# Research Papers — 2026-03 · bundle page 23 of 243 > Full-text markdown of papers #1101–1150 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/23 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/22.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/24.md) ### Development and Preliminary Evaluation of a Domain-Specific Large Language Model for Tuberculosis Care in South Africa Authors: Thokozile Khosa, Olawande Daramola Published: 2026-03-28 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.19776v1 Tuberculosis (TB) is one of the world's deadliest infectious diseases, and in South Africa, it contributes a significant burden to the country's health care system. This paper presents an experimental study on the development of a domain-specific Large Language Model (DS-LLM) for TB care that can help to alleviate the burden on patients and healthcare providers. To achieve this, a literature review was conducted to understand current LLM development strategies, specifically in the medical domain. Thereafter, data were collected from South African TB guidelines, selected TB literature, and existing benchmark medical datasets. We performed LLM fine-tuning by using the Quantised Low-Rank Adaptation (QLoRA) algorithm on a medical LLM (BioMistral-7B), and also implemented Retrieval-Augmented Generation using GraphRAG. The developed DS-LLM was evaluated against the base BioMistral-7B model and a general-purpose LLM using a mix of automated metrics and quantitative ratings. The results show that the DS-LLM had better performance compared to the base model in terms of its contextual alignment (lexical, semantic, and knowledge) for TB care in South Africa. --- ### A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search Authors: Riccardo Terrenzi, Phongsakon Mark Konrad, Tim Lukas Adam, Serkan Ayvaz Published: 2026-03-28 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.16394v1 Ad hoc dataset search requires matching underspecified natural-language queries against sparse, heterogeneous metadata records, a task where typical lexical or dense retrieval alone falls short. We reposition dataset search as a software-architecture problem and propose a bounded, auditable reference architecture for agentic hybrid retrieval that combines BM25 lexical search with dense-embedding retrieval via reciprocal rank fusion (RRF), orchestrated by a large language model (LLM) agent that repeatedly plans queries, evaluates the sufficiency of results, and reranks candidates. To reduce the vocabulary mismatch between user intent and provider-authored metadata, we introduce an offline metadata augmentation step in which an LLM generates pseudo-queries for each dataset record, augmenting both retrieval indexes before query time. Two architectural styles are examined: a single ReAct agent and a multi-agent horizontal architecture with Feedback Control. Their quality-attribute tradeoffs are analyzed with respect to modifiability, observability, performance, and governance. An evaluation framework comprising seven system variants is defined to isolate the contribution of each architectural decision. The architecture is presented as an extensible reference design for the software architecture community, incorporating explicit governance tactics to bound and audit nondeterministic LLM components. --- ### RoMathExam: A Longitudinal Dataset of Romanian Math Exams (1895-2025) with a Seven-Decade Core (1957-2025) Authors: Luca-Ncolae Cuclea, Sabin-Codrut Badea, Adrian-Marius Dumitran Published: 2026-03-28 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.16392v1 AI in Education research increasingly relies on authentic, curriculum-grounded assessment data, yet large, well-structured exam corpora remain scarce for many languages and educational systems. We introduce RoMathExam, a longitudinal dataset of Romanian high-school mathematics exams spanning 1895-2025, with a robust standardized core for 1957-2025. The dataset contains 10,592 mathematics problems organized into 600+ complete exam sets across multiple tracks (M1-M4), covering both official national examination sessions and ministry-published training variants. Beyond high-fidelity digitization and a unified JSON schema with traceable provenance, RoMathExam is enriched with curriculum-aligned topic tags and dense text embeddings, enabling variant detection, deduplication, and similarity-based retrieval. To overcome the lack of historical psychometric data, we propose and validate a solution complexity metric as a scalable intrinsic proxy for difficulty. Our evaluation across three frontier reasoning models (GPT-5-mini, DeepSeek-R1, and Qwen3-235B-Thinking) reveals high cross-model synchronization (r > 0.72), confirming the metric's ability to isolate intrinsic mathematical depth from stochastic generation noise. We demonstrate the dataset's utility through a longitudinal analysis that quantifies a "regime shift" from volatile historical formats to a standardized, algebra-dominant modern curriculum. RoMathExam provides a foundation for reproducible research in difficulty modeling, curriculum analytics, and LLM evaluation in low-resource linguistic contexts. --- ### SocialWise: LLM-Agentic Conversation Therapy for Individuals with Autism Spectrum Disorder to Enhance Communication Skills Authors: Albert Tang Published: 2026-03-28 Categories: cs.HC, cs.AI, cs.IR, cs.MA arXiv: https://arxiv.org/abs/2604.15347v1 Autism Spectrum Disorder (ASD) affects more than 75 million people worldwide. However, scalable support for practicing everyday conversation is scarce: Low-cost activities such as story reading yield limited improvement. At the same time, effective role-play therapy demands expensive, in-person sessions with specialists. SocialWise bridges this gap through a browser-based application that pairs LLM conversational agents with a therapeutic retrieval augmented generation (RAG) knowledge base. Users select a scenario (e.g., ordering food, joining a group), interact by text or voice, and receive instant, structured feedback on tone, engagement, and alternative phrasing. The SocialWise prototype, implemented with Streamlit, LangChain, and ChromaDB, runs on any computer with internet access, and demonstrates how recent advances in LLM can provide evidence-based, on-demand communication coaching for individuals with ASD. --- ### Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systems Authors: Hong Su Published: 2026-03-28 Categories: cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2604.14178v1 Large Language Model (LLM) agents have demonstrated remarkable capabilities in reasoning and tool use, yet they often suffer from rigid, reactive control flows that limit their adaptability and efficiency. Most existing frameworks rely on fixed pipelines or failure-triggered reflection, causing agents to act impulsively or correct errors only after they occur. In this paper, we introduce Heartbeat-Driven Autonomous Thinking Activity Scheduling, a mechanism that enables proactive, adaptive, and continuous self-regulation. Mirroring the natural rhythm of human cognition, our system employs a periodic ``heartbeat'' mechanism to orchestrate a dynamic repertoire of cognitive modules (e.g., Planner, Critic, Recaller, Dreamer). Unlike traditional approaches that rely on hard-coded symbolic rules or immediate reactive triggers, our scheduler learns to determine when to engage specific thinking activities -- such as recalling memories, summarizing experiences, or strategic planning -- based on temporal patterns and historical context. This functional approach allows cognitive modules to be dynamically added or removed without structural reengineering. Meanwhile, we propose a meta-learning strategy for continual policy adaptation, where the scheduler optimizes its cognitive strategy over time using historical interaction logs. Evaluation results demonstrate that our approach effectively learns to schedule cognitive activities based on historical data and can autonomously integrate new thinking modules. --- ### Listen, Correct, and Feed Back: Spoken Pedagogical Feedback Generation Authors: Junhong Liang, Yifan Lu, Ekaterina Kochmar, Fajri Koto Published: 2026-03-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.14177v1 Grammatical error correction (GEC) and explanation (GEE) have made rapid progress, but real teaching scenarios also require \emph{learner-friendly pedagogical feedback} that is actionable, level-appropriate, and encouraging. We introduce \textbf{SPFG} (\textbf{S}poken \textbf{P}edagogical \textbf{F}eedback \textbf{G}eneration), a dataset built based on the Speak \& Improve Challenge 2025 corpus, pairing fluency-oriented transcriptions with GEC targets and \emph{human-verified} teacher-style feedback, including preferred/rejected feedback pairs for preference learning. We study a transcript-based Spoken Grammatical Error Correction (SGEC) setting and evaluate three instruction-tuned LLMs (Qwen2.5, Llama-3.1, and GLM-4), comparing supervised fine-tuning (SFT) with preference-based alignment (using DPO and KTO) for jointly generating corrections and feedback. Results show that SFT provides the most consistent improvements, while DPO/KTO yield smaller or mixed gains, and that correction quality and feedback quality are weakly coupled. Our implementation is available at https://github.com/Skywalker-Harrison/spfg. --- ### Selectivity and Shape in the Design of Forward-Forward Goodness Functions Authors: Talha Ruzgar Akkus, Suayp Talha Kocabay, Kamer Ali Yuksel, Hassan Sawaf Published: 2026-03-28 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2604.13081v2 The Forward-Forward (FF) algorithm trains networks layer-by-layer using a local "goodness function," yet sum-of-squares (SoS) has remained the only choice studied. We systematically explore the goodness-function design space and identify a unifying principle: the goodness function must be sensitive to the shape of neural activity, not its total energy. This principle is motivated by the observation that deep network activations follow heavy-tailed distributions and that discriminative information is often concentrated in peak activities. We propose two complementary families: selective functions (top-k, entmax-weighted energy) that measure only peak activity, and shape-sensitive functions (excess kurtosis / "burstiness" and higher-order moments) that reward heavy-tailed distributions via scale-invariant statistics. Combined with separate label-feature forwarding (FFCL), controlled experiments across 13 goodness functions, 5 activations, 6 datasets, and three continuous sweeps, each tracing a characteristic inverted-U, yield 89.0% on Fashion-MNIST and 98.2+-0.1% on MNIST (4x2000), a +32.6pp gain over SoS, with consistent improvements across all benchmarks (+72pp USPS, +52pp SVHN). The scale-invariant nature of burstiness makes it particularly robust to magnitude shifts across layers and datasets. --- ### Fully Autonomous Z-Score-Based TinyML Anomaly Detection on Resource-Constrained MCUs Using Power Side-Channel Data Authors: Abdulrahman Albaiz, Fathi Amsaad Published: 2026-03-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08581v1 This paper presents a fully autonomous Tiny Machine Learning (TinyML) Z-Score-based anomaly detection system deployed on a low-power microcontroller for real-time monitoring of appliance behavior using power side-channel data. Unlike existing Internet of Things (IoT) anomaly detection approaches that rely on offline training or cloud-assisted analytics, the proposed system performs both model training and inference directly on a resource-constrained microcontroller without external computation or connectivity. The system continuously samples current consumption, computes Root Mean Square (RMS) values on-device, and derives statistical parameters during an initial training phase. Anomalies are detected using lightweight Z-Score thresholds, enabling interpretable and computationally efficient inference suitable for embedded deployment. The architecture was implemented on an STM32-based platform and evaluated using a 14-day dataset collected from a household mini-fridge under normal operation and controlled anomaly conditions. Results demonstrate perfect detection performance, with Precision and Recall of 1.00, inference latencies on the order of tens of microseconds, and a total memory footprint of approximately 3.3 KB SRAM and 63 KB Flash. These results confirm that robust and fully autonomous TinyML anomaly detection can be achieved on low-cost microcontrollers. Future work includes extending the framework to incorporate additional lightweight models and multi-device learning scenarios. --- ### Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control Authors: Carles Domingo-Enrich, Jiequn Han Published: 2026-03-28 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2604.08580v2 Reward fine-tuning of diffusion and flow models and sampling from tilted or Boltzmann distributions can both be formulated as stochastic optimal control (SOC) problems, where learning an optimal generative dynamics corresponds to optimizing a control under SDE constraints. In this work, we revisit and generalize Adjoint Matching, a recently proposed SOC-based method for learning optimal controls, and place it on a rigorous footing by deriving it from the Stochastic Maximum Principle (SMP). We formulate a general Hamiltonian adjoint matching objective for SOC problems with control-dependent drift and diffusion and convex running costs, and show that its expected value has the same first variation as the original SOC objective. As a consequence, critical points satisfy the Hamilton--Jacobi--Bellman (HJB) stationarity conditions. In the important practical case of state- and control-independent diffusion, we recover the lean adjoint matching loss previously introduced, which avoids second-order terms and whose critical points coincide with the optimal control under mild uniqueness assumptions. Numerical experiments confirm that the extra terms it discards become necessary once the diffusion is state-dependent. Finally, we show that adjoint matching can be precisely interpreted as a continuous-time method of successive approximations induced by the SMP, yielding a practical and implementable alternative to classical SMP-based algorithms, which are obstructed by intractable martingale terms in the stochastic setting. These results are also of independent interest to the stochastic control community, providing new implementable objectives and a viable pathway for SMP-based iterations in stochastic problems. --- ### On the Spectral Geometry of Cross-Modal Representations: A Functional Map Diagnostic for Multimodal Alignment Authors: Krisanu Sarkar Published: 2026-03-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08579v1 We study cross-modal alignment between independently pretrained vision (DINOv2) and language (all-MiniLM-L6-v2) encoders using the functional map framework from computational geometry, which represents correspondence between representation manifolds as a compact linear operator between graph Laplacian eigenbases. While the framework underperforms Procrustes alignment and relative representations for cross-modal retrieval across all supervision budgets, it reveals a structural property of multimodal representations. We find that the Laplacian eigenvalue spectra of the two encoders are quantitatively similar (normalized spectral distance 0.043), indicating that independently trained models develop manifolds of comparable intrinsic complexity. However, the functional map exhibits near-zero diagonal dominance (mean below 0.05) and large orthogonality error (70.15), showing that the eigenvector bases are effectively unaligned. We term this decoupling the spectral complexity--orientation gap: models converge in how much structure they capture but not in how they organize it. This gap defines a boundary condition for spectral alignment methods and motivates three diagnostic quantities : diagonal dominance, orthogonality deviation, and Laplacian commutativity error for characterizing cross-modal representation compatibility. --- ### Structured Exploration and Exploitation of Label Functions for Automated Data Annotation Authors: Phong Lam, Ha-Linh Nguyen, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo Published: 2026-03-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08578v1 High-quality labeled data is critical for training reliable machine learning and deep learning models, yet manual annotation remains costly and error-prone. Programmatic labeling addresses this challenge by using label functions (LFs), i.e., heuristic rules that automatically generate weak labels for training datasets. However, existing automated LF generation methods either rely on large language models (LLMs) to synthesize surface-level heuristics or employ model-based synthesis over hand-crafted primitives. These approaches often result in limited coverage and unreliable label quality. In this paper, we introduce EXPONA, an automated framework for programmatic labeling that formulates LF generation as a principled process balancing diversity and reliability. EXPONA systematically explores multi-level LFs, spanning surface, structural, and semantic perspectives. EXPONA further applies reliability-aware mechanisms to suppress noisy or redundant heuristics while preserving complementary signals. To evaluate EXPONA, we conducted extensive experiments on eleven classification datasets across diverse domains. Experimental results show that EXPONA consistently outperformed state-of-the-art automated LF generation methods. Specifically, EXPONA achieved nearly complete label coverage (up to 98.9%), improved weak label quality by up to 87%, and yielded downstream performance gains of up to 46% in weighted F1. These results indicate that EXPONA's combination of multi-level LF exploration and reliability-aware filtering enabled more consistent label quality and downstream performance across diverse tasks by balancing coverage and precision in the generated LF set. --- ### Hybrid CNN-Transformer Architecture for Arabic Speech Emotion Recognition Authors: Youcef Soufiane Gheffari, Oussama Mustapha Benouddane, Samiya Silarbi Published: 2026-03-28 Categories: cs.CL, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2604.07357v1 Recognizing emotions from speech using machine learning has become an active research area due to its importance in building human-centered applications. However, while many studies have been conducted in English, German, and other European and Asian languages, research in Arabic remains scarce because of the limited availability of annotated datasets. In this paper, we present an Arabic Speech Emotion Recognition (SER) system based on a hybrid CNN-Transformer architecture. The model leverages convolutional layers to extract discriminative spectral features from Mel-spectrogram inputs and Transformer encoders to capture long-range temporal dependencies in speech. Experiments were conducted on the EYASE (Egyptian Arabic speech emotion) corpus, and the proposed model achieved 97.8% accuracy and a macro F1-score of 0.98. These results demonstrate the effectiveness of combining convolutional feature extraction with attention-based modeling for Arabic SER and highlight the potential of Transformer-based approaches in low-resource languages. --- ### Prediction Arena: Benchmarking AI Models on Real-World Prediction Markets Authors: Jaden Zhang, Gardenia Liu, Oliver Johansson, Hileamlak Yitayew, Kamryn Ohly, Grace Li Published: 2026-03-28 Categories: cs.LG, cs.AI, econ.GN arXiv: https://arxiv.org/abs/2604.07355v1 We introduce Prediction Arena, a benchmark for evaluating AI models' predictive accuracy and decision-making by enabling them to trade autonomously on live prediction markets with real capital. Unlike synthetic benchmarks, Prediction Arena tests models in environments where trades execute on actual exchanges (Kalshi and Polymarket), providing objective ground truth that cannot be gamed or overfitted. Each model operates as an independent agent starting with $10,000, making autonomous decisions every 15-45 minutes. Over a 57-day longitudinal evaluation (January 12 to March 9, 2026), we track two cohorts: six frontier models in live trading (Cohort 1, full period) and four next-generation models in paper trading (Cohort 2, 3-day preliminary). For Cohort 1, final Kalshi returns range from -16.0% to -30.8%. Our analysis identifies a clear performance hierarchy: initial prediction accuracy and the ability to capitalize on correct predictions are the main drivers, while research volume shows no correlation with outcomes. A striking cross-platform contrast emerges from parallel Polymarket live trading: Cohort 1 models averaged only -1.1% on Polymarket vs. -22.6% on Kalshi, with grok-4-20-checkpoint achieving a 71.4% settlement win rate - the highest across any platform or cohort. gemini-3.1-pro-preview (Cohort 2), which executed zero trades on Kalshi, achieved +6.02% on Polymarket in 3 days - the best return of any model across either cohort - demonstrating that platform design has a profound effect on which models succeed. Beyond performance, we analyze computational efficiency (token usage, cycle time), settlement accuracy, exit patterns, and market preferences, providing a comprehensive view of how frontier models behave under real financial pressure. --- ### Contextual Earnings-22: A Speech Recognition Benchmark with Custom Vocabulary in the Wild Authors: Berkin Durmus, Chen Cen, Eduardo Pacheco, Arda Okan, Atila Orhon Published: 2026-03-28 Categories: cs.CL, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2604.07354v1 The accuracy frontier of speech-to-text systems has plateaued on academic benchmarks.1 In contrast, industrial benchmarks and adoption in high-stakes domains suggest otherwise. We hypothesize that the primary difference between the two is contextual conditioning: Academic benchmarks are dominated by frequently encountered general vocabulary that is relatively easy to recognize compared with rare and context-defined custom vocabulary that has disproportionate impact on the usability of speech transcripts. Despite progress on contextual speech-to-text, there is no standardized benchmark. We introduce Contextual Earnings-22, an open dataset built upon Earnings-22, with realistic custom vocabulary contexts to foster research and reveal latent progress. We set six strong baselines for two dominant approaches: keyword prompting and keyword boosting. Experiments show both reach comparable and significantly improved accuracy when scaled from proof-of-concept to large-scale systems. --- ### Sparse Autoencoders as a Steering Basis for Phase Synchronization in Graph-Based CFD Surrogates Authors: Yeping Hu, Ruben Glatt, Shusen Liu Published: 2026-03-28 Categories: cs.CE, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2604.04946v1 Graph-based surrogate models provide fast alternatives to high-fidelity CFD solvers, but their opaque latent spaces and limited controllability restrict use in safety-critical settings. A key failure mode in oscillatory flows is phase drift, where predictions remain qualitatively correct but gradually lose temporal alignment with observations, limiting use in digital twins and closed-loop control. Correcting this through retraining is expensive and impractical during deployment. We ask whether phase drift can instead be corrected post hoc by manipulating the latent space of a frozen surrogate. We propose a phase-steering framework for pretrained graph-based CFD models that combines the right representation with the right intervention mechanism. To obtain disentangled representation for effective steering, we use sparse autoencoders (SAEs) on frozen MeshGraphNet embeddings. To steer dynamics, we move beyond static per-feature interventions such as scaling or clamping, and introduce a temporally coherent, phase-aware method. Specifically, we identify oscillatory feature pairs with Hilbert analysis, project spatial fields into low-rank temporal coefficients via SVD, and apply smooth time-varying rotations to advance or delay periodic modes while preserving amplitude-phase structure. Using a representation-agnostic setup, we compare SAE-based steering with PCA and raw embedding spaces under the same intervention pipeline. Results show that sparse, disentangled representations outperform dense or entangled ones, while static interventions fail in this dynamical setting. Overall, this work shows that latent-space steering can be extended from semantic domains to time-dependent physical systems when interventions respect the underlying dynamics, and that the same sparse features used for interpretability can also serve as physically meaningful control axes. --- ### ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs Authors: Jinwu Yang, Jiaan Wu, Zedong Liu, Xinyang Ma, Hairui Zhao, Yida Gu, Yuanhong Huang, Xingchen Liu, Wenjing Huang, Zheng Wei, Jing Xing, Yili Ma et al. Published: 2026-03-28 Categories: cs.AR, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2604.03298v2 The rapid scaling of Large Language Models presents significant challenges for their deployment and inference, particularly on resource-constrained specialized AI hardware accelerators such as Huawei's Ascend NPUs, where weight data transfer has become a critical performance bottleneck. While lossless compression can preserve model accuracy and reduce data volume, existing lossless compression algorithms exhibit extremely low throughput when ported to the Ascend NPU architecture. In this paper, we propose ENEC, a novel lossless compression method specifically customized for AI model weights and optimized for Ascend Neural Processing Units. ENEC adopts a block-based fixed-length encoding scheme and incorporates a series of NPU-specific optimizations: bit-width quantization with hierarchical halving bit-packing, vectorized branch-free integer transformation, and dependency-decoupled intra-segment scan for efficient prefix-sum computation. Experimental results demonstrate that ENEC outperforms existing state-of-the-art NPU compressors in both compression ratio and throughput. Compared to leading GPU solutions, ENEC achieves a 3.43X higher throughput than DietGPU and a 1.12X better compression ratio than nvCOMP. By reducing weight transmission overhead, ENEC significantly improves end-to-end inference performance, achieving up to a 6.3X speedup. On Ascend NPUs, ENEC is the first open-source lossless compression algorithm for model weights that achieves performance comparable to state-of-the-art GPU compressors, offering an effective solution for deploying large-scale AI models. --- ### XAttnRes: Cross-Stage Attention Residuals for Medical Image Segmentation Authors: Xinyu Liu, Qing Xu, Zhen Chen Published: 2026-03-28 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.03297v1 In the field of Large Language Models (LLMs), Attention Residuals have recently demonstrated that learned, selective aggregation over all preceding layer outputs can outperform fixed residual connections. We propose Cross-Stage Attention Residuals (XAttnRes), a mechanism that maintains a global feature history pool accumulating both encoder and decoder stage outputs. Through lightweight pseudo-query attention, each stage selectively aggregates from all preceding representations. To bridge the gap between the same-dimensional Transformer layers in LLMs and the multi-scale encoder-decoder stages in segmentation networks, XAttnRes introduces spatial alignment and channel projection steps that handle cross-resolution features with negligible overhead. When added to existing segmentation networks, XAttnRes consistently improves performance across four datasets and three imaging modalities. We further observe that XAttnRes alone, even without skip connections, achieves performance on par with the baseline, suggesting that learned aggregation can recover the inter-stage information flow traditionally provided by predetermined connections. --- ### 3D-IDE: 3D Implicit Depth Emergent Authors: Chushan Zhang, Ruihan Lu, Jinguang Tong, Yikai Wang, Hongdong Li Published: 2026-03-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.03296v1 Leveraging 3D information within Multimodal Large Language Models (MLLMs) has recently shown significant advantages for indoor scene understanding. However, existing methods, including those using explicit ground-truth 3D positional encoding and those grafting external 3D foundation models for implicit geometry, struggle with the trade-off in 2D-3D representation fusion, leading to suboptimal deployment. To this end, we propose 3D-Implicit Depth Emergence, a method that reframes 3D perception as an emergent property derived from geometric self-supervision rather than explicit encoding. Our core insight is the Implicit Geometric Emergence Principle: by strategically leveraging privileged geometric supervision through mechanisms like a fine-grained geometry validator and global representation constraints, we construct an information bottleneck. This bottleneck forces the model to maximize the mutual information between visual features and 3D structures, allowing 3D awareness to emerge naturally within a unified visual representation. Unlike existing approaches, our method enables 3D perception to emerge implicitly, disentangling features in dense regions and, crucially, eliminating depth and pose dependencies during inference with zero latency overhead. This paradigm shift from external grafting to implicit emergence represents a fundamental rethinking of 3D knowledge integration in visual-language models. Extensive experiments demonstrate that our method surpasses SOTA on multiple 3D scene understanding benchmarks. Our approach achieves a 55% reduction in inference latency while maintaining strong performance across diverse downstream tasks, underscoring the effectiveness of meticulously designed auxiliary objectives for dependency-free 3D understanding. Source code can be found at github.com/ChushanZhang/3D-IDE. --- ### GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models Authors: Md Jueal Mia, Joaquin Molto, Yanzhao Wu, M. Hadi Amini Published: 2026-03-28 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.28817v1 Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make SLMs suitable for resource-constrained and efficient deployment on edge devices. However, existing jailbreak defenses show limited robustness against heterogeneous attacks, largely due to an incomplete understanding of the internal representations across different layers of language models that facilitate jailbreak behaviors. In this paper, we conduct a comprehensive empirical study on 9 jailbreak attacks across 7 SLMs and 3 LLMs. Our analysis shows that SLMs remain highly vulnerable to malicious prompts that bypass safety alignment. We analyze hidden-layer activations across different layers and model architectures, revealing that different input types form distinguishable patterns in the internal representation space. Based on this observation, we propose GUARD-SLM, a lightweight token activation-based method that operates in the representation space to filter malicious prompts during inference while preserving benign ones. Our findings highlight robustness limitations across layers of language models and provide a practical direction for secure small language model deployment. --- ### ASTRA: Mapping Art-Technology Institutions via Conceptual Axes, Text Embeddings, and Unsupervised Clustering Authors: Joonhyung Bae Published: 2026-03-28 Categories: cs.DL, cs.AI arXiv: https://arxiv.org/abs/2603.28816v2 The global landscape of art-technology institutions, including festivals, biennials, research labs, conferences, and hybrid organizations, has grown increasingly diverse, yet systematic frameworks for analyzing their multidimensional characteristics remain scarce. This paper proposes ASTRA (Art-technology Institution Spatial Taxonomy and Relational Analysis), a computational methodology combining an eight-axis conceptual framework (Curatorial Philosophy, Territorial Relation, Knowledge Production Mode, Institutional Genealogy, Temporal Orientation, Ecosystem Function, Audience Relation, and Disciplinary Positioning) with a text-embedding and clustering pipeline to map 78 cultural-technology institutions into a unified analytical space. Each institution is characterized through qualitative descriptions along the eight axes, encoded via E5-large-v2 sentence embeddings and quantized through a word-level codebook into TF-IDF feature vectors. Dimensionality reduction using UMAP, followed by agglomerative clustering (Average linkage, k=10), yields a composite score of 0.825, a silhouette coefficient of 0.803, and a Calinski-Harabasz index of 11196. Non-negative matrix factorization extracts ten latent topics, and a neighbor-cluster entropy measure identifies boundary institutions bridging multiple thematic communities. An interactive React-based tool enables curators, researchers, and policymakers to explore institutional similarities and cross-disciplinary connections. Results reveal coherent groupings such as an art-science hub cluster anchored by ZKM and ArtScience Museum, an innovation and industry cluster including Ars Electronica, transmediale, and Sonar, an ACM academic cluster comprising TEI, DIS, and NIME, and an electronic music cluster including CTM Festival, MUTEK, and Sonic Acts. Code and data: https://github.com/joonhyungbae/astra --- ### SkillTester: Benchmarking Utility and Security of Agent Skills Authors: Leye Wang, Zixing Wang, Anjie Xu Published: 2026-03-28 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.28815v1 This technical report presents SkillTester, a tool for evaluating the utility and security of agent skills. Its evaluation framework combines paired baseline and with-skill execution conditions with a separate security probe suite. Grounded in a comparative utility principle and a user-facing simplicity principle, the framework normalizes raw execution artifacts into a utility score, a security score, and a three-level security status label. More broadly, it can be understood as a comparative quality-assurance harness for agent skills in an agent-first world. The public service is deployed at https://skilltester.ai, and the broader project is maintained at https://github.com/skilltester-ai/skilltester. --- ### The impact of multi-agent debate protocols on debate quality: a controlled case study Authors: Ramtin Zargari Marandi Published: 2026-03-28 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2603.28813v1 In multi-agent debate (MAD) systems, performance gains are often reported; however, because the debate protocol (e.g., number of agents, rounds, and aggregation rule) is typically held fixed while model-related factors vary, it is difficult to disentangle protocol effects from model effects. To isolate these effects, we compare three main protocols, Within-Round (WR; agents see only current-round contributions), Cross-Round (CR; full prior-round context), and novel Rank-Adaptive Cross-Round (RA-CR; dynamically reorders agents and silences one per round via an external judge model), against a No-Interaction baseline (NI; independent responses without peer visibility). In a controlled macroeconomic case study (20 diverse events, five random seeds, matched prompts/decoding), RA-CR achieves faster convergence than CR, WR shows higher peer-referencing, and NI maximizes Argument Diversity (unaffected across the main protocols). These results reveal a trade-off between interaction (peer-referencing rate) and convergence (consensus formation), confirming protocol design matters. When consensus is prioritized, RA-CR outperforms the others. --- ### Data-Driven Estimation of the interfacial Dzyaloshinskii-Moriya Interaction with Machine Learning Authors: Davi Rodrigues, Andrea Meo, Ali Hasan, Edoardo Piccolo, Adriano Di Pietro, Alessandro Magni, Marco Madami, Giovanni Finocchio, Mario Carpentieri, Michaela Kuepferling, Vito Puliafito Published: 2026-03-28 Categories: cond-mat.mtrl-sci, cond-mat.mes-hall, cs.LG arXiv: https://arxiv.org/abs/2603.28812v1 Machine learning offers powerful tools to support experimental techniques, particularly for extracting latent features from large datasets. In magnetic materials, accurately estimating the interfacial Dzyaloshinskii-Moriya interaction strength remains challenging, as existing experimental methods often rely on indirect measurements and can yield inconsistent results across techniques. Because this interaction is often extracted experimentally from bubble domain expansion, we investigate whether bubble textures alone contain sufficient and reliable information for data driven DMI inference. We therefore develop a compact convolutional neural network trained on a comprehensive micromagnetic dataset of magnetic bubble domains designed to emulate magneto optical Kerr effect imaging, including structural non uniformity, additive noise, and image pixelation. The proposed network demonstrates strong robustness against sample inhomogeneities, noise, and reduced spatial resolution. Furthermore, it exhibits reliable generalization by accurately predicting DMI values outside the trained interval. These results support the use of machine learning as a fast and quantitative tool to characterize magnetic textures with interfacial DMI. --- ### WAter: A Workload-Adaptive Knob Tuning System based on Workload Compression Authors: Yibo Wang, Jiale Lao, Chen Zhang, Cehua Yang, Jianguo Wang, Mingjie Tang Published: 2026-03-28 Categories: cs.DB, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.28809v1 Selecting appropriate values for the configurable parameters of Database Management Systems (DBMS) to improve performance is a significant challenge. Recent machine learning (ML)-based tuning systems have shown strong potential, but their practical adoption is often limited by the high tuning cost. This cost arises from two main factors: (1) the system needs to evaluate a large number of configurations to identify a satisfactory one, and (2) for each configuration, the system must execute the entire target workload on the DBMS, which is both time-consuming. Existing studies have primarily addressed the first factor by improving sample efficiency, that is, by reducing the number of configurations evaluated. However, the second factor, improving runtime efficiency by reducing the time required for each evaluation, has received limited attention and remains an underexplored direction. We develop WAter, a runtime-efficient and workload-adaptive tuning system that finds near-optimal configurations at a fraction of the tuning cost compared with state-of-the-art methods. We divide the tuning process into multiple time slices and evaluate only a small subset of queries from the workload in each slice. Different subsets are evaluated across slices, and a runtime profile is used to dynamically identify more representative subsets for evaluation in subsequent slices. At the end of each time slice, the most promising configurations are evaluated on the original workload to measure their actual performance. Evaluations demonstrate that WAter identifies the best-performing configurations with up to 73.5% less tuning time and achieves up to 16.2% higher performance than the best-performing alternative. --- ### LOME: Learning Human-Object Manipulation with Action-Conditioned Egocentric World Model Authors: Quankai Gao, Jiawei Yang, Qiangeng Xu, Le Chen, Yue Wang Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27449v1 Learning human-object manipulation presents significant challenges due to its fine-grained and contact-rich nature of the motions involved. Traditional physics-based animation requires extensive modeling and manual setup, and more importantly, it neither generalizes well across diverse object morphologies nor scales effectively to real-world environment. To address these limitations, we introduce LOME, an egocentric world model that can generate realistic human-object interactions as videos conditioned on an input image, a text prompt, and per-frame human actions, including both body poses and hand gestures. LOME injects strong and precise action guidance into object manipulation by jointly estimating spatial human actions and the environment contexts during training. After finetuning a pretrained video generative model on videos of diverse egocentric human-object interactions, LOME demonstrates not only high action-following accuracy and strong generalization to unseen scenarios, but also realistic physical consequences of hand-object interactions, e.g., liquid flowing from a bottle into a mug after executing a ``pouring'' action. Extensive experiments demonstrate that our video-based framework significantly outperforms state-of-the-art image based and video-based action-conditioned methods and Image/Text-to-Video (I/T2V) generative model in terms of both temporal consistency and motion control. LOME paves the way for photorealistic AR/VR experiences and scalable robotic training, without being limited to simulated environments or relying on explicit 3D/4D modeling. --- ### GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedback Authors: Giorgio Giannone, Anna Clare Doris, Amin Heyrani Nobari, Kai Xu, Akash Srivastava, Faez Ahmed Published: 2026-03-28 Categories: cs.LG, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2603.27448v1 Generating executable CAD programs from images requires alignment between visual geometry and symbolic program representations, a capability that current methods fail to learn reliably as design complexity increases. Existing fine-tuning approaches rely on either limited supervised datasets or expensive post-training pipelines, resulting in brittle systems that restrict progress in generative CAD design. We argue that the primary bottleneck lies not in model or algorithmic capacity, but in the scarcity of diverse training examples that align visual geometry with program syntax. This limitation is especially acute because the collection of diverse and verified engineering datasets is both expensive and difficult to scale, constraining the development of robust generative CAD models. We introduce Geometric Inference Feedback Tuning (GIFT), a data augmentation framework that leverages geometric feedback to turn test-time compute into a bootstrapped set of high-quality training samples. GIFT combines two mechanisms: Soft-Rejection Sampling (GIFT-REJECT), which retains diverse high-fidelity programs beyond exact ground-truth matches, and Failure-Driven Augmentation (GIFT-FAIL), which converts near-miss predictions into synthetic training examples that improve robustness on challenging geometries. By amortizing inference-time search into the model parameters, GIFT captures the benefits of test-time scaling while reducing inference compute by 80%. It improves mean IoU by 12% over a strong supervised baseline and remains competitive with more complex multimodal systems, without requiring additional human annotation or specialized architectures. --- ### Interpretable Physics Extraction from Data for Linear Dynamical Systems using Lie Generator Networks Authors: Shafayeth Jamil, Rehan Kapadia Published: 2026-03-28 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.27442v1 When the system is linear, why should learning be nonlinear? Linear dynamical systems, the analytical backbone of control theory, signal processing and circuit analysis, have exact closed-form solutions via the state transition matrix. Yet when system parameters must be inferred from data, recent neural approaches offer flexibility at the cost of physical guarantees: Neural ODEs provide flexible trajectory approximation but may violate physical invariants, while energy preserving architectures do not natively represent dissipation essential to real-world systems. We introduce Lie Generator Networks (LGN), which learn a structured generator A and compute trajectories directly via matrix exponentiation. This shift from integration to exponentiation preserves structure by construction. By parameterizing A = S - D (skew-symmetric minus positive diagonal), stability and dissipation emerge from the underlying architecture and are not introduced during training via the loss function. LGN provides a unified framework for linear conservative, dissipative, and time-varying systems. On a 100-dimensional stable RLC ladder, standard derivative-based least-squares system identification can yield unstable eigenvalues. The unconstrained LGN yields stable but physically incorrect spectra, whereas LGN-SD recovers all 100 eigenvalues with over two orders of magnitude lower mean eigenvalue error than unconstrained alternatives. Critically, these eigenvalues reveal poles, natural frequencies, and damping ratios which are interpretable physics that black-box networks do not provide. --- ### Evaluating Large and Lightweight Vision Models for Irregular Component Segmentation in E-Waste Disassembly Authors: Xinyao Zhang, Chang Liu, Xiao Liang, Minghui Zheng, Sara Behdad Published: 2026-03-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.27441v1 Precise segmentation of irregular and densely arranged components is essential for robotic disassembly and material recovery in electronic waste (e-waste) recycling. This study evaluates the impact of model architecture and scale on segmentation performance by comparing SAM2, a transformer-based vision model, with the lightweight YOLOv8 network. Both models were trained and tested on a newly collected dataset of 1,456 annotated RGB images of laptop components including logic boards, heat sinks, and fans, captured under varying illumination and orientation conditions. Data augmentation techniques, such as random rotation, flipping, and cropping, were applied to improve model robustness. YOLOv8 achieved higher segmentation accuracy (mAP50 = 98.8%, mAP50-95 = 85%) and stronger boundary precision than SAM2 (mAP50 = 8.4%). SAM2 demonstrated flexibility in representing diverse object structures but often produced overlapping masks and inconsistent contours. These findings show that large pre-trained models require task-specific optimization for industrial applications. The resulting dataset and benchmarking framework provide a foundation for developing scalable vision algorithms for robotic e-waste disassembly and circular manufacturing systems. --- ### The Novelty Bottleneck: A Framework for Understanding Human Effort Scaling in AI-Assisted Work Authors: Jacky Liang Published: 2026-03-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.27438v1 We propose a stylized model of human-AI collaboration that isolates a mechanism we call the novelty bottleneck: the fraction of a task requiring human judgment creates an irreducible serial component analogous to Amdahl's Law in parallel computing. The model assumes that tasks decompose into atomic decisions, a fraction $ν$ of which are "novel" (not covered by the agent's prior), and that specification, verification, and error correction each scale with task size. From these assumptions, we derive several non-obvious consequences: (1) there is no smooth sublinear regime for human effort it transitions sharply from $O(E)$ to $O(1)$ with no intermediate scaling class; (2) better agents improve the coefficient on human effort but not the exponent; (3) for organizations of n humans with AI agents, optimal team size decreases with agent capability; (4) wall-clock time achieves $O(\sqrt{E})$ through team parallelism but total human effort remains $O(E)$; and (5) the resulting AI safety profile is asymmetric -- AI is bottlenecked on frontier research but unbottlenecked on exploiting existing knowledge. We show these predictions are consistent with empirical observations from AI coding benchmarks, scientific productivity data, and practitioner reports. Our contribution is not a proof that human effort must scale linearly, but a framework that identifies the novelty fraction as the key parameter governing AI-assisted productivity, and derives consequences that clarify -- rather than refute -- prevalent narratives about intelligence explosions and the "country of geniuses in a data center." --- ### SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning Authors: Jian Zhang, Shijie Zhou, Bangya Liu, Achuta Kadambi, Zhiwen Fan Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27437v3 Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-grained 3D geometry and spatial relationships. While recent efforts have introduced multi-view geometry transformers into VLMs, they typically fuse only the deep-layer features from vision and geometry encoders, discarding rich hierarchical signals and creating a fundamental bottleneck for spatial understanding. To overcome this, we propose SpatialStack, a general hierarchical fusion framework that progressively aligns vision, geometry, and language representations across the model hierarchy. Moving beyond conventional late-stage vision-geometry fusion, SpatialStack stacks and synchronizes multi-level geometric features with the language backbone, enabling the model to capture both local geometric precision and global contextual semantics. Building upon this framework, we develop VLM-SpatialStack, a model that achieves state-of-the-art performance on multiple 3D spatial reasoning benchmarks. Extensive experiments and ablations demonstrate that our multi-level fusion strategy consistently enhances 3D understanding and generalizes robustly across diverse spatial reasoning tasks, establishing SpatialStack as an effective and extensible design paradigm for vision-language-geometry integration in next-generation multimodal physical AI systems. --- ### Improving Attributed Long-form Question Answering with Intent Awareness Authors: Xinran Zhao, Aakanksha Naik, Jay DeYoung, Joseph Chee Chang, Jena D. Hwang, Tongshuang Wu, Varsha Kishore Published: 2026-03-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.27435v2 Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers and reports, they are not exposed to the reasoning processes and intents that guide authors in crafting these documents. We hypothesize that enhancing a model's intent awareness can significantly improve the quality of generated long-form reports. We develop and employ structured, tag-based schemes to better elicit underlying implicit intents to write or cite. We demonstrate that these extracted intents enhance both zero-shot generation capabilities in LLMs and enable the creation of high-quality synthetic data for fine-tuning smaller models. Our experiments reveal improved performance across various challenging scientific report generation tasks, with an average improvement of +2.9 and +12.3 absolute points for large and small models over baselines, respectively. Furthermore, our analysis illuminates how intent awareness enhances model citation usage and substantially improves report readability. --- ### Improving Attributed Long-form Question Answering with Intent Awareness Authors: Xinran Zhao, Aakanksha Naik, Jay DeYoung, Joseph Chee Chang, Jena D. Hwang, Tongshuang Wu, Varsha Kishore Published: 2026-03-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.27435v1 Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers and reports, they are not exposed to the reasoning processes and intents that guide authors in crafting these documents. We hypothesize that enhancing a model's intent awareness can significantly improve the quality of generated long-form reports. We develop and employ structured, tag-based schemes to better elicit underlying implicit intents to write or cite. We demonstrate that these extracted intents enhance both zero-shot generation capabilities in LLMs and enable the creation of high-quality synthetic data for fine-tuning smaller models. Our experiments reveal improved performance across various challenging scientific report generation tasks, with an average improvement of +2.9 and +12.3 absolute points for large and small models over baselines, respectively. Furthermore, our analysis illuminates how intent awareness enhances model citation usage and substantially improves report readability. --- ### The Geometric Cost of Normalization: Affine Bounds on the Bayesian Complexity of Neural Networks Authors: Sungbae Chun Published: 2026-03-28 Categories: cs.LG, cs.IT arXiv: https://arxiv.org/abs/2603.27432v1 LayerNorm and RMSNorm impose fundamentally different geometric constraints on their outputs - and this difference has a precise, quantifiable consequence for model complexity. We prove that LayerNorm's mean-centering step, by confining data to a linear hyperplane (through the origin), reduces the Local Learning Coefficient (LLC) of the subsequent weight matrix by exactly $m/2$ (where $m$ is its output dimension); RMSNorm's projection onto a sphere preserves the LLC entirely. This reduction is structurally guaranteed before any training begins, determined by data manifold geometry alone. The underlying condition is a geometric threshold: for the codimension-one manifolds we study, the LLC drop is binary -- any non-zero curvature, regardless of sign or magnitude, is sufficient to preserve the LLC, while only affinely flat manifolds cause the drop. At finite sample sizes this threshold acquires a smooth crossover whose width depends on how much of the data distribution actually experiences the curvature, not merely on whether curvature exists somewhere. We verify both predictions experimentally with controlled single-layer scaling experiments using the wrLLC framework. We further show that Softmax simplex data introduces a "smuggled bias" that activates the same $m/2$ LLC drop when paired with an explicit downstream bias, proved via the affine symmetry extension of the main theorem and confirmed empirically. --- ### Mind the Shape Gap: A Benchmark and Baseline for Deformation-Aware 6D Pose Estimation of Agricultural Produce Authors: Nikolas Chatzis, Angeliki Tsinouka, Katerina Papadimitriou, Niki Efthymiou, Marios Glytsos, George Retsinas, Paris Oikonomou, Gerasimos Potamianos, Petros Maragos, Panagiotis Paraskevas Filntisis Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27429v1 Accurate 6D pose estimation for robotic harvesting is fundamentally hindered by the biological deformability and high intra-class shape variability of agricultural produce. Instance-level methods fail in this setting, as obtaining exact 3D models for every unique piece of produce is practically infeasible, while category-level approaches that rely on a fixed template suffer significant accuracy degradation when the prior deviates from the true instance geometry. To bridge such lack of robustness to deformation, we introduce PEAR (Pose and dEformation of Agricultural pRoduce), the first benchmark providing joint 6D pose and per-instance 3D deformation ground truth across 8 produce categories, acquired via a robotic manipulator for high annotation accuracy. Using PEAR, we show that state-of-the-art methods suffer up to 6x performance degradation when faced with the inherent geometric deviations of real-world produce. Motivated by this finding, we propose SEED (Simultaneous Estimation of posE and Deformation), a unified RGB-only framework that jointly predicts 6D pose and explicit lattice deformations from a single image across multiple produce categories. Trained entirely on synthetic data with generative texture augmentation applied at the UV level, SEED outperforms MegaPose on 6 out of 8 categories under identical RGB-only conditions, demonstrating that explicit shape modeling is a critical step toward reliable pose estimation in agricultural robotics. --- ### AstraAI: LLMs, Retrieval, and AST-Guided Assistance for HPC Codebases Authors: Mahesh Natarajan, Xiaoye Li, Weiqun Zhang Published: 2026-03-28 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.27423v1 We present AstraAI, a command-line interface (CLI) coding framework for high-performance computing (HPC) software development. AstraAI operates directly within a Linux terminal and integrates large language models (LLMs) with Retrieval-Augmented Generation (RAG) and Abstract Syntax Tree (AST)-based structural analysis to enable context-aware code generation for complex scientific codebases. The central idea is to construct a high-fidelity prompt that is passed to the LLM for inference. This prompt augments the user request with relevant code snippets retrieved from the underlying framework codebase via RAG and structural context extracted from AST analysis, providing the model with precise information about relevant functions, data structures, and overall code organization. The framework is designed to perform scoped modifications to source code while preserving structural consistency with the surrounding code. AstraAI supports both locally hosted models from Hugging Face and API-based frontier models accessible via the American Science Cloud, enabling flexible deployment across HPC environments. The system generates code that aligns with existing project structures and programming patterns. We demonstrate AstraAI on representative HPC code generation tasks within AMReX, a DOE-supported HPC software infrastructure for exascale applications. --- ### CarbonEdge: Carbon-Aware Deep Learning Inference Framework for Sustainable Edge Computing Authors: Guilin Zhang, Wulan Guo, Ziqi Tan, Chuanyi Sun, Hailong Jiang Published: 2026-03-28 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.27420v2 Deep learning applications at the network edge lead to a significant growth in AI-related carbon emissions, presenting a critical sustainability challenge. The existing edge computing frameworks optimize for latency and throughput, but they largely ignore the environmental impact of inference workloads. This paper introduces CarbonEdge, a carbon-aware deep learning inference framework that extends adaptive model partitioning with carbon footprint estimation and green scheduling apabilities. We propose a carbon-aware scheduling algorithm that extends traditional weighted scoring with a carbon efficiency metric, supporting a tunable performance--carbon trade-off (demonstrated via weight sweep). Experimental evaluations on Docker-simulated heterogeneous edge environments show that CarbonEdge-Green mode achieves a 22.9% reduction in carbon emissions compared to monolithic execution. The framework achieves 1.3x improvement in carbon efficiency (245.8 vs 189.5 inferences per gram CO2) with negligible scheduling overhead (0.03ms per task). These results highlight the framework's potential for sustainable edge AI deployment, providing researchers and practitioners a tool to quantify and minimize the environmental footprint of distributed deep learning inference. --- ### Kempe Swap K-Means: A Scalable Near-Optimal Solution for Semi-Supervised Clustering Authors: Yuxuan Ren, Shijie Deng Published: 2026-03-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.27417v1 This paper presents a novel centroid-based heuristic algorithm, termed Kempe Swap K-Means, for constrained clustering under rigid must-link (ML) and cannot-link (CL) constraints. The algorithm employs a dual-phase iterative process: an assignment step that utilizes Kempe chain swaps to refine current clustering in the constrained solution space and a centroid update step that computes optimal cluster centroids. To enhance global search capabilities and avoid local optima, the framework incorporates controlled perturbations during the update phase. Empirical evaluations demonstrate that the proposed method achieves near-optimal partitions while maintaining high computational efficiency and scalability. The results indicate that Kempe Swap K-Means consistently outperforms state-of-the-art benchmarks in both clustering accuracy and algorithmic efficiency for large-scale datasets. --- ### Agent-Driven Autonomous Reinforcement Learning Research: Iterative Policy Improvement for Quadruped Locomotion Authors: Nimesh Khandelwal, Shakti S. Gupta Published: 2026-03-28 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.27416v1 This paper documents a case study in agent-driven autonomous reinforcement learning research for quadruped locomotion. The setting was not a fully self-starting research system. A human provided high-level directives through an agentic coding environment, while an agent carried out most of the execution loop: reading code, diagnosing failures, editing reward and terrain configurations, launching and monitoring jobs, analyzing intermediate metrics, and proposing the next wave of experiments. Across more than 70 experiments organized into fourteen waves on a DHAV1 12-DoF quadruped in Isaac Lab, the agent progressed from early rough-terrain runs with mean reward around 7 to a best logged Wave 12 run, exp063, with velocity error 0.263 and 97\% timeout over 2000 iterations, independently reproduced five times across different GPUs. The archive also records several concrete autonomous research decisions: isolating PhysX deadlocks to terrain sets containing boxes and stair-like primitives, porting four reward terms from openly available reference implementations \cite{deeprobotics, rlsar}, correcting Isaac Sim import and bootstrapping issues, reducing environment count for diagnosis, terminating hung runs, and pivoting effort away from HIM after repeated terrain=0.0 outcomes. Relative to the AutoResearch paradigm \cite{autoresearch}, this case study operates in a more failure-prone robotics RL setting with multi-GPU experiment management and simulator-specific engineering constraints. The contribution is empirical and documentary: it shows that an agent can materially execute the iterative RL research loop in this domain with limited human intervention, while also making clear where human direction still shaped the agenda. --- ### Greedy Is a Strong Default: Agents as Iterative Optimizers Authors: Yitao Li Published: 2026-03-28 Categories: cs.AI, stat.CO arXiv: https://arxiv.org/abs/2603.27415v1 Classical optimization algorithms--hill climbing, simulated annealing, population-based methods--generate candidate solutions via random perturbations. We replace the random proposal generator with an LLM agent that reasons about evaluation diagnostics to propose informed candidates, and ask: does the classical optimization machinery still help when the proposer is no longer random? We evaluate on four tasks spanning discrete, mixed, and continuous search spaces (all replicated across 3 independent runs): rule-based classification on Breast Cancer (test accuracy 86.0% to 96.5%), mixed hyperparameter optimization for MobileNetV3-Small on STL-10 (84.5% to 85.8%, zero catastrophic failures vs. 60% for random search), LoRA fine-tuning of Qwen2.5-0.5B on SST-2 (89.5% to 92.7%, matching Optuna TPE with 2x efficiency), and XGBoost on Adult Census (AUC 0.9297 to 0.9317, tying CMA-ES with 3x fewer evaluations). Empirically, on these tasks: a cross-task ablation shows that simulated annealing, parallel investigators, and even a second LLM model (OpenAI Codex) provide no benefit over greedy hill climbing while requiring 2-3x more evaluations. In our setting, the LLM's learned prior appears strong enough that acceptance-rule sophistication has limited impact--round 1 alone delivers the majority of improvement, and variants converge to similar configurations across strategies. The practical implication is surprising simplicity: greedy hill climbing with early stopping is a strong default. Beyond accuracy, the framework produces human-interpretable artifacts--the discovered cancer classification rules independently recapitulate established cytopathology principles. --- ### Multiple-Prediction-Powered Inference Authors: Charlie Cowen-Breen, Alekh Agarwal, Stephen Bates, William W. Cohen, Jacob Eisenstein, Amir Globerson, Adam Fisch Published: 2026-03-28 Categories: math.ST, cs.AI arXiv: https://arxiv.org/abs/2603.27414v1 Statistical estimation often involves tradeoffs between expensive, high-quality measurements and a variety of lower-quality proxies. We introduce Multiple-Prediction-Powered Inference (MultiPPI): a general framework for constructing statistically efficient estimates by optimally allocating resources across these diverse data sources. This work provides theoretical guarantees about the minimax optimality, finite-sample performance, and asymptotic normality of the MultiPPI estimator. Through experiments across three diverse large language model (LLM) evaluation scenarios, we show that MultiPPI consistently achieves lower estimation error than existing baselines. This advantage stems from its budget-adaptive allocation strategy, which strategically combines subsets of models by learning their complex cost and correlation structures. --- ### The Hidden Costs of AI-Mediated Political Outreach: Persuasion and AI Penalties in the US and UK Authors: Andreas Jungherr, Adrian Rauchfleisch Published: 2026-03-28 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.27413v1 As AI-enabled systems become available for political campaign outreach, an important question has received little empirical attention: how do people evaluate the communicative practices these systems represent, and what consequences do those evaluations carry? Most research on AI-enabled persuasion examines attitude change under enforced exposure, leaving aside whether people regard AI-mediated outreach as legitimate or not. We address this gap with a preregistered 2x2 experiment conducted in the United States and United Kingdom (N = 1,800 per country) varying outreach intent (informational vs.~persuasive) and type of interaction partner (human vs.~AI-mediated) in the context of political issues that respondents consider highly important. We find consistent evidence for two evaluation penalties. A persuasion penalty emerges across nearly all outcomes in both countries: explicitly persuasive outreach is evaluated as less acceptable, more threatening to personal autonomy, less beneficial, and more damaging to organizational trust than informational outreach, consistent with reactance to perceived threats to attitudinal freedom. An AI penalty is consistent with a distinct mechanism: AI-mediated outreach triggers normative concerns about appropriate communicative agents, producing similarly negative evaluations across five outcomes in both countries. As automated outreach becomes more widespread, how people judge it may matter for democratic communication just as much as whether it changes minds. --- ### The Geometry of Harmful Intent: Training-Free Anomaly Detection via Angular Deviation in LLM Residual Streams Authors: Isaac Llorente-Saguer Published: 2026-03-28 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.27412v1 We present LatentBiopsy, a training-free method for detecting harmful prompts by analysing the geometry of residual-stream activations in large language models. Given 200 safe normative prompts, LatentBiopsy computes the leading principal component of their activations at a target layer and characterises new prompts by their radial deviation angle $θ$ from this reference direction. The anomaly score is the negative log-likelihood of $θ$ under a Gaussian fit to the normative distribution, flagging deviations symmetrically regardless of orientation. No harmful examples are required for training. We evaluate two complete model triplets from the Qwen3.5-0.8B and Qwen2.5-0.5B families: base, instruction-tuned, and \emph{abliterated} (refusal direction surgically removed via orthogonalisation). Across all six variants, LatentBiopsy achieves AUROC $\geq$0.937 for harmful-vs-normative detection and AUROC = 1.000 for discriminating harmful from benign-aggressive prompts (XSTest), with sub-millisecond per-query overhead. Three empirical findings emerge. First, geometry survives refusal ablation: both abliterated variants achieve AUROC at most 0.015 below their instruction-tuned counterparts, establishing a geometric dissociation between harmful-intent representation and the downstream generative refusal mechanism. Second, harmful prompts exhibit a near-degenerate angular distribution ($σ_θ\approx 0.03$ rad), an order of magnitude tighter than the normative distribution ($σ_θ\approx 0.27$ rad), preserved across all alignment stages including abliteration. Third, the two families exhibit opposite ring orientations at the same depth: harmful prompts occupy the outer ring in Qwen3.5-0.8B but the inner ring in Qwen2.5-0.5B, directly motivating the direction-agnostic scoring rule. --- ### Grounding Social Perception in Intuitive Physics Authors: Lance Ying, Aydan Y. Huang, Aviv Netanyahu, Andrei Barbu, Boris Katz, Joshua B. Tenenbaum, Tianmin Shu Published: 2026-03-28 Categories: q-bio.NC, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.27410v1 People infer rich social information from others' actions. These inferences are often constrained by the physical world: what agents can do, what obstacles permit, and how the physical actions of agents causally change an environment and other agents' mental states and behavior. We propose that such rich social perception is more than visual pattern matching, but rather a reasoning process grounded in an integration of intuitive psychology with intuitive physics. To test this hypothesis, we introduced PHASE (PHysically grounded Abstract Social Events), a large dataset of procedurally generated animations, depicting physically simulated two-agent interactions on a 2D surface. Each animation follows the style of the Heider and Simmel movie, with systematic variation in environment geometry, object dynamics, agent capacities, goals, and relationships (friendly/adversarial/neutral). We then present a computational model, SIMPLE, a physics-grounded Bayesian inverse planning model that integrates planning, probabilistic planning, and physics simulation to infer agents' goals and relations from their trajectories. Our experimental results showed that SIMPLE achieved high accuracy and agreement with human judgments across diverse scenarios, while feedforward baseline models -- including strong vision-language models -- and physics-agnostic inverse planning failed to achieve human-level performance and did not align with human judgments. These results suggest that our model provides a computational account for how people understand physically grounded social scenes by inverting a generative model of physics and agents. --- ### On the Relationship between Bayesian Networks and Probabilistic Structural Causal Models Authors: Peter J. F. Lucas, Eleonora Zullo, Fabio Stella Published: 2026-03-28 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.27406v2 In this paper, the relationship between probabilistic graphical models, in particular Bayesian networks, and causal diagrams, also called structural causal models, is studied. Structural causal models are deterministic models, based on structural equations or functions, that can be provided with uncertainty by adding independent, unobserved random variables to the models, equipped with probability distributions. One question that arises is whether a Bayesian network that has obtained from expert knowledge or learnt from data can be mapped to a probabilistic structural causal model, and whether or not this has consequences for the network structure and probability distribution. We show that linear algebra and linear programming offer key methods for the transformation, and examine properties for the existence and uniqueness of solutions based on dimensions of the probabilistic structural model. Finally, we examine in what way the semantics of the models is affected by this transformation. Keywords: Causality, probabilistic structural causal models, Bayesian networks, linear algebra, experimental software. --- ### Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring Authors: Jakub Masłowski, Jarosław A. Chudziak Published: 2026-03-28 Categories: cs.AI, cs.CL, cs.CY, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2603.27404v1 Large Language Models (LLMs) are being increasingly used as autonomous agents in complex reasoning tasks, opening the niche for dialectical interactions. However, Multi-Agent systems implemented with systematically unconstrained systems systematically undergo semantic drift and logical deterioration and thus can hardly be used in providing ethical tutoring where a precise answer is required. Current simulation often tends to degenerate into dialectical stagnation, the agents degenerate into recursive concurrence or circular arguments. A critical challenge remains: how to enforce doctrinal fidelity without suppressing the generative flexibility required for dialectical reasoning? To address this niche, we contribute the Heterogeneous Debate Engine (HDE), a cognitive architecture that combines Identity-Grounded Retrieval-Augmented Generation (ID-RAG) for doctrinal fidelity and Heuristic Theory of Mind for strategic opponent modeling. Our evaluation shows that architectural heterogeneity is a crucial variable to stability: contrary doctrinal initializations (e.g., Deontology vs. Utilitarianism) have increased the Argument Complexity Scores of students by an order of magnitude, over baselines. These findings validate the effectiveness of ID-RAG and Heuristic ToM as architectural requirements in maintaining high-fidelity (adversarial) pedagogy. --- ### Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling Authors: Kai Ye, Qingtao Pan, Shuo Li Published: 2026-03-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.27403v1 Large language models (LLMs) need reliable test-time control of hallucinations. Existing conformal methods for LLMs typically provide only \emph{marginal} guarantees and rely on a single global threshold, which can under-cover hard prompts, over-cover easy ones, and produce oversized prediction sets. We propose \emph{Conditional Factuality Control} (CFC), a post-hoc conformal framework that returns \emph{set-valued} outputs with \emph{conditional} coverage guarantees. CFC defines a continuous, feature-conditional acceptance threshold through augmented quantile regression on a latent ``success'' score, and deploys it through a fixed-point threshold rule at inference time. Theoretically, we show that CFC satisfies a conditional coverage guarantee under exchangeability and analyze its \emph{efficiency}, proving that, under mild assumptions on the score distributions, the conditional rule is strictly more sample-efficient than marginal conformal prediction at the same target coverage. We further derive a PAC-style variant, CFC-PAC, which shrinks the nominal risk level based on a stability bound, yielding a finite-sample certificate that the conditional miscoverage deviates from the target by at most $O(\sqrt{\log(1/δ)/N})$. Empirically, on synthetic data, real-world reasoning and QA benchmarks, and a Flickr8k VLM setting, CFC and CFC-PAC consistently attain near-target coverage across difficulty groups while using smaller prediction sets than CP and non-CP baselines. --- ### Rainbow-DemoRL: Combining Improvements in Demonstration-Augmented Reinforcement Learning Authors: Dwait Bhatt, Shih-Chieh Chou, Nikolay Atanasov Published: 2026-03-28 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2603.27400v1 Several approaches have been proposed to improve the sample efficiency of online reinforcement learning (RL) by leveraging demonstrations collected offline. The offline data can be used directly as transitions to optimize RL objectives, or offline policy and value functions can first be learned from the data and then used for online finetuning or to provide reference actions. While each of these strategies has shown compelling results, it is unclear which method has the most impact on sample efficiency, whether these approaches can be combined, and if there are cumulative benefits. We classify existing demonstration-augmented RL approaches into three categories and perform an extensive empirical study of their strengths, weaknesses, and combinations to isolate the contribution of each strategy and determine effective hybrid combinations for sample-efficient online RL. Our analysis reveals that directly reusing offline data and initializing with behavior cloning consistently outperform more complex offline RL pretraining methods for improving online sample efficiency. --- ### Topological Detection of Hopf Bifurcations via Persistent Homology: A Functional Criterion from Time Series Authors: Jhonathan Barrios, Yásser Echávez, Carlos F. Álvarez Published: 2026-03-28 Categories: math.DS, math.AT, stat.ML arXiv: https://arxiv.org/abs/2603.27395v2 We propose a topological framework for detecting Hopf-type dynamical transitions directly from scalar time series. The method combines delay-coordinate reconstruction with persistent homology and uses the maximum persistence of one-dimensional homology classes as a scalar descriptor of cyclic structure. For the supercritical Hopf setting, we derive finite-resolution persistence bounds that relate detectability of the reconstructed periodic orbit to its geometry, sampling quality, and finite-data perturbations. A derivative-based estimator is then introduced to localize the critical parameter from the sampled topological functional. The approach is evaluated on the Hopf normal form, the Lorenz system, and a reduced Belousov--Zhabotinsky model. The numerical experiments show accurate finite-resolution localization of the corresponding transitions and illustrate the effects of embedding parameters, temporal sampling, smoothing, observational noise, and transient removal. These results support persistent homology as an interpretable data-driven tool for detecting geometric reorganizations in nonlinear time series. --- ### Topological Detection of Hopf Bifurcations via Persistent Homology: A Functional Criterion from Time Series Authors: Jhonathan Barrios, Yásser Echávez, Carlos F. Álvarez Published: 2026-03-28 Categories: math.DS, math.AT, stat.ML arXiv: https://arxiv.org/abs/2603.27395v1 We propose a topological framework for the detection of Hopf bifurcations directly from time series, based on persistent homology applied to phase space reconstructions via Takens embedding within the framework of Topological Data Analysis. The central idea is that changes in the dynamical regime are reflected in the emergence or disappearance of a dominant one-dimensional homological features in the reconstructed attractor. To quantify this behavior, we introduce a simple and interpretable scalar topological functional defined as the maximum persistence of homology classes in dimension one. This functional is used to construct a computable criterion for identifying critical parameters in families of dynamical systems without requiring knowledge of the underlying equations. The proposed approach is validated on representative systems of increasing complexity, showing consistent detection of the bifurcation point. The results support the interpretation of dynamical transitions as topological phase transitions and demonstrate the potential of topological data analysis as a model-free tool for the quantitative analysis of nonlinear time series. --- ### K-Means Based TinyML Anomaly Detection and Distributed Model Reuse via the Distributed Internet of Learning (DIoL) Authors: Abdulrahman Albaiz, Fathi Amsaad Published: 2026-03-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.27393v1 This paper presents a lightweight K-Means anomaly detection model and a distributed model-sharing workflow designed for resource-constrained microcontrollers (MCUs). Using real power measurements from a mini-fridge appliance, the system performs on-device feature extraction, clustering, and threshold estimation to identify abnormal appliance behavior. To avoid retraining models on every device, we introduce the Distributed Internet of Learning (DIoL), which enables a model trained on one MCU to be exported as a portable, text-based representation and reused directly on other devices. A two-device prototype demonstrates the feasibility of the "Train Once, Share Everywhere" (TOSE) approach using a real-world appliance case study, where Device A trains the model and Device B performs inference without retraining. Experimental results show consistent anomaly detection behavior, negligible parsing overhead, and identical inference runtimes between standalone and DIoL-based operation. The proposed framework enables scalable, low-cost TinyML deployment across fleets of embedded devices. ---