# Research Papers — 2026-04 · bundle page 182 of 233 > Full-text markdown of papers #9051–9100 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/182 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/181.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/183.md) ### FMI@SU ToxHabits: Evaluating LLMs Performance on Toxic Habit Extraction in Spanish Clinical Texts Authors: Sylvia Vassileva, Ivan Koychev, Svetla Boytcheva Published: 2026-04-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.06403v1 The paper presents an approach for the recognition of toxic habits named entities in Spanish clinical texts. The approach was developed for the ToxHabits Shared Task. Our team participated in subtask 1, which aims to detect substance use and abuse mentions in clinical case reports and classify them in four categories (Tobacco, Alcohol, Cannabis, and Drug). We explored various methods of utilizing LLMs for the task, including zero-shot, few-shot, and prompt optimization, and found that GPT-4.1's few-shot prompting performed the best in our experiments. Our method achieved an F1 score of 0.65 on the test set, demonstrating a promising result for recognizing named entities in languages other than English. --- ### ProofSketcher: Hybrid LLM + Lightweight Proof Checker for Reliable Math/Logic Reasoning Authors: Kranthi Kommuru, Kunal Khanvilkar, Gaurav Parekh Published: 2026-04-07 Categories: cs.AI, cs.CE, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.06401v1 The large language models (LLMs) might produce a persuasive argument within mathematical and logical fields, although such argument often includes some minor missteps, including the entire omission of side conditions, invalid inference patterns, or appeals to a lemma that cannot be derived logically out of the context being discussed. These omissions are infamously hard to notice solely out of the text, as even the misconstrued construction still may seem mostly accurate. Conversely, interactive theorem provers like Lean and Coq have rigorous reliability by ensuring that syntactic and semantic statements only accept statements that can pass all the syntactic and semantic steps in the program which is a small trusted kernel of the language type-checks with. Despite the fact that this technique provides strong guarantees, it comes at quite a heavy price: the evidence must be completely formalized, and the evidence user or a auxiliary search program must provide an avalanche of low-level information. This paper presents a hybrid pipeline where an LLM generates a typed proof sketch in a compact DSL and a lightweight trusted kernel expands the sketch into explicit proof obligations. --- ### Calibration of a neural network ocean closure for improved mean state and variability Authors: Pavel Perezhogin, Alistair Adcroft, Laure Zanna Published: 2026-04-07 Categories: physics.ao-ph, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2604.06398v2 Global ocean models exhibit biases in the mean state and variability, particularly at coarse resolution, where mesoscale eddies are unresolved. To address these biases, parameterization coefficients are typically tuned ad hoc. Here, we formulate parameter tuning as a calibration problem using Ensemble Kalman Inversion (EKI). We optimize parameters of a neural network parameterization of mesoscale eddies in two idealized ocean models at coarse resolution. The calibrated parameterization reduces errors by factors of 1.7-3.3 in the time-averaged fluid interfaces and their variability compared to the unparameterized model, depending on the metric and configuration. The EKI method is robust to noise in time-averaged statistics arising from chaotic ocean dynamics. Furthermore, we propose an efficient calibration protocol that bypasses integration to statistical equilibrium by carefully choosing an initial condition. These results demonstrate that systematic calibration can substantially improve coarse-resolution ocean simulations and provide a practical pathway for reducing biases in global ocean models. --- ### Bridging Theory and Practice in Crafting Robust Spiking Reservoirs Authors: Ruggero Freddi, Nicolas Seseri, Diana Nigrisoli, Alessio Basti Published: 2026-04-07 Categories: cs.LG, q-bio.NC, stat.ML arXiv: https://arxiv.org/abs/2604.06395v1 Spiking reservoir computing provides an energy-efficient approach to temporal processing, but reliably tuning reservoirs to operate at the edge-of-chaos is challenging due to experimental uncertainty. This work bridges abstract notions of criticality and practical stability by introducing and exploiting the robustness interval, an operational measure of the hyperparameter range over which a reservoir maintains performance above task-dependent thresholds. Through systematic evaluations of Leaky Integrate-and-Fire (LIF) architectures on both static (MNIST) and temporal (synthetic Ball Trajectories) tasks, we identify consistent monotonic trends in the robustness interval across a broad spectrum of network configurations: the robustness-interval width decreases with presynaptic connection density $β$ (i.e., directly with sparsity) and directly with the firing threshold $θ$. We further identify specific $(β, θ)$ pairs that preserve the analytical mean-field critical point $w_{\text{crit}}$, revealing iso-performance manifolds in the hyperparameter space. Control experiments on Erdős-Rényi graphs show the phenomena persist beyond small-world topologies. Finally, our results show that $w_{\text{crit}}$ consistently falls within empirical high-performance regions, validating $w_{\text{crit}}$ as a robust starting coordinate for parameter search and fine-tuning. To ensure reproducibility, the full Python code is publicly available. --- ### ART: Attention Replacement Technique to Improve Factuality in LLMs Authors: Ziqin Luo, Yihao Quan, Xiaofeng Zhang, Xiaosong Yuan, Chen Shen Published: 2026-04-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.06393v1 Hallucination in large language models (LLMs) continues to be a significant issue, particularly in tasks like question answering, where models often generate plausible yet incorrect or irrelevant information. Although various methods have been proposed to mitigate hallucinations, the relationship between attention patterns and hallucinations has not been fully explored. In this paper, we analyze the distribution of attention scores across each layer and attention head of LLMs, revealing a common and intriguing phenomenon: shallow layers of LLMs primarily rely on uniform attention patterns, where the model distributes its attention evenly across the entire sequence. This uniform attention pattern can lead to hallucinations, as the model fails to focus on the most relevant information. To mitigate this issue, we propose a training-free method called Attention Replacement Technique (ART), which replaces these uniform attention patterns in the shallow layers with local attention patterns. This change directs the model to focus more on the relevant contexts, thus reducing hallucinations. Through extensive experiments, ART demonstrates significant reductions in hallucinations across multiple LLM architectures, proving its effectiveness and generalizability without requiring fine-tuning or additional training data. --- ### Qualixar OS: A Universal Operating System for AI Agent Orchestration Authors: Varun Pratap Bhardwaj Published: 2026-04-07 Categories: cs.AI, cs.MA, cs.SE arXiv: https://arxiv.org/abs/2604.06392v1 We present Qualixar OS, the first application-layer operating system for universal AI agent orchestration. Unlike kernel-level approaches (AIOS) or single-framework tools (AutoGen, CrewAI), Qualixar OS provides a complete runtime for heterogeneous multi-agent systems spanning 10 LLM providers, 8+ agent frameworks, and 7 transports. We contribute: (1) execution semantics for 12 multi-agent topologies including grid, forest, mesh, and maker patterns; (2) Forge, an LLM-driven team design engine with historical strategy memory; (3) three-layer model routing combining Q-learning, five strategies, and Bayesian POMDP with dynamic multi-provider discovery; (4) a consensus-based judge pipeline with Goodhart detection, JSD drift monitoring, and alignment trilemma navigation; (5) four-layer content attribution with HMAC signing and steganographic watermarks; (6) universal compatibility via the Claw Bridge supporting MCP and A2A protocols with a 25-command Universal Command Protocol; (7) a 24-tab production dashboard with visual workflow builder and skill marketplace. Qualixar OS is validated by 2,821 test cases across 217 event types and 8 quality modules. On a custom 20-task evaluation suite, the system achieves 100% accuracy at a mean cost of $0.000039 per task. Source-available under the Elastic License 2.0. --- ### Toward a universal foundation model for graph-structured data Authors: Sakib Mostafa, Lei Xing, Md. Tauhidul Islam Published: 2026-04-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.06391v1 Graphs are a central representation in biomedical research, capturing molecular interaction networks, gene regulatory circuits, cell--cell communication maps, and knowledge graphs. Despite their importance, currently there is not a broadly reusable foundation model available for graph analysis comparable to those that have transformed language and vision. Existing graph neural networks are typically trained on a single dataset and learn representations specific only to that graph's node features, topology, and label space, limiting their ability to transfer across domains. This lack of generalization is particularly problematic in biology and medicine, where networks vary substantially across cohorts, assays, and institutions. Here we introduce a graph foundation model designed to learn transferable structural representations that are not specific to specific node identities or feature schemes. Our approach leverages feature-agnostic graph properties, including degree statistics, centrality measures, community structure indicators, and diffusion-based signatures, and encodes them as structural prompts. These prompts are integrated with a message-passing backbone to embed diverse graphs into a shared representation space. The model is pretrained once on heterogeneous graphs and subsequently reused on unseen datasets with minimal adaptation. Across multiple benchmarks, our pretrained model matches or exceeds strong supervised baselines while demonstrating superior zero-shot and few-shot generalization on held-out graphs. On the SagePPI benchmark, supervised fine-tuning of the pretrained backbone achieves a mean ROC-AUC of 95.5%, a gain of 21.8% over the best supervised message-passing baseline. The proposed technique thus provides a unique approach toward reusable, foundation-scale models for graph-structured data in biomedical and network science applications. --- ### MorphDistill: Distilling Unified Morphological Knowledge from Pathology Foundation Models for Colorectal Cancer Survival Prediction Authors: Hikmat Khan, Usama Sajjad, Metin N. Gurcan, Anil Parwani, Wendy L. Frankel, Wei Chen, Muhammad Khalid Khan Niazi Published: 2026-04-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.06390v2 Background: Colorectal cancer (CRC) remains a leading cause of cancer-related mortality worldwide. Accurate survival prediction is essential for treatment stratification, yet existing pathology foundation models often overlook organ-specific features critical for CRC prognostication. Methods: We propose MorphDistill, a two-stage framework that distills complementary knowledge from multiple pathology foundation models into a compact CRC-specific encoder. In Stage I, a student encoder is trained using dimension-agnostic multi-teacher relational distillation with supervised contrastive regularization on large-scale colorectal datasets. This preserves inter-sample relationships from ten foundation models without explicit feature alignment. In Stage II, the encoder extracts patch-level features from whole-slide images, which are aggregated via attention-based multiple instance learning to predict five-year survival. Results: On the Alliance/CALGB 89803 cohort (n=424, stage III CRC), MorphDistill achieves an AUC of 0.68 (SD 0.08), an approximately 8% relative improvement over the strongest baseline (AUC 0.63). It also attains a C-index of 0.661 and a hazard ratio of 2.52 (95% CI: 1.73-3.65), outperforming all baselines. On an external TCGA cohort (n=562), it achieves a C-index of 0.628, demonstrating strong generalization across datasets and robustness across clinical subgroups. Conclusion: MorphDistill enables task-specific representation learning by integrating knowledge from multiple foundation models into a unified encoder. This approach provides an efficient strategy for prognostic modeling in computational pathology, with potential for broader oncology applications. Further validation across additional cohorts and disease stages is warranted. --- ### SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratio Authors: Satwik Pandey, Suresh Raghu, Shashwat Pandey Published: 2026-04-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.06389v1 Uncertainty estimation for reasoning language models remains difficult to deploy in practice: sampling-based methods are computationally expensive, while common single-pass proxies such as verbalized confidence or trace length are often inconsistent across models. This problem is compounded for proprietary reasoning APIs that expose neither logits nor intermediate token probabilities, leaving practitioners with no reliable uncertainty signal at inference time. We propose SELFDOUBT, a single-pass uncertainty framework that resolves this impasse by extracting behavioral signals directly from the reasoning trace itself. Our key signal, the Hedge-to-Verify Ratio (HVR), detects whether a reasoning trace contains uncertainty markers and, if so, whether they are offset by explicit selfchecking behavior. Unlike methods that require multiple sampled traces or model internals, SELFDOUBT operates on a single observed reasoning trajectory, making it suitable for latency- and cost-constrained deployment over any proprietary API. We evaluate SELFDOUBT across seven models and three multi-step reasoning benchmarks (BBH, GPQA-Diamond, and MMLU-Pro). Most notably, traces containing no hedging markers are correct 96% of the time, revealing an emergent high-precision confidence gate at zero additional cost. For the remaining cases, the full SELFDOUBT score significantly outperforms sampling-based semantic entropy at 10x lower inference cost. A deployment cascade combining both stages attains 90% accuracy at 71% coverage without any task-specific labels. These results establish SELFDOUBT as a scalable, production-ready foundation for uncertainty estimation over proprietary reasoning models. --- ### Uncertainty Estimation for Deep Reconstruction in Actuatic Disaster Scenarios with Autonomous Vehicles Authors: Samuel Yanes Luis, Alejandro Casado Pérez, Alejandro Mendoza Barrionuevo, Dame Seck Diop, Sergio Toral Marín, Daniel Gutiérrez Reina Published: 2026-04-07 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.06387v1 Accurate reconstruction of environmental scalar fields from sparse onboard observations is essential for autonomous vehicles engaged in aquatic monitoring. Beyond point estimates, principled uncertainty quantification is critical for active sensing strategies such as Informative Path Planning, where epistemic uncertainty drives data collection decisions. This paper compares Gaussian Processes, Monte Carlo Dropout, Deep Ensembles, and Evidential Deep Learning for simultaneous scalar field reconstruction and uncertainty decomposition under three perceptual models representative of real sensor modalities. Results show that Evidential Deep Learning achieves the best reconstruction accuracy and uncertainty calibration across all sensor configurations at the lowest inference cost, while Gaussian Processes are fundamentally limited by their stationary kernel assumption and become intractable as observation density grows. These findings support Evidential Deep Learning as the preferred method for uncertainty-aware field reconstruction in real-time autonomous vehicle deployments. --- ### Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning Authors: Navan Preet Singh, Xiaokun Wang, Anurag Garikipati, Madalina Ciobanu, Qingqing Mao, Ritankar Das Published: 2026-04-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.06385v1 We present an innovative multi-stage optimization strategy combining reinforcement learning (RL) and supervised fine-tuning (SFT) to enhance the pedagogical knowledge of large language models (LLMs), as illustrated by EduQwen 32B-RL1, EduQwen 32B-SFT, and an optional third-stage model EduQwen 32B-SFT-RL2: (1) RL optimization that implements progressive difficulty training, focuses on challenging examples, and employs extended reasoning rollouts; (2) a subsequent SFT phase that leverages the RL-trained model to synthesize high-quality training data with difficulty-weighted sampling; and (3) an optional second round of RL optimization. EduQwen 32B-RL1, EduQwen 32B-SFT, and EduQwen 32B-SFT-RL2 are an application-driven family of open-source pedagogical LLMs built on a dense Qwen3-32B backbone. These models remarkably achieve high enough accuracy on the Cross-Domain Pedagogical Knowledge (CDPK) Benchmark to establish new state-of-the-art (SOTA) results across the interactive Pedagogy Benchmark Leaderboard and surpass significantly larger proprietary systems such as the previous benchmark leader Gemini-3 Pro. These dense 32-billion-parameter models demonstrate that domain-specialized optimization can transform mid-sized open-source LLMs into true pedagogical domain experts that outperform much larger general-purpose systems, while preserving the transparency, customizability, and cost-efficiency required for responsible educational AI deployment. --- ### Revisiting Fairness Impossibility with Endogenous Behavior Authors: Elizabeth Maggie Penn, John W. Patty Published: 2026-04-07 Categories: cs.GT, cs.LG, econ.TH arXiv: https://arxiv.org/abs/2604.06378v1 In many real-world settings, institutions can and do adjust the consequences attached to algorithmic classification decisions, such as the size of fines, sentence lengths, or benefit levels. We refer to these consequences as the stakes associated with classification. These stakes can give rise to behavioral responses to classification, as people adjust their actions in anticipation of how they will be classified. Much of the algorithmic fairness literature evaluates classification outcomes while holding behavior fixed, treating behavioral differences across groups as exogenous features of the environment. Under this assumption, the stakes of classification play no role in shaping outcomes. We revisit classic impossibility results in algorithmic fairness in a setting where people respond strategically to classification. We show that, in this environment, the well-known incompatibility between error-rate balance and predictive parity disappears, but only by potentially introducing a qualitatively different form of unequal treatment. Concretely, we construct a two-stage design in which a classifier first standardizes its statistical performance across groups, and then adjusts stakes so as to induce comparable patterns of behavior. This requires treating groups differently in the consequences attached to identical classification decisions. Our results demonstrate that fairness in strategic settings cannot be assessed solely by how algorithms map data into decisions. Rather, our analysis treats the human consequences of classification as primary design variables, introduces normative criteria governing their use, and shows that their interaction with statistical fairness criteria generates qualitatively new tradeoffs. Our aim is to make these tradeoffs precise and explicit. --- ### The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment Authors: Rishab Balasubramanian, Pin-Jie Lin, Rituraj Sharma, Anjie Fang, Fardin Abdi, Viktor Rozgic, Zheng Du, Mohit Bansal, Tu Vu Published: 2026-04-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.06377v3 We investigate whether post-trained capabilities can be transferred across models without retraining, with a focus on transfer across different model scales. We propose the Master Key Hypothesis, which states that model capabilities correspond to directions in a low-dimensional latent subspace that induce specific behaviors and are transferable across models through linear alignment. Based on this hypothesis, we introduce UNLOCK, a training-free and label-free framework that extracts a capability direction by contrasting activations between capability-present and capability-absent Source variants, aligns it with a Target model through a low-rank linear transformation, and applies it at inference time to elicit the behavior. Experiments on reasoning behaviors, including Chain-of-Thought (CoT) and mathematical reasoning, demonstrate substantial improvements across model scales without training. For example, transferring CoT reasoning from Qwen1.5-14B to Qwen1.5-7B yields an accuracy gain of 12.1% on MATH, and transferring a mathematical reasoning direction from Qwen3-4B-Base to Qwen3-14B-Base improves AGIEval Math accuracy from 61.1% to 71.3%, surpassing the 67.8% achieved by the 14B post-trained model. Our analysis shows that the success of transfer depends on the capabilities learned during pre-training, and that our intervention amplifies latent capabilities by sharpening the output distribution toward successful reasoning trajectories. --- ### MTA-Agent: An Open Recipe for Multimodal Deep Search Agents Authors: Xiangyu Peng, Can Qin, An Yan, Xinyi Yang, Zeyuan Chen, Ran Xu, Chien-Sheng Wu Published: 2026-04-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.06376v1 Multimodal large language models (MLLMs) have demonstrated strong capabilities in visual understanding, yet they remain limited in complex, multi-step reasoning that requires deep searching and integrating visual evidence with external knowledge. In this work, we address this challenge by constructing high-quality, verified multi-hop vision-language training data for multimodal deep-search agents. We propose a Multi-hop Tool-Augmented Agent for Evidence-based QA Synthesis (MTA-Agent), which automatically selects tools and their parameters to retrieve and validate evidence from both visual and textual sources and generates structured multi-hop question-answer trajectories. Starting from diverse VQA seed datasets, our pipeline produces a large-scale training dataset, MTA-Vision-DeepSearch, containing 21K high-quality multi-hop examples. The data is filtered through a multi-stage verification process to ensure factual consistency and answer uniqueness. Using MTA-Vision-DeepSearch, a 32B open-source multimodal search agent achieves state-of-the-art performance, reaching an average of 54.63\% across six challenging benchmarks, outperforming GPT-5 (51.86\%), Gemini-2.5-Pro (50.98\%), and Gemini-3-Pro (54.46\%) under the same tool settings. We further show that training on our data improves both reasoning depth and tool-use behavior, increasing the average number of steps from 2.27 to 4.28, and leading to more systematic and persistent search strategies. Additionally, we demonstrate that training can be performed without real-time tool calls by replaying cached interactions, significantly reducing training cost. Importantly, we present MTA-Agent as a fully open recipe for multimodal deep search: we release the entire dataset, training trajectories, and implementation details to enable reproducibility and future research on open multimodal search agents. --- ### SymptomWise: A Deterministic Reasoning Layer for Reliable and Efficient AI Systems Authors: Isaac Henry, Avery Byrne, Christopher Giza, Ron Henry, Shahram Yazdani Published: 2026-04-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.06375v1 AI-driven symptom analysis systems face persistent challenges in reliability, interpretability, and hallucination. End-to-end generative approaches often lack traceability and may produce unsupported or inconsistent diagnostic outputs in safety-critical settings. We present SymptomWise, a framework that separates language understanding from diagnostic reasoning. The system combines expert-curated medical knowledge, deterministic codex-driven inference, and constrained use of large language models. Free-text input is mapped to validated symptom representations, then evaluated by a deterministic reasoning module operating over a finite hypothesis space to produce a ranked differential diagnosis. Language models are used only for symptom extraction and optional explanation, not for diagnostic inference. This architecture improves traceability, reduces unsupported conclusions, and enables modular evaluation of system components. Preliminary evaluation on 42 expert-authored challenging pediatric neurology cases shows meaningful overlap with clinician consensus, with the correct diagnosis appearing in the top five differentials in 88% of cases. Beyond medicine, the framework generalizes to other abductive reasoning domains and may serve as a deterministic structuring and routing layer for foundation models, improving precision and potentially reducing unnecessary computational overhead in bounded tasks. --- ### The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models Authors: Michael Rizvi-Martel, Guillaume Rabusseau, Marius Mosbach Published: 2026-04-07 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.06374v2 Latent reasoning via continuous chain-of-thoughts (Latent CoT) has emerged as a promising alternative to discrete CoT reasoning. Operating in continuous space increases expressivity and has been hypothesized to enable superposition: the ability to maintain multiple candidate solutions simultaneously within a single representation. Despite theoretical arguments, it remains unclear whether language models actually leverage superposition when reasoning using latent CoTs. We investigate this question across three regimes: a training-free regime that constructs latent thoughts as convex combinations of token embeddings, a fine-tuned regime where a base model is adapted to produce latent thoughts, and a from-scratch regime where a model is trained entirely with latent thoughts to solve a given task. Using Logit Lens and entity-level probing to analyze internal representations, we find that only models trained from scratch exhibit signs of using superposition. In the training-free and fine-tuned regimes, we find that the superposition either collapses or is not used at all, with models discovering shortcut solutions instead. We argue that this is due to two complementary phenomena: i) pretraining on natural language data biases models to commit to a token in the last layers ii) capacity has a huge effect on which solutions a model favors. Together, our results offer a unified explanation for when and why superposition arises in continuous chain-of-thought reasoning, and identify the conditions under which it collapses. --- ### Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects Authors: Syed Mohammad Kashif, Ruiyin Li, Peng Liang, Amjed Tahir, Qiong Feng, Zengyang Li, Mojtaba Shahin Published: 2026-04-07 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.06373v1 New generation of AI coding tools, including AI-powered IDEs equipped with agentic capabilities, can generate code within the context of the project. These AI IDEs are increasingly perceived as capable of producing project-level code at scale. However, there is limited empirical evidence on the extent to which they can generate large-scale software systems and what design issues such systems may exhibit. To address this gap, we conducted a study to explore the capability of Cursor in generating large-scale projects and to evaluate the design quality of projects generated by Cursor. First, we propose a Feature-Driven Human-In-The-Loop (FD-HITL) framework that systematically guides project generation from curated project descriptions. We generated 10 projects using Cursor with the FD-HITL framework across three application domains and multiple technologies. We assessed the functional correctness of these projects through manual evaluation, obtaining an average functional correctness score of 91%. Next, we analyzed the generated projects using two static analysis tools, CodeScene and SonarQube, to detect design issues. We identified 1,305 design issues categorized into 9 categories by CodeScene and 3,193 issues in 11 categories by SonarQube. Our findings show that (1) when used with the FD-HITL framework, Cursor can generate functional large-scale projects averaging 16,965 LoC and 114 files; (2) the generated projects nevertheless contain design issues that may pose long-term maintainability and evolvability risks, requiring careful review by experienced developers; (3) the most prevalent issues include Code Duplication, high Code Complexity, Large Methods, Framework Best-Practice Violations, Exception-Handling Issues and Accessibility Issues; (4) these design issues violate design principles such as SRP, SoC, and DRY. The replication package is at https://github.com/Kashifraz/DIinAGP --- ### ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache Authors: Shao Wang, Rui Ren, Lin Gui Published: 2026-04-07 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2604.06370v1 The serving paradigm of large language models (LLMs) is rapidly shifting towards complex multi-agent workflows where specialized agents collaborate over massive shared contexts. While Low-Rank Adaptation (LoRA) enables the efficient co-hosting of these specialized agents on a single base model, it introduces a critical memory footprint bottleneck during serving. Specifically, unique LoRA activations cause Key-Value (KV) cache divergence across agents, rendering traditional prefix caching ineffective for shared contexts. This forces redundant KV cache maintenance, rapidly saturating GPU capacity and degrading throughput. To address this challenge, we introduce ForkKV, a serving system for multi-LoRA agent workflows centered around a novel memory management paradigm in OS: fork with copy-on-write (CoW). By exploiting the structural properties of LoRA, ForkKV physically decouples the KV cache into a massive shared component (analogous to the parent process's memory pages) and lightweight agent-specific components (the child process's pages). To support this mechanism, we propose a DualRadixTree architecture that allows newly forked agents to inherit the massive shared cache and apply CoW semantics for their lightweight unique cache. Furthermore, to guarantee efficient execution, we design ResidualAttention, a specialized kernel that reconstructs the disaggregated KV cache directly within on-chip SRAM. Comprehensive evaluations across diverse language models and practical datasets of different tasks demonstrate that ForkKV achieves up to 3.0x the throughput of state-of-the-art multi-LoRA serving systems with a negligible impact on generation quality. --- ### WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks Authors: Guruprasad Viswanathan Ramesh, Asmit Nayak, Basieem Siddique, Kassem Fawaz Published: 2026-04-07 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.06367v2 Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performance~(e.g., WebArena) or safety against malicious actions~(e.g., SafeArena), no existing framework assesses an agent's ability to successfully execute user-facing website security and privacy tasks, such as managing cookie preferences, configuring privacy-sensitive account settings, or revoking inactive sessions. To address this gap, we introduce WebSP-Eval, an evaluation framework for measuring web agent performance on website security and privacy tasks. WebSP-Eval comprises 1) a manually crafted task dataset of 200 task instances across 28 websites; 2) a robust agentic system supporting account and initial state management across runs using a custom Google Chrome extension; and 3) an automated evaluator. We evaluate a total of 8 web agent instantiations using state-of-the-art multimodal large language models, conducting a fine-grained analysis across websites, task categories, and UI elements. Our evaluation reveals that current models suffer from limited autonomous exploration capabilities to reliably solve website security and privacy tasks, and struggle with specific task categories and websites. Crucially, we identify stateful UI elements are a primary reason for agent failure, with toggles causing more than 45% task failure across many models. --- ### Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networks Authors: Guillaume Corlouer, Avi Semler, Alexander Strang, Alexander Gietelink Oldenziel Published: 2026-04-07 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.06366v1 Deep linear networks (DLNs) are used as an analytically tractable model of the training dynamics of deep neural networks. While gradient descent in DLNs is known to exhibit saddle-to-saddle dynamics, the impact of stochastic gradient descent (SGD) noise on this regime remains poorly understood. We investigate the dynamics of SGD during training of DLNs in the saddle-to-saddle regime. We model the training dynamics as stochastic Langevin dynamics with anisotropic, state-dependent noise. Under the assumption of aligned and balanced weights, we derive an exact decomposition of the dynamics into a system of one-dimensional per-mode stochastic differential equations. This establishes that the maximal diffusion along a mode precedes the corresponding feature being completely learned. We also derive the stationary distribution of SGD for each mode: in the absence of label noise, its marginal distribution along specific features coincides with the stationary distribution of gradient flow, while in the presence of label noise it approximates a Boltzmann distribution. Finally, we confirm experimentally that the theoretical results hold qualitatively even without aligned or balanced weights. These results establish that SGD noise encodes information about the progression of feature learning but does not fundamentally alter the saddle-to-saddle dynamics. --- ### A Severity-Based Curriculum Learning Strategy for Arabic Medical Text Generation Authors: Ahmed Alansary, Molham Mohamed, Ali Hamdi Published: 2026-04-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.06365v1 Arabic medical text generation is increasingly needed to help users interpret symptoms and access general health guidance in their native language. Nevertheless, many existing methods assume uniform importance across training samples, overlooking differences in clinical severity. This simplification can hinder the model's ability to properly capture complex or high-risk cases. To overcome this issue, this work introduces a Severity-based Curriculum Learning Strategy for Arabic Medical Text Generation, where the training process is structured to move gradually from less severe to more critical medical conditions. The approach divides the dataset into ordered stages based on severity and incrementally exposes the model to more challenging cases during fine-tuning, allowing it to first learn basic medical patterns before addressing more complex scenarios. The proposed method is evaluated on a subset of the Medical Arabic Question Answering (MAQA) dataset, which includes Arabic medical questions describing symptoms alongside corresponding responses. In addition, the dataset is annotated with three severity levels (Mild, Moderate, and Critical) using a rule-based method developed in this study. The results demonstrate that incorporating severity-aware curriculum learning leads to consistent performance improvements across all tested models, with gains of around +4% to +7% over baseline models and +3% to +6% compared with conventional fine-tuning approaches. --- ### GS-Surrogate: Deformable Gaussian Splatting for Parameter Space Exploration of Ensemble Simulations Authors: Ziwei Li, Rumali Perera, Angus Forbes, Ken Moreland, Dave Pugmire, Scott Klasky, Wei-Lun Chao, Han-Wei Shen Published: 2026-04-07 Categories: cs.GR, cs.AI arXiv: https://arxiv.org/abs/2604.06358v1 Exploring ensemble simulations is increasingly important across many scientific domains. However, supporting flexible post-hoc exploration remains challenging due to the trade-off between storing the expensive raw data and flexibly adjusting visualization settings. Existing visualization surrogate models have improved this workflow, but they either operate in image space without an explicit 3D representation or rely on neural radiance fields that are computationally expensive for interactive exploration and encode all parameter-driven variations within a single implicit field. In this work, we introduce GS-Surrogate, a deformable Gaussian Splatting-based visualization surrogate for parameter-space exploration. Our method first constructs a canonical Gaussian field as a base 3D representation and adapts it through sequential parameter-conditioned deformations. By separating simulation-related variations from visualization-specific changes, this explicit formulation enables efficient and controllable adaptation to different visualization tasks, such as isosurface extraction and transfer function editing. We evaluate our framework on a range of simulation datasets, demonstrating that GS-Surrogate enables real-time and flexible exploration across both simulation and visualization parameter spaces. --- ### In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads Authors: Charlotte Pouw, Hosein Mohebbi, Afra Alishahi, Willem Zuidema Published: 2026-04-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.06356v1 In-Context Learning (ICL) has been extensively studied in text-only Language Models, but remains largely unexplored in the speech domain. Here, we investigate how linguistic and acoustic features affect ICL in Speech Language Models. We focus on the Text-to-Speech (TTS) task, which allows us to analyze ICL from two angles: (1) how accurately the model infers the task from the demonstrations (i.e., generating the correct spoken content), and (2) to what extent the model mimics the acoustic characteristics of the demonstration speech in its output. We find that speaking rate strongly affects ICL performance and is also mimicked in the output, whereas pitch range and intensity have little impact on performance and are not consistently reproduced. Finally, we investigate the role of induction heads in speech-based ICL and show that these heads play a causal role: ablating the top-k induction heads completely removes the model's ICL ability, mirroring findings from text-based ICL. --- ### DietDelta: A Vision-Language Approach for Dietary Assessment via Before-and-After Images Authors: Gautham Vinod, Siddeshwar Raghavan, Bruce Coburn, Fengqing Zhu Published: 2026-04-07 Categories: cs.CV, cs.AI, cs.MM, eess.IV arXiv: https://arxiv.org/abs/2604.06352v1 Accurate dietary assessment is critical for precision nutrition, yet most image-based methods rely on a single pre-consumption image and provide only coarse, meal-level estimates. These approaches cannot determine what was actually consumed and often require restrictive inputs such as depth sensing, multi-view imagery, or explicit segmentation. In this paper, we propose a simple vision-language framework for food-item-level nutritional analysis using paired before-and-after eating images. Instead of relying on rigid segmentation masks, our method leverages natural language prompts to localize specific food items and estimate their weight directly from a single RGB image. We further estimate food consumption by predicting weight differences between paired images using a two-stage training strategy. We evaluate our method on three publicly available datasets and demonstrate consistent improvements over existing approaches, establishing a strong baseline for before-and-after dietary image analysis. --- ### Bi-Level Optimization for Single Domain Generalization Authors: Marzi Heidari, Hanping Zhang, Hao Yan, Yuhong Guo Published: 2026-04-07 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.06349v1 Generalizing from a single labeled source domain to unseen target domains, without access to any target data during training, remains a fundamental challenge in robust machine learning. We address this underexplored setting, known as Single Domain Generalization (SDG), by proposing BiSDG, a bi-level optimization framework that explicitly decouples task learning from domain modeling. BiSDG simulates distribution shifts through surrogate domains constructed via label-preserving transformations of the source data. To capture domain-specific context, we propose a domain prompt encoder that generates lightweight modulation signals to produce augmenting features via feature-wise linear modulation. The learning process is formulated as a bi-level optimization problem: the inner objective optimizes task performance under fixed prompts, while the outer objective maximizes generalization across the surrogate domains by updating the domain prompt encoder. We further develop a practical gradient approximation scheme that enables efficient bi-level training without second-order derivatives. Extensive experiments on various SGD benchmarks demonstrate that BiSDG consistently outperforms prior methods, setting new state-of-the-art performance in the SDG setting. --- ### Evidence-Based Actor-Verifier Reasoning for Echocardiographic Agents Authors: Peng Huang, Yiming Wang, Yineng Chen, Liangqiao Gui, Hui Guo, Bo Peng, Shu Hu, Xi Wu, Tsao Connie, Hongtu Zhu, Balakrishnan Prabhakaran, Xin Wang Published: 2026-04-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.06347v1 Echocardiography plays an important role in the screening and diagnosis of cardiovascular diseases. However, automated intelligent analysis of echocardiographic data remains challenging due to complex cardiac dynamics and strong view heterogeneity. In recent years, visual language models (VLM) have opened a new avenue for building ultrasound understanding systems for clinical decision support. Nevertheless, most existing methods formulate this task as a direct mapping from video and question to answer, making them vulnerable to template shortcuts and spurious explanations. To address these issues, we propose EchoTrust, an evidence-driven Actor-Verifier framework for trustworthy reasoning in echocardiography VLM-based agents. EchoTrust produces a structured intermediate representation that is subsequently analyzed by distinct roles, enabling more reliable and interpretable decision-making for high-stakes clinical applications. --- ### Severity-Aware Weighted Loss for Arabic Medical Text Generation Authors: Ahmed Alansary, Molham Mohamed, Ali Hamdi Published: 2026-04-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.06346v1 Large language models have shown strong potential for Arabic medical text generation; however, traditional fine-tuning objectives treat all medical cases uniformly, ignoring differences in clinical severity. This limitation is particularly critical in healthcare settings, where errors in severe cases contain higher clinical risk. In this work, we propose a severity-aware weighted loss for fine-tuning Arabic language models on medical complaint-response data. The method depends on soft severity probabilities to dynamically scale token-level loss contributions during optimization, thereby prioritizing clinically critical interactions without modifying model architectures. Experiments are conducted using the MAQA dataset, which provides Arabic medical complaints and trusted human responses. Severity labels and probabilistic scores are automatically derived using a fine-tuned AraBERT-based classifier and incorporated exclusively at the loss level. The proposed approach is evaluated across ten Arabic large language models of varying architectures and parameter scales. While standard cross-entropy fine-tuning yields only modest improvements, severity-aware optimization consistently achieves larger gains. Using a balanced weighting configuration, performance improves from 54.04% to 66.14% for AraGPT2-Base, from 59.16% to 67.18% for AraGPT2-Medium, and from 57.83% to 66.86% for Qwen2.5-0.5B, with peak performance reaching 67.18%. Overall, severity-aware fine-tuning delivers improvements of up to 12.10% over non-fine-tuned baselines, demonstrating robust and architecture-consistent gains. --- ### "Don't Be Afraid, Just Learn": Insights from Industry Practitioners to Prepare Software Engineers in the Age of Generative AI Authors: Daniel Otten, Trevor Stalnaker, Nathan Wintersgill, Oscar Chaparro, Denys Poshyvanyk, Douglas Schmidt Published: 2026-04-07 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.06342v1 Although tension between university curricula and industry expectations has existed in some form for decades, the rapid integration of generative AI (GenAI) tools into software development has recently widened the gap between the two domains. To better understand this disconnect, we surveyed 51 industry practitioners (software developers, technical leads, upper management, \etc) and conducted 11 follow-up interviews focused on hiring practices, required job skills, perceived shortcomings in university curricula, and views on how university learning outcomes can be improved. Our results suggest that GenAI creates demand for new skills (\eg prompting and output evaluation), while strengthening the importance of soft-skills (\eg problem solving and critical thinking) and traditional competencies (\eg architecture design and debugging). We synthesize these findings into actionable recommendations for academia (\eg how to incorporate GenAI into curricula and evaluation redesign). Our work offers empirical guidance to help educators prepare students for modern software engineering environments. --- ### Evolution of Video Generative Foundations Authors: Teng Hu, Jiangning Zhang, Hongrui Huang, Ran Yi, Zihan Su, Jieyu Weng, Zhucun Xue, Lizhuang Ma, Ming-Hsuan Yang, Dacheng Tao Published: 2026-04-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.06339v1 The rapid advancement of Artificial Intelligence Generated Content (AIGC) has revolutionized video generation, enabling systems ranging from proprietary pioneers like OpenAI's Sora, Google's Veo3, and Bytedance's Seedance to powerful open-source contenders like Wan and HunyuanVideo to synthesize temporally coherent and semantically rich videos. These advancements pave the way for building "world models" that simulate real-world dynamics, with applications spanning entertainment, education, and virtual reality. However, existing reviews on video generation often focus on narrow technical fields, e.g., Generative Adversarial Networks (GAN) and diffusion models, or specific tasks (e. g., video editing), lacking a comprehensive perspective on the field's evolution, especially regarding Auto-Regressive (AR) models and integration of multimodal information. To address these gaps, this survey firstly provides a systematic review of the development of video generation technology, tracing its evolution from early GANs to dominant diffusion models, and further to emerging AR-based and multimodal techniques. We conduct an in-depth analysis of the foundational principles, key advancements, and comparative strengths/limitations. Then, we explore emerging trends in multimodal video generation, emphasizing the integration of diverse data types to enhance contextual awareness. Finally, by bridging historical developments and contemporary innovations, this survey offers insights to guide future research in video generation and its applications, including virtual/augmented reality, personalized education, autonomous driving simulations, digital entertainment, and advanced world models, in this rapidly evolving field. For more details, please refer to the project at https://github.com/sjtuplayer/Awesome-Video-Foundations. --- ### BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning Authors: Yi Yang, Ovidiu Daescu Published: 2026-04-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.06336v2 Fragment-level representations provide a natural way to capture recurring molecular substructures and reuse their learned representations across molecules. However, a shared fragment identity alone may not fully describe how a fragment is instantiated in a particular molecule, since the same fragment can exhibit different chemical behavior depending on its surrounding atomic environment. Effective fragment-based molecular learning therefore requires representations that are both reusable across molecules and sensitive to local atomic context. We introduce BiScale-GTR, a self-supervised molecular representation framework built around context-grounded shared fragment tokens. BiScale-GTR constructs a reusable graph Byte Pair Encoding (graph-BPE) vocabulary using Weisfeiler-Lehman (WL)-based fragment identity, chemical validity filtering, and recursive out-of-vocabulary (OOV) decomposition. Each shared fragment token is then grounded with atom-level GNN representations through atom-to-fragment pooling and gated fusion, allowing the same fragment identity to acquire context-dependent representations in different molecular environments. A structure-aware fragment Transformer performs global reasoning over these atom-grounded tokens, capturing reusable substructure identity, local chemical context, and long-range molecular dependencies. Experiments on MoleculeNet, PharmaBench, and the Long Range Graph Benchmark demonstrate strong performance across classification and regression tasks. Attribution analysis further shows that BiScale-GTR highlights chemically meaningful recurring motifs, providing interpretable links between molecular structure and predicted properties. --- ### BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning Authors: Yi Yang, Ovidiu Daescu Published: 2026-04-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.06336v1 Graph Transformers have recently attracted attention for molecular property prediction by combining the inductive biases of graph neural networks (GNNs) with the global receptive field of Transformers. However, many existing hybrid architectures remain GNN-dominated, causing the resulting representations to remain heavily shaped by local message passing. Moreover, most existing methods operate at only a single structural granularity, limiting their ability to capture molecular patterns that span multiple molecular scales. We introduce BiScale-GTR, a unified framework for self-supervised molecular representation learning that combines chemically grounded fragment tokenization with adaptive multi-scale reasoning. Our method improves graph Byte Pair Encoding (BPE) tokenization to produce consistent, chemically valid, and high-coverage fragment tokens, which are used as fragment-level inputs to a parallel GNN-Transformer architecture. Architecturally, atom-level representations learned by a GNN are pooled into fragment-level embeddings and fused with fragment token embeddings before Transformer reasoning, enabling the model to jointly capture local chemical environments, substructure-level motifs, and long-range molecular dependencies. Experiments on MoleculeNet, PharmaBench, and the Long Range Graph Benchmark (LRGB) demonstrate state-of-the-art performance across both classification and regression tasks. Attribution analysis further shows that BiScale-GTR highlights chemically meaningful functional motifs, providing interpretable links between molecular structure and predicted properties. Code will be released upon acceptance. --- ### Drifting Fields are not Conservative Authors: Leonard T. Franz, Sebastian Hoffmann, Tim Weiland, Bernhard Schölkopf, Georg Martius Published: 2026-04-07 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2604.06333v3 Drifting models have recently gained attention for generating high-quality samples in a single forward pass. During training, they learn a push-forward map by following a vector-valued field, the drift field. We ask whether this procedure is equivalent to optimizing a scalar loss and find that, in general, it is not: drift fields are not conservative and cannot be written as the gradient of any scalar potential. We identify the position-dependent normalization as the source of non-conservatism, with the Gaussian kernel as the unique radial exception. Guided by this, we introduce the sharp kernel $k^\#$ and a sharp-normalized drift field that is conservative for general radial kernels. The resulting vector field is the gradient of a scalar potential that can be optimized directly using stochastic gradient descent. Moreover, the field has the form of a score difference of kernel density estimates, and gives exact equilibrium identifiability. Thus, sharp normalization closes the gap to related literature, such as Wasserstein gradient-flows and denoising score matching, also for non-Gaussian kernels. Empirically, sharp normalization preserves the performance of the original drifting objective, suggesting that the non-conservative flexibility is not required for high-quality generation. --- ### Telescope: Learnable Hyperbolic Foveation for Ultra-Long-Range Object Detection Authors: Parker Ewen, Dmitriy Rivkin, Mario Bijelic, Felix Heide Published: 2026-04-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.06332v1 Autonomous highway driving, especially for long-haul heavy trucks, requires detecting objects at long ranges beyond 500 meters to satisfy braking distance requirements at high speeds. At long distances, vehicles and other critical objects occupy only a few pixels in high-resolution images, causing state-of-the-art object detectors to fail. This challenge is compounded by the limited effective range of commercially available LiDAR sensors, which fall short of ultra-long range thresholds because of quadratic loss of resolution with distance, making image-based detection the most practically scalable solution given commercially available sensor constraints. We introduce Telescope, a two-stage detection model designed for ultra-long range autonomous driving. Alongside a powerful detection backbone, this model contains a novel re-sampling layer and image transformation to address the fundamental challenges of detecting small, distant objects. Telescope achieves $76\%$ relative improvement in mAP in ultra-long range detection compared to state-of-the-art methods (improving from an absolute mAP of 0.185 to 0.326 at distances beyond 250 meters), requires minimal computational overhead, and maintains strong performance across all detection ranges. --- ### STDec: Spatio-Temporal Stability Guided Decoding for dLLMs Authors: Yuzhe Chen, Jiale Cao, Xuyang Liu, Jin Xie, Aiping Yang, Yanwei Pang Published: 2026-04-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.06330v1 Diffusion Large Language Models (dLLMs) have achieved rapid progress, viewed as a promising alternative to the autoregressive paradigm. However, most dLLM decoders still adopt a global confidence threshold, and do not explicitly model local context from neighboring decoded states or temporal consistency of predicted token IDs across steps. To address this issue, we propose a simple spatio-temporal stability guided decoding approach, named STDec. We observe strong spatio-temporal stability in dLLM decoding: newly decoded tokens tend to lie near decoded neighbors, and their predicted IDs often remain consistent across several denoising steps. Inspired by this stability, our STDec includes spatial-aware decoding and temporal-aware decoding. The spatial-aware decoding dynamically generates the token-adaptive threshold by aggregating the decoded states of nearby tokens. The temporal-aware decoding relaxes the decoding thresholds for tokens whose predicted token IDs remain consistent over denoising steps. Our STDec is training-free and remains compatible with cache-based acceleration methods. Across textual reasoning and multimodal understanding benchmarks, STDec substantially improves throughput while maintaining comparable task performance score. Notably, on MBPP with LLaDA, STDec achieves up to 14.17x speedup with a comparable score. Homepage: https://yzchen02.github.io/STDec. --- ### A Novel Automatic Framework for Speaker Drift Detection in Synthesized Speech Authors: Jia-Hong Huang, Seulgi Kim, Yi Chieh Liu, Yixian Shen, Hongyi Zhu, Prayag Tiwari, Stevan Rudinac, Evangelos Kanoulas Published: 2026-04-07 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2604.06327v1 Recent diffusion-based text-to-speech (TTS) models achieve high naturalness and expressiveness, yet often suffer from speaker drift, a subtle, gradual shift in perceived speaker identity within a single utterance. This underexplored phenomenon undermines the coherence of synthetic speech, especially in long-form or interactive settings. We introduce the first automatic framework for detecting speaker drift by formulating it as a binary classification task over utterance-level speaker consistency. Our method computes cosine similarity across overlapping segments of synthesized speech and prompts large language models (LLMs) with structured representations to assess drift. We provide theoretical guarantees for cosine-based drift detection and demonstrate that speaker embeddings exhibit meaningful geometric clustering on the unit sphere. To support evaluation, we construct a high-quality synthetic benchmark with human-validated speaker drift annotations. Experiments with multiple state-of-the-art LLMs confirm the viability of this embedding-to-reasoning pipeline. Our work establishes speaker drift as a standalone research problem and bridges geometric signal analysis with LLM-based perceptual reasoning in modern TTS. --- ### Blockchain and AI: Securing Intelligent Networks for the Future Authors: Joy Dutta, Hossien B. Eldeeb, Tu Dac Ho Published: 2026-04-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.06323v2 Blockchain and artificial intelligence (AI) are increasingly proposed together for securing intelligent networks, but the literature remains fragmented across ledger design, AI-driven detection, cyber-physical applications, and emerging agentic workflows. This paper synthesizes the area through three reusable contributions: (i) a taxonomy of blockchain-AI security for intelligent networks, (ii) integration patterns for verifiable and adaptive security workflows, and (iii) the Blockchain-AI Security Evaluation Blueprint (BASE), a reporting checklist spanning AI quality, ledger behavior, end-to-end service levels, privacy, energy, and reproducibility. The paper also maps the evidence landscape across IoT, critical infrastructure, smart grids, transportation, and healthcare, showing that the conceptual fit is strong but real-world evidence remains uneven and often prototype-heavy. The synthesis clarifies where blockchain contributes provenance, trust, and auditability, where AI contributes detection, adaptation, and orchestration, and where future work should focus on interoperable interfaces, privacy-preserving analytics, bounded agentic automation, and open cross-domain benchmarks. The paper is intended as a reference for researchers and practitioners designing secure, transparent, and resilient intelligent networks. --- ### Limits of Difficulty Scaling: Hard Samples Yield Diminishing Returns in GRPO-Tuned SLMs Authors: Suraj Yadav, Siddharth Yadav, Parth Goyal Published: 2026-04-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.06298v1 Recent alignment work on Large Language Models (LLMs) suggests preference optimization can improve reasoning by shifting probability mass toward better solutions. We test this claim in a resource-constrained setting by applying GRPO with LoRA to SLMs (up to 3B) for math reasoning on GSM8K and MATH datasets with difficulty-stratified analyses. As problem difficulty increases, accuracy plateaus, revealing a capacity boundary: GRPO primarily reshapes output preferences without reliably improving hardest-tier solving. Consistent with this, training GRPO only on lower-difficulty problems matches full-dataset accuracy across difficulty tiers while using only ~45% training steps, indicating diminishing returns from harder samples in this regime. We also find a cross-dataset generalization effect: GSM8K-trained GRPO achieves higher accuracy on the numeric subset of MATH than MATH-trained GRPO, exceeding it by ~5% at 1.5B and by ~3% at 3B. We show that the best achievable gains depend strongly on the base model's prior reasoning competence and the dataset's difficulty profile. --- ### FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs Authors: Syed Irfan Ali Meerza, Feiyi Wang, Jian Liu Published: 2026-04-07 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.06297v1 Given the growing reliance on private data in training Large Language Models (LLMs), Federated Learning (FL) combined with Parameter-Efficient Fine-Tuning (PEFT) has garnered significant attention for enhancing privacy and efficiency. Despite FL's privacy benefits, prior studies have shown that private data can still be extracted from shared gradients. However, these studies, mainly on full-parameter model training, are limited to reconstructing small batches, short input sequences, and specific model architectures, such as encoder-based or decoder-based models. The reconstruction quality becomes even worse when dealing with gradients from PEFT methods. To fully understand the practical attack surface of federated LLMs, this paper proposes FedSpy-LLM, a scalable and generalizable data reconstruction attack designed to reconstruct training data with larger batch sizes and longer sequences while generalizing across diverse model architectures, even when PEFT methods are deployed for training. At the core of FedSpy-LLM is a novel gradient decomposition strategy that exploits the rank deficiency and subspace structure of gradients, enabling efficient token extraction while preserving key signal components at scale. This approach further mitigates the reconstruction challenges introduced by PEFT's substantial null space, ensuring robustness across encoder-based, decoder-based, and encoder-decoder model architectures. Additionally, by iteratively aligning each token's partial-sequence gradient with the full-sequence gradient, FedSpy-LLM ensures accurate token ordering in reconstructed sequences. --- ### AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent Authors: Wenyue Hua, Sripad Karne, Qian Xie, Armaan Agrawal, Nikos Pagonas, Kostis Kaffes, Tianyi Peng Published: 2026-04-07 Categories: cs.LG, cs.AI, cs.MA, cs.SE arXiv: https://arxiv.org/abs/2604.06296v2 AI agents are increasingly deployed in real-world applications, including systems such as Manus, OpenClaw, and coding agents. Existing research has primarily focused on server-side efficiency, proposing methods such as caching, speculative execution, traffic scheduling, and load balancing to reduce the cost of serving agentic workloads. However, as users increasingly construct agents by composing local tools, remote APIs, and diverse models, an equally important optimization problem arises on the client side. Client-side optimization asks how developers should allocate the resources available to them, including model choice, local tools, and API budget across pipeline stages, subject to application-specific quality, cost, and latency constraints. Because these objectives depend on the task and deployment setting, they cannot be determined by server-side systems alone. We introduce AgentOpt, the first framework-agnostic Python package for client-side agent optimization. We first study model selection, a high-impact optimization lever in multi-step agent pipelines. Given a pipeline and a small evaluation set, the goal is to find the most cost-effective assignment of models to pipeline roles. This problem is consequential in practice: at matched accuracy, the cost gap between the best and worst model combinations can reach 13-32x in our experiments. To efficiently explore the exponentially growing combination space, AgentOpt implements ten search algorithms, including UCB-E, UCB-E with Low-Rank Factorization, Arm Elimination, Epsilon-LUCB, Threshold Successive Elimination, and Bayesian Optimization. Across four benchmarks, UCB-E recovers near-optimal accuracy while reducing evaluation budget by 62-76\% relative to brute-force search. Code and benchmark results available at https://agentoptimizer.github.io/agentopt/. --- ### TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models Authors: Lin Mu, Haiyang Wang, Li Ni, Lei Sang, Zhize Wu, Peiquan Jin, Yiwen Zhang Published: 2026-04-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.06291v1 Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of Large Language Models (LLMs), and recent Mixture-of-Experts (MoE) extensions further enhance flexibility by dynamically combining multiple LoRA experts. However, existing MoE-augmented LoRA methods assume that experts operate independently, often leading to unstable routing, expert dominance. In this paper, we propose \textbf{TalkLoRA}, a communication-aware MoELoRA framework that relaxes this independence assumption by introducing expert-level communication prior to routing. TalkLoRA equips low-rank experts with a lightweight Talking Module that enables controlled information exchange across expert subspaces, producing a more robust global signal for routing. Theoretically, we show that expert communication smooths routing dynamics by mitigating perturbation amplification while strictly generalizing existing MoELoRA architectures. Empirically, TalkLoRA consistently outperforms vanilla LoRA and MoELoRA across diverse language understanding and generation tasks, achieving higher parameter efficiency and more balanced expert routing under comparable parameter budgets. These results highlight structured expert communication as a principled and effective enhancement for MoE-based parameter-efficient adaptation. Code is available at https://github.com/why0129/TalkLoRA. --- ### Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment Authors: Xaver Fink, Borja Fernandez Adiego, Daniele Mirarchi, Eloise Matheson, Alvaro Garcia Gonzales, Gianmarco Ricci, Joost-Pieter Katoen Published: 2026-04-07 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.06289v1 In this paper, we analyze and improve the adversarial robustness of a convolutional neural network (CNN) that assists crystal-collimator alignment at CERN's Large Hadron Collider (LHC) by classifying a beam-loss monitor (BLM) time series during crystal rotation. We formalize a local robustness property for this classifier under an adversarial threat model based on real-world plausibility. Building on established parameterized input-transformation patterns used for transformation- and semantic-perturbation robustness, we instantiate a preprocessing-aware wrapper for our deployed time-series pipeline: we encode time-series normalization, padding constraints, and structured perturbations as a lightweight differentiable wrapper in front of the CNN, so that existing gradient-based robustness frameworks can operate on the deployed pipeline. For formal verification, data-dependent preprocessing such as per-window z-normalization introduces nonlinear operators that require verifier-specific abstractions. We therefore focus on attack-based robustness estimates and pipeline-checked validity by benchmarking robustness with the frameworks Foolbox and ART. Adversarial fine-tuning of the resulting CNN improves robust accuracy by up to 18.6 % without degrading clean accuracy. Finally, we extend robustness on time-series data beyond single windows to sequence-level robustness for sliding-window classification, introduce adversarial sequences as counterexamples to a temporal robustness requirement over full scans, and observe attack-induced misclassifications that persist across adjacent windows. --- ### Asymptotic-Preserving Neural Networks for Viscoelastic Parameter Identification in Multiscale Blood Flow Modeling Authors: Giulia Bertaglia, Raffaella Fiamma Cabini Published: 2026-04-07 Categories: cs.LG, math.NA, physics.comp-ph, physics.flu-dyn arXiv: https://arxiv.org/abs/2604.06287v1 Mathematical models and numerical simulations offer a non-invasive way to explore cardiovascular phenomena, providing access to quantities that cannot be measured directly. In this study, we start with a one-dimensional multiscale blood flow model that describes the viscoelastic properties of arterial walls, and we focus on improving its practical applicability by addressing a major challenge: determining, in a reliable way, the viscoelastic parameters that control how arteries deform under pulsatile pressure. To achieve this, we employ Asymptotic-Preserving Neural Networks that embed the governing physical principles of the multiscale viscoelastic blood flow model within the learning procedure. This framework allows us to infer the viscoelastic parameters while simultaneously reconstructing the time-dependent evolution of the state variables of blood vessels. With this approach, pressure waveforms are estimated from readily accessible patient-specific data, i.e., cross-sectional area and velocity measurements from Doppler ultrasound, in vascular segments where direct pressure measurements are not available. Different numerical simulations, conducted in both synthetic and patient-specific scenarios, show the effectiveness of the proposed methodology. --- ### Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization Authors: Igor Maljkovic, Maria Rosaria Briglia, Iacopo Masi, Antonio Emanuele Cinà, Fabio Roli Published: 2026-04-07 Categories: cs.CR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.06285v1 Vision-Language Models (VLMs) have become essential for tasks such as image synthesis, captioning, and retrieval by aligning textual and visual information in a shared embedding space. Yet, this flexibility also makes them vulnerable to malicious prompts designed to produce unsafe content, raising critical safety concerns. Existing defenses either rely on blacklist filters, which are easily circumvented, or on heavy classifier-based systems, both of which are costly and fragile under embedding-level attacks. We address these challenges with two complementary components: Hyperbolic Prompt Espial (HyPE) and Hyperbolic Prompt Sanitization (HyPS). HyPE is a lightweight anomaly detector that leverages the structured geometry of hyperbolic space to model benign prompts and detect harmful ones as outliers. HyPS builds on this detection by applying explainable attribution methods to identify and selectively modify harmful words, neutralizing unsafe intent while preserving the original semantics of user prompts. Through extensive experiments across multiple datasets and adversarial scenarios, we prove that our framework consistently outperforms prior defenses in both detection accuracy and robustness. Together, HyPE and HyPS offer an efficient, interpretable, and resilient approach to safeguarding VLMs against malicious prompt misuse. --- ### ClawLess: A Security Model of AI Agents Authors: Hongyi Lu, Nian Liu, Shuai Wang, Fengwei Zhang Published: 2026-04-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.06284v1 Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to regulate agent behavior through training or prompting, which does not offer fundamental security guarantees. We present ClawLess, a security framework that enforces formally verified policies on AI agents under a worst-case threat model where the agent itself may be adversarial. ClawLess formalizes a fine-grained security model over system entities, trust scopes, and permissions to express dynamic policies that adapt to agents' runtime behavior. These policies are translated into concrete security rules and enforced through a user-space kernel augmented with BPF-based syscall interception. This approach bridges the formal security model with practical enforcement, ensuring security regardless of the agent's internal design. --- ### Tight Convergence Rates for Online Distributed Linear Estimation with Adversarial Measurements Authors: Nibedita Roy, Vishal Halder, Gugan Thoppe, Alexandre Reiffers-Masson, Mihir Dhanakshirur, Naman, Alexandre Azor Published: 2026-04-07 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.06282v1 We study mean estimation of a random vector $X$ in a distributed parameter-server-worker setup. Worker $i$ observes samples of $a_i^\top X$, where $a_i^\top$ is the $i$th row of a known sensing matrix $A$. The key challenges are adversarial measurements and asynchrony: a fixed subset of workers may transmit corrupted measurements, and workers are activated asynchronously--only one is active at any time. In our previous work, we proposed a two-timescale $\ell_1$-minimization algorithm and established asymptotic recovery under a null-space-property-like condition on $A$. In this work, we establish tight non-asymptotic convergence rates under the same null-space-property-like condition. We also identify relaxed conditions on $A$ under which exact recovery may fail but recovery of a projected component of $\mathbb{E}(X)$ remains possible. Overall, our results provide a unified finite-time characterization of robustness, identifiability, and statistical efficiency in distributed linear estimation with adversarial workers, with implications for network tomography and related distributed sensing problems. --- ### Generalization error bounds for two-layer neural networks with Lipschitz loss function Authors: Jiang Yu Nguwi, Nicolas Privault Published: 2026-04-07 Categories: stat.ML, math.PR arXiv: https://arxiv.org/abs/2604.06281v1 We derive generalization error bounds for the training of two-layer neural networks without assuming boundedness of the loss function, using Wasserstein distance estimates on the discrepancy between a probability distribution and its associated empirical measure, together with moment bounds for the associated stochastic gradient method. In the case of independent test data, we obtain a dimension-free rate of order $O(n^{-1/2} )$ on the $n$-sample generalization error, whereas without independence assumption, we derive a bound of order $O(n^{-1 / ( d_{\rm in}+d_{\rm out} )} )$, where $d_{\rm in}$, $d_{\rm out}$ denote input and output dimensions. Our bounds and their coefficients can be explicitly computed prior to the training of the model, and are confirmed by numerical simulations. --- ### DosimeTron: Automating Personalized Monte Carlo Radiation Dosimetry in PET/CT with Agentic AI Authors: Eleftherios Tzanis, Michail E. Klontzas, Antonios Tzortzakakis Published: 2026-04-07 Categories: physics.med-ph, cs.AI arXiv: https://arxiv.org/abs/2604.06280v1 Purpose: To develop and evaluate DosimeTron, an agentic AI system for automated patient-specific MC internal radiation dosimetry in PET/CT examinations. Materials and Methods: In this retrospective study, DosimeTron was evaluated on a publicly available PSMA-PET/CT dataset comprising 597 studies from 378 male patients acquired on three scanner models (18-F, n = 369; 68-Ga, n = 228). The system uses GPT-5.2 as its reasoning engine and 23 tools exposed via four Model Context Protocol servers, automating DICOM metadata extraction, image preprocessing, MC simulation, organ segmentation, and dosimetric reporting through natural-language interaction. Agentic performance was assessed using diverse prompt templates spanning single-turn instructions of varying specificity and multi-turn conversational exchanges, monitored via OpenTelemetry traces. Dosimetric accuracy was validated against OpenDose3D across 114 cases and 22 organs using Pearson's r, Lin's concordance correlation coefficient (CCC), and Bland-Altman analysis. Results: Across all prompt templates and all runs, no execution failures, pipeline errors, or hallucinated outputs were observed. Pearson's r ranged from 0.965 to 1.000 (median 0.997; all p < 0.001) and CCC from 0.963 to 1.000 (median 0.996). Mean absolute percentage difference was below 5% for 19 of 22 organs (median 2.5%). Total per-study processing time (SD) was 32.3 (6.0) minutes. Conclusion: DosimeTron autonomously executed complex dosimetry pipelines across diverse prompt configurations and achieved high dosimetric agreement with OpenDose3D at clinically acceptable processing times, demonstrating the feasibility of agentic AI for patient-specific Monte Carlo dosimetry in PET/CT. --- ### Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations Authors: Ruichen Zhang, Feda AlMuhisen, Chenguang Wan, Zhisong Qu, Kunpeng Li, Youngwoo Cho, Kyungtak Lim, Virginie Grandgirard, Xavier Garbet Published: 2026-04-07 Categories: physics.plasm-ph, cs.AI arXiv: https://arxiv.org/abs/2604.06279v1 Accurate parameter selection is fundamental to gyrokinetic plasma simulations, yet current practices rely heavily on manual literature reviews, leading to inefficiencies and inconsistencies. We introduce Plasma GraphRAG, a novel framework that integrates Graph Retrieval-Augmented Generation (GraphRAG) with large language models (LLMs) for automated, physics-grounded parameter range identification. By constructing a domain-specific knowledge graph from curated plasma literature and enabling structured retrieval over graph-anchored entities and relations, Plasma GraphRAG enables LLMs to generate accurate, context-aware recommendations. Extensive evaluations across five metrics, comprehensiveness, diversity, grounding, hallucination, and empowerment, demonstrate that Plasma GraphRAG outperforms vanilla RAG by over $10\%$ in overall quality and reduces hallucination rates by up to $25\%$. {Beyond enhancing simulation reliability, Plasma GraphRAG offers a methodology for accelerating scientific discovery across complex, data-rich domains. --- ### Weakly Supervised Distillation of Hallucination Signals into Transformer Representations Authors: Shoaib Sadiq Salehmohamed, Jinal Prashant Thakkar, Hansika Aredla, Shaik Mohammed Omar, Shalmali Ayachit Published: 2026-04-07 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.06277v1 Existing hallucination detection methods for large language models (LLMs) rely on external verification at inference time, requiring gold answers, retrieval systems, or auxiliary judge models. We ask whether this external supervision can instead be distilled into the model's own representations during training, enabling hallucination detection from internal activations alone at inference time. We introduce a weak supervision framework that combines three complementary grounding signals: substring matching, sentence embedding similarity, and an LLM as a judge verdict to label generated responses as grounded or hallucinated without human annotation. Using this framework, we construct a 15000-sample dataset from SQuAD v2 (10500 train/development samples and a separate 5000-sample test set), where each example pairs a LLaMA-2-7B generated answer with its full per-layer hidden states and structured hallucination labels. We then train five probing classifiers: ProbeMLP (M0), LayerWiseMLP (M1), CrossLayerTransformer (M2), HierarchicalTransformer (M3), and CrossLayerAttentionTransformerV2 (M4), directly on these hidden states, treating external grounding signals as training-time supervision only. Our central hypothesis is that hallucination detection signals can be distilled into transformer representations, enabling internal detection without any external verification at inference time. Results support this hypothesis. Transformer-based probes achieve the strongest discrimination, with M2 performing best on 5-fold average AUC/F1, and M3 performing best on both single-fold validation and held-out test evaluation. We also benchmark inference efficiency: probe latency ranges from 0.15 to 5.62 ms (batched) and 1.55 to 6.66 ms (single sample), while end-to-end generation plus probe throughput remains approximately 0.231 queries per second, indicating negligible practical overhead. --- ### Structural Regularities of Cinema SDR-to-HDR Mapping in a Controlled Mastering Workflow: A Pixel-wise Case Study on ASC StEM2 Authors: Xin Zhang, Xiaoyi Chen Published: 2026-04-07 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2604.06276v1 We present an empirical case study of cinema SDR-to-HDR mapping using ASC StEM2, a rare common-source dataset containing EXR scene-referred images and matched SDR/HDR cinema release masters from the same ACES-based mastering workflow. Based on pixel-wise statistics over all 18,580 frames of the test film, we construct a three-domain comparison involving EXR source data, SDR release masters, and HDR release masters to characterize their luminance and color structural relationships within this controlled workflow. In the luminance dimension, SDR and HDR masters exhibit a highly stable global monotonic correspondence, with geometric structure remaining largely consistent overall; sparse and structured deviations appear in self-luminous highlights and specific material regions. In the color dimension, the two masters remain largely consistent in hue, with saturation exhibiting a redistribution pattern of shadow suppression, midtone expansion, and highlight convergence. Using EXR as a scene-referred anchor, we further define a pixel-level decision map that operationally separates EXR-closer recovery regions from content-adaptive adjustment regions. Under this operational definition, 82.4% of sampled image regions are classified as EXR-closer recovery, while the remainder require localized adaptive adjustment. Rather than claiming a universal law for all cinema mastering pipelines, the study provides an interpretable quantitative baseline for structure-aware SDR-to-HDR analysis and for designing learning-based models under shared-source mastering conditions. ---