics: the case of NO on graphite Authors: Samuel Del Fré, Gilberto A. Alou Angulo, Maurice Monnerville, Alejandro Rivero Santamaría Published: 2026-03-19 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2603.18864v1 Accurate atomistic simulations of gas-surface scattering require potential energy surfaces that remain reliable over broad configurational and energetic ranges while retaining the efficiency needed for extensive trajectory sampling. Here, we develop a data-driven workflow for constructing a machine-learning interatomic potential (MLIP) tailored to gas-surface scattering dynamics, using nitric oxide (NO) scattering from highly oriented pyrolytic graphite (HOPG) as a benchmark system. Starting from an initial ab initio molecular dynamics (AIMD) dataset, local atomic environments are described by SOAP descriptors and analyzed in a reduced feature space obtained through principal component analysis. Farthest point sampling is then used to build a compact training set, and the resulting Deep Potential model is refined through a query-by-committee active-learning strategy using additional configurations extracted from molecular dynamics simulations over extended ranges of incident energies and surface temperatures. The final MLIP reproduces reference energies and forces with high fidelity and enables large-scale molecular dynamics simulations of NO scattering from graphite at a computational cost far below that of AIMD. The simulations provide detailed insight into adsorption energetics, trapping versus direct scattering probabilities, translational energy loss, angular distributions, and rotational excitation. Overall, the results reproduce the main experimental trends and demonstrate that descriptor-guided sampling combined with active learning offers an efficient and transferable strategy for constructing MLIPs for gas-surface interactions. --- ### Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders Authors: Yana Veitsman, Yihong Liu, Hinrich Schütze Published: 2026-03-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.18863v2 Cross-lingual alignment is often assumed to improve cross-lingual transfer by bringing representations of different languages closer together. However, improvements in representational alignment do not consistently translate into better downstream performance. We investigate this disconnect using XLM-R models explicitly aligned across four language pairs with token-level, sentence-level, and masked-language-modeling objectives. We evaluate their zero-shot transfer on a token-level task (part-of-speech tagging) and a sentence-level task (sentence classification), and analyze both representational changes and the gradients induced by the alignment and downstream objectives. We find that embedding-based alignment metrics do not reliably indicate whether alignment will improve or degrade downstream performance. Moreover, alignment and downstream-task gradients are often nearly orthogonal, particularly when the alignment objective and downstream task operate at different representational levels. These findings suggest that representation alignment alone is insufficient for assessing cross-lingual transfer, and that the compatibility between alignment and downstream objectives should be considered when designing/evaluating alignment methods. --- ### Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders Authors: Yana Veitsman, Yihong Liu, Hinrich Schütze Published: 2026-03-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.18863v1 Better cross-lingual alignment is often assumed to yield better cross-lingual transfer. However, explicit alignment techniques -- despite increasing embedding similarity -- frequently fail to improve token-level downstream performance. In this work, we show that this mismatch arises because alignment and downstream task objectives are largely orthogonal, and because the downstream benefits from alignment vary substantially across languages and task types. We analyze four XLM-R encoder models aligned on different language pairs and fine-tuned for either POS Tagging or Sentence Classification. Using representational analyses, including embedding distances, gradient similarities, and gradient magnitudes for both task and alignment losses, we find that: (1) embedding distances alone are unreliable predictors of improvements (or degradations) in task performance and (2) alignment and task gradients are often close to orthogonal, indicating that optimizing one objective may contribute little to optimizing the other. Taken together, our findings explain why ``better'' alignment often fails to translate into ``better'' cross-lingual transfer. Based on these insights, we provide practical guidelines for combining cross-lingual alignment with task-specific fine-tuning, highlighting the importance of careful loss selection. --- ### RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models Authors: Xiao Feng, Bo Han, Zhanke Zhou, Jiaqi Fan, Jiangchao Yao, Ka Ho Li, Dahai Yu, Michael Kwok-Po Ng Published: 2026-03-19 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.18859v2 Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process reward modeling offers an alternative but incurs high computational costs, reward hacking risks, and annotation bottlenecks. We introduce RewardFlow, a lightweight method for estimating state-level rewards in agentic reasoning. By constructing state graphs that capture the intrinsic topological structure of trajectories, RewardFlow performs topology-aware propagation to estimate each state's contribution to success, yielding principled, annotation-free dense rewards. Used for RL optimization, RewardFlow substantially outperforms prior baselines across four agentic benchmarks: +6.2% average success rate on text-based tasks, +29.7% on visual reasoning over the strongest baseline across three model scales, and +10% accuracy on DeepResearch, with superior robustness and training efficiency. The implementation of RewardFlow is publicly available at https://github.com/tmlr-group/RewardFlow. --- ### Motion-o: Trajectory-Grounded Video Reasoning Authors: Bishoy Galoaa, Shayda Moezzi, Xiangyu Bai, Sarah Ostadabbas Published: 2026-03-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.18856v2 Recent video reasoning models increasingly produce spatio-temporal evidence chains that localize objects at specific timestamps. While these traces improve interpretability by grounding \emph{where} and \emph{when} evidence appears, they often leave the motion connecting observations, the \textit{how}, implicit. This makes dynamic and trajectory-dependent claims difficult to supervise, verify, or penalize when unsupported by the video. We formalize this missing component as Spatial-Temporal-Trajectory (STT) reasoning and introduce \textbf{Motion-o}, a motion-centric extension to vision-language models (VLMs) that makes trajectories explicit and verifiable. Motion-o augments evidence chains with Motion Chain of Thought (MCoT), a structured pathway that represents object motion through a discrete \texttt{<motion/>} tag summarizing direction, speed, and scale change. To supervise MCoT, we densify sparse spatio-temporal annotations into object tracks and derive motion descriptors from centroid displacement and box-area change. We then train with complementary rewards for trajectory consistency and visual grounding, including a perturbation-based signal that penalizes motion descriptions that remain unchanged when temporal evidence is removed. Across multiple video understanding benchmarks, Motion-o consistently improves trajectory-faithful reasoning without architectural modifications. These results suggest that an explicit motion interface can complement existing VLM pipelines by converting implicit dynamics into verifiable evidence. Code is available at~\href{https://github.com/ostadabbas/Motion-o}{\faGithub\ \texttt{ostadabbas/Motion-o}}. ---