# Research Papers — 2026-04 · bundle page 42 of 233

> Full-text markdown of papers #2051–2100 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/42
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/41.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/43.md)

### A Dynamic Learning Observatory Reveals the Rapid Salinization of Satkhira, Bangladesh

Authors: Showmitra Kumar Sarkar, Sai Ravela
Published: 2026-04-25
Categories: physics.geo-ph, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2604.23127v1

Soil salinity is a major environmental challenge in coastal Bangladesh, threatening agricultural productivity and local livelihoods. This study develops a machine-learning-based framework to predict and map soil salinity in Satkhira district by integrating field observations with Landsat-derived spectral indices. A total of 205 soil samples collected during 2024-2025 were used to train an Extreme Gradient Boosting (XGBoost) model, and predictions were further improved using a Generalized Additive Model (GAM). Spatial cross-validation was applied to reduce autocorrelation bias, and bootstrap resampling was used to quantify prediction uncertainty. The results show strong spatial variability of soil salinity, with higher concentrations in the southern and central coastal regions and lower levels in the northern inland areas. Vegetation indices, particularly NDVI, along with salinity-related spectral indicators, were identified as key predictors. 10-year-window peak-exposure maps generated for 2014-2023 reveal recurrent high-salinity zones and a persistent, expanding footprint of moderate-to-high salinity exposure across the central parts of the district. Uncertainty analysis indicates higher variability in coastal zones and improved prediction stability when multi-year datasets are combined. The proposed framework provides a robust and scalable approach for long-term monitoring of soil salinity. It supports climate-resilient agriculture, land-use planning, and evidence-based decision-making in coastal Bangladesh.

---

### Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label

Authors: Mengke Li, Haiquan Ling, Yiqun Zhang, Yang Lu, Hui Huang
Published: 2026-04-25
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2604.23125v1

Real-world data often exhibit long-tailed distributions with numerous noisy labels, substantially degrading the performance of deep models. While prior research has made progress in addressing this combined challenge, it overlooks the severe label-image mismatch inherent to high-noise settings, thereby limiting their effectiveness. Given that observed labels, though mismatched with images, still retain category information, we propose employing auxiliary text information from labels to address label-image inconsistencies in long-tailed noisy data. Specifically, we leverage the intrinsic cross-modal alignment in pre-trained visual-language models to correct the label-image inconsistencies. This supervisory signal, referred to as Weak Teacher Supervision (WTS), is unaffected by label noise and data distribution biases, albeit exhibits limited accuracy. Therefore, the activation of WTS is determined by evaluating the discrepancy between text-predicted labels and observed labels. Extensive experiments demonstrate the superior performance of WTS across synthetic and real-world datasets, particularly under high-noise conditions. The source code is available at https://anonymous.4open.science/r/WTS-0F3C.

---

### ArgRE: Formal Argumentation for Conflict Resolution in Multi-Agent Requirements Negotiation

Authors: Haowei Cheng, Milhan Kim, Chong Liu, Teeradaj Racharak, Truong Vinh Truong Duy, Phan Thi Huyen Thanh, Jialong Li, Naoyasu Ubayashi, Hironori Washizaki
Published: 2026-04-25
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2604.23124v1

As software systems grow in complexity, they must satisfy an increasing number of competing quality attributes, making it essential to balance them in a principled manner -- for example, a safety requirement for sensor-fusion verification may conflict with a tight planning-cycle budget. Multi-agent large language model frameworks support this balancing process by assigning specialized agents to different objectives. However, their conflict resolution is typically heuristic. Requirements are aggregated implicitly without explicit acceptance or rejection, limiting auditability in regulated domains. We present ArgRE, a multi-agent requirements negotiation system that embeds Dung-style abstract argumentation into the negotiation stage. Each proposal, critique, and refinement is modeled as an argument, conflicts are represented as directed attack relations, and the accepted set of arguments is computed under grounded and preferred semantics. The pipeline further integrates KAOS goal modeling, multi-layer verification, and standards-oriented artifact generation. Evaluation across five case studies spanning safety-critical, financial, and information-system domains shows that ArgRE provides argument-level traceability absent from existing frameworks. Independent evaluators rated its decision justifications significantly higher than those of heuristic synthesis (4.32 vs. 3.07, p < 0.001), indicating improved auditability, while semantic intent preservation remains comparable (94.9% BERTScore F1) and compliance coverage reaches 84.7% versus 47.6%--47.8% for baselines. Structural analysis further confirms that the default pairwise protocol yields acyclic graphs in which grounded and preferred semantics coincide, whereas cross-pair arbitration introduces controlled cyclicity, leading to predictable divergence between the two semantics.

---

### Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training

Authors: Suning Huang, Jiaqi Shao, Ke Wang, Qianzhong Chen, Jiankai Sun, Yanjiang Guo, Mac Schwager, Jeannette Bohg
Published: 2026-04-25
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2604.23121v1

Have you ever post-trained a generalist vision-language-action (VLA) policy on a small demonstration dataset, only to find that it stops responding to new instructions and is limited to behaviors observed during post-training? We identify this phenomenon as lock-in: after low-data, supervised fine-tuning (SFT), the policy becomes overly specialized to the post-training data and fails to generalize to novel instructions, manifesting as concept lock-in (fixation on training objects/attributes) and spatial lock-in (fixation on training spatial targets). Many existing remedies introduce additional supervision signals, such as those derived from foundation models or auxiliary objectives, or rely on augmented datasets to recover generalization. In this paper, we show that the policy's internal pre-trained knowledge is sufficient: DeLock mitigates lock-in by preserving visual grounding during post-training and applying test-time contrastive prompt guidance to steer the policy's denoising dynamics according to novel instructions. Across eight simulation and real-world evaluations, DeLock consistently outperforms strong baselines and matches or exceeds the performance of a state-of-the-art generalist policy post-trained with substantially more curated demonstrations.

---

### HBGSA: Hydrogen Bond Graph with Self-Attention for Drug-Target Binding Affinity Prediction

Authors: Junxiao Kong, Chupei Tang, Di Wang, Jixiu Zhai, Yi He, Moyu Tang, Tianchi Lu
Published: 2026-04-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.23115v1

Accurate prediction of drug-target binding affinity accelerates drug discovery by prioritizing compounds for experimental validation. Current methods face three limitations: sequence-based approaches discard spatial geometric constraints, structure-based methods fail to exploit hydrogen bond features, and conventional loss functions neglect prediction-target correlation, a key factor for identifying high-affinity compounds in virtual screening. We developed HBGSA (Hydrogen Bond Graph with Self-Attention), a 3.06M-parameter model that encodes hydrogen bond spatial features. HBGSA uses graph neural networks to model hydrogen bond spatial topology with self-attention enhancement and Pearson correlation loss. Experimental results on PDBbind Core Set and CSAR-HiQ dataset demonstrate that HBGSA outperforms baseline methods with strong generalization capability. Ablation studies confirm the effectiveness of hydrogen bond modeling and Pearson correlation loss.

---

### A Tale of Two Variances: When Single-Seed Benchmarks Fail in Bayesian Deep Learning

Authors: Qishi Zhan, Minxuan Hu, Liang He, Guansu Wang, Jiaxin Liu
Published: 2026-04-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.23114v1

In limited-data settings, a single endpoint mean of an evaluation metric such as the Continuous Ranked Probability Score (CRPS) is itself a random variable, yet it is routinely reported as if it were a stable property of the method. We study when this practice fails. Using 50 independent repetitions across six regression datasets, we show that CRPS variance trajectories differ substantially across methods and are not always well described by a smooth power-law decay. Methods with a learned heteroscedastic variance head, namely MAP and Deep Ensembles, can develop pronounced, reproducible variance peaks at intermediate training sizes on real datasets, whereas MC Dropout and Bayes by Backprop typically show smooth variance contraction. These peaks have direct practical consequences: at the variance peak on Seoul Bike, the relative RMSE of a single-seed MAP estimate reaches 93.6\%, and the probability of falling within \(\pm 10\%\) of the repeated-run mean drops to 5.9\%. We show that local CRPS variance provides a direct signal of single-seed estimation error, with Spearman correlations above 0.96 on every real dataset. Power-law fit quality and monotonicity together provide compact method-level summaries of trajectory regularity. Finally, replacing the standard heteroscedastic objective with \(β\)-NLL substantially reduces the irregular behavior, consistent with the view that the heteroscedastic training objective contributes to the instability. Practitioners should report trajectory summaries alongside endpoint means and concentrate repeated evaluation in high-variance regions.

---

### Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learning

Authors: Wugeng Zheng, Ziwen Kan, Katie Wang, Chen Chen, Song Wang
Published: 2026-04-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.23112v1

Multimodal Federated Learning (MMFL) enables privacy-preserving collaborative training, but real-world clinical applications often suffer from within-modality missingness caused by sensor intermittency or irregular sampling. Existing methods implicitly represent unobserved data via architectural alignment or missing embeddings, often failing to recover the true distribution and yielding sub-optimal performance. We propose CondI, a federated framework explicitly addressing this missingness using conditional diffusion models. CondI employs a two-phase training pipeline: first, imputing unobserved temporal components using available multimodal context and conditional embeddings; second, optimizing modality-specific extractors and joint embedding spaces. During inference, imputed raw data pass through trained extractors to generate robust features, providing a holistic representation for downstream tasks. Explicit data imputation ensures models operate on complete semantic structures, significantly enhancing resilience against severe data incompleteness. Experiments on three clinical datasets (PTB-XL, SLEEP-EDF, MIMIC-IV) demonstrate CondI achieves comparable results to state-of-the-art baselines. Code: https://github.com/ZhengWugeng/CondI

---

### Mixture of Heterogeneous Grouped Experts for Language Modeling

Authors: Zhicheng Ma, Xiang Liu, Zhaoxiang Liu, Ning Wang, Yi Shen, Kai Wang, Shuming Shi, Shiguo Lian
Published: 2026-04-25
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.23108v2

Large Language Models (LLMs) based on Mixture-of-Experts (MoE) are pivotal in industrial applications for their ability to scale performance efficiently. However, standard MoEs enforce uniform expert sizes,creating a rigidity that fails to align computational costs with varying token-level complexity. While heterogeneous expert architectures attempt to address this by diversifying expert sizes, they often suffer from significant system-level challenges, specifically unbalanced GPU utilization and inefficient parameter utilization, which hinder practical deployment. To bridge the gap between theoretical heterogeneity and robust industrial application, we propose Mixture of Heterogeneous Grouped Experts (MoHGE) which introduces a two-level routing mechanism to enable flexible, resource-aware expert combinations. To optimize inference efficiency, we propose a Group-Wise Auxiliary Loss, which dynamically steers tokens to the most parameter-efficient expert groups based on task difficulty. To address the critical deployment challenge of GPU load balancing, we introduce an All-size Group-decoupling Allocation strategy coupled with an Intra-Group Experts Auxiliary Loss. These mechanisms collectively ensure uniform computation distribution across GPUs. Extensive evaluations demonstrate that MoHGE matches the performance of MoE architectures while reducing the total parameters by approximately 20% and maintaining balanced GPU utilization. Our work establishes a scalable paradigm for resource-efficient MoE design, offering a practical solution for optimizing inference costs in real-world scenarios. The code is publicly available at https://github.com/UnicomAI/MoHGE.

---

### MOCA: A Transformer-based Modular Causal Inference Framework with One-way Cross-attention and Cutting Feedback

Authors: Lei Wang, Debashis Ghosh
Published: 2026-04-25
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2604.23107v2

Causal effect estimation from observational data requires careful adjustment for confounding. Classical estimators such as inverse probability weighting and augmented inverse probability weighting can perform well under favorable model specification but may become unstable in complex settings. Machine-learning and representation-learning methods provide greater flexibility, but joint optimization may allow outcome information to alter treatment representations and compromise the intended causal structure. We propose MOCA (Modular One-way Causal Attention), a transformer-based framework that separates treatment and outcome modeling through a modular architecture. This design preserves directional information flow while retaining the flexibility of transformer architectures. Using a Markov-kernel formulation, we show that MOCA learns an autonomous treatment representation and is predictively KL-optimal within its Gaussian model class. Under correct specification, MOCA recovers the true average treatment effect, while additional two-way feedback does not further reduce average treatment effect estimation error. We also propose a conformal inference procedure for individual treatment effects. Across multiple simulation scenarios, MOCA achieved competitive or improved average treatment effect estimation compared with IPW, AIPW, the X-learner, TARNet, DragonNet, BART, Causal Forest, and Do-PFN. Ablation studies supported the contributions of the proposed architectural components. We further evaluated MOCA on the Infant Health and Development Program benchmark and the observational Dehejia-Wahba dataset. Overall, modular attention with one-way information flow provides an effective and interpretable framework for causal inference using modern deep-learning models.

---

### No Test Cases, No Problem: Distillation-Driven Code Generation for Scientific Workflows

Authors: Siddeshwar Raghavan, Tanwi Mallick
Published: 2026-04-25
Categories: cs.SE, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2604.23106v1

Existing multi-agent Large Language Model (LLM) frameworks for code generation typically use execution feedback and improve iteratively using Input/Output (I/O) test cases. However, this does not work for scientific workflows, where I/O test cases do not exist, and generating them requires solving the very problem at hand. To address this, we introduce MOSAIC, a training-free multi-agent framework for scientific code generation without I/O supervision. Instead of execution feedback, MOSAIC employs a student-teacher knowledge distillation framework that grounds generation through domain-specific examples and structured problem decomposition. To further mitigate hallucinations across chained subproblems, we introduce a Consolidated Context Window (CCW) for maintaining consistent reasoning across agents. Experiments on the SciCode benchmark show that MOSAIC improves accuracy, executability, and numerical precision over existing approaches while relying on lightweight models.

---

### Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving

Authors: Zihui Zhu, Ziqi Zhou, Yichen Wang, Lulu Xue, Minghui Li, Shengshan Hu
Published: 2026-04-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.23105v1

Deep learning drives major advances in autonomous driving (AD), where object detectors are central to perception. However, adversarial attacks pose significant threats to the reliability and safety of these systems, with physical adversarial patches representing a particularly potent form of attack. Physical adversarial patch attacks pose severe risks but are usually crafted for a single model, yielding poor transferability to unseen detectors. We propose AdvAD, a transfer-based physical attack against object detection in autonomous driving. Instead of targeting a specific detector, AdvAD optimizes adversarial patches over multiple detection models in a unified framework, encouraging the learned perturbations to capture shared vulnerabilities across architectures. The optimization process adaptively balances model contributions and enforces robustness to physical variations. It further employs data augmentation and geometric transformations to maintain patch effectiveness under diverse physical conditions. Experiments in both digital and real-world settings show that AdvAD consistently outperforms state-of-the-art (SOTA) attacks in performance and transferability.

---

### Unstable Rankings in Bayesian Deep Learning Evaluation

Authors: Qishi Zhan, Minxuan Hu, Guansu Wang, Jiaxin Liu, Liang He
Published: 2026-04-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.23102v1

Standard evaluations of Bayesian deep learning methods assume that metric estimates are reliable, but we show this assumption fails under data scarcity. Method rankings are not only unreliable at small $n$, but also dataset-dependent in ways that point estimates cannot reveal: the same method comparison yields $P(\mathrm{MCD} \prec \mathrm{Ensemble}) = 1.000$ at $n = 50$ on one dataset and remains below $0.95$ even at $n = 500$ on another. Across the datasets we consider, no universal sample size threshold exists, which is precisely why dataset-specific posterior inference is necessary. To address this, we use a Bayesian hierarchical model with method-specific variances to treat evaluation metrics as random variables across data realizations, and we use a predictive Minimum Detectable Difference curve to assess whether an observed gap would be detectable at a given training size. Across six Bayesian deep learning methods and five regression datasets, our results show that uncertainty-aware evaluation is necessary in low-data settings, because current evidence for method superiority and predictive detectability at the same training size can diverge substantially. Our framework provides practitioners with principled tools to determine whether their evaluation data is sufficient before drawing conclusions about method superiority.

---

### ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation

Authors: Yizheng Huang, Wenjun Zeng, Aditi Kumaresan, Zi Wang
Published: 2026-04-25
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2604.23099v2

Evaluating generative AI models is increasingly resource-intensive due to slow inference, expensive raters, and a rapidly growing landscape of models and benchmarks. We propose ProEval, a proactive evaluation framework that leverages transfer learning to efficiently estimate performance and identify failure cases. ProEval employs pre-trained Gaussian Processes (GPs) as surrogates for the performance score function, mapping model inputs to metrics such as the severity of errors or safety violations. By framing performance estimation as Bayesian quadrature (BQ) and failure discovery as superlevel set sampling, we develop uncertainty-aware decision strategies that actively select or synthesize highly informative inputs for testing. Theoretically, we prove that our pre-trained GP-based BQ estimator is unbiased and bounded. Empirically, extensive experiments on reasoning, safety alignment, and classification benchmarks demonstrate that ProEval is significantly more efficient than competitive baselines. It requires 8-65x fewer samples to achieve estimates within 1% of the ground truth, while simultaneously revealing more diverse failure cases under a stricter evaluation budget.

---

### INSIGHT: Indoor Scene Intelligence from Geometric-Semantic Hierarchy Transfer for Public~Safety

Authors: Alexander Nikitas Dimopoulos, Joseph Grasso, John Beltz
Published: 2026-04-25
Categories: cs.CV, cs.ET
arXiv: https://arxiv.org/abs/2604.23095v1

Indoor environments lack the spatial intelligence infrastructure that GPS provides outdoors; first responders arriving at unfamiliar buildings typically have no machine-readable map of safety equipment. Prior work on 3D semantic segmentation for public safety identified two barriers: scarcity of labeled indoor training data and poor recognition of small safety-critical features by native point-cloud methods. This paper presents INSIGHT, a zero-target-domain-annotation pipeline that projects 2D image understanding into 3D metric space via registered RGB-D data. Two interchangeable vision stacks share a common 3D back end: a SAM3 foundation-model stack for text-prompted segmentation, and a traditional CV stack (open-set detection, VQA, OCR) whose intermediate outputs are independently inspectable. Evaluated on all seven subareas of Stanford 2D-3D-S (70{,}496 images), the pipeline produces Pointcept-schema-compatible labeled point clouds and ISO~19164-compliant scene graphs with ${\sim}10^{4}{\times}$ compression; role-filtered payloads transmit in ${<}15$\,s at 1\,Mbps over FirstNet Band~14. We report per-point labeling accuracy on 7 shared classes, detection sensitivity for 15 safety-critical classes absent from public 3D benchmarks alongside code-capped deployable estimates, and inter-pipeline complementarity, demonstrating that 2D-to-3D semantic transfer addresses the labeled-data bottleneck while scene graphs provide building intelligence compact enough for field deployment.

---

### FusionRelight: Relighting Portraits in Real Time via Hybrid Domain Knowledge Fusion

Authors: Qian Huang, Mayoore Selvarasa Jaiswal, Zhen Zhong, Rochelle Pereira, Jianyuan Min
Published: 2026-04-25
Categories: cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2604.23094v2

Portrait relighting is a low-level vision problem in which physically plausible illumination transfer, identity preservation, and compact real-time inference must be considered together. Iterative diffusion-style methods can synthesize fine detail, but stochastic inference and cost complicate deterministic live video creation; physically grounded relighting preserves identity, but controlled synthetic or light-stage supervision transfers poorly to unconstrained cameras. We present Hybrid Domain Knowledge Fusion (HDKF), a relighting-specific training framework that learns complementary physics, reflectance, and realism priors from synthetic, One-Light-at-A-Time (OLAT), and in-the-wild data, then distills their source-routed supervision into a compact student with clean teacher labels and degraded student inputs. The framework is trained with pixel-aligned RGB, albedo, and normal supervision, providing a simulation substrate for physically grounded low-level relighting. On a held-out OLAT benchmark, HDKF obtains the best MSE, PSNR, and SSIM among evaluated methods while remaining competitive in LPIPS. The distilled model runs in real time at 512x512, reaching 11.89 ms on an RTX 2060 and 1.82 ms on an RTX 4090.

---

### Toward Real-World Adoption of Portrait Relighting via Hybrid Domain Knowledge Fusion

Authors: Qian Huang, Mayoore Selvarasa Jaiswal, Zhen Zhong, Rochelle Pereira, Jianyuan Min
Published: 2026-04-25
Categories: cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2604.23094v1

The real-world adoption of portrait relighting is hindered by dataset domain gaps, camera sensitivity, and computational costs. We address these challenges with Hybrid Domain Knowledge Fusion, a paradigm that fuses the specialized strengths of synthetic, One-Light-at-A-Time (OLAT), and real-world datasets into a compact model. Our approach features specialized prior models hardened by domain-aware adaptation, followed by augmented knowledge distillation into a lightweight student model with multi-domain expertise. Our method demonstrates a 6x to 240x inference speedup while maintaining state-of-the-art (SOTA) visual quality in the experiments. Additionally, we construct a massive, high-fidelity synthetic dataset with diverse ground-truth intrinsics to support our training pipeline.

---

### Channel Adaptation for EEG Foundation Models: A Systematic Benchmark Across Architectures, Tasks, and Training Regimes

Authors: Kuntal Kokate, Bruno Aristimunha, Dung Truong, Arnaud Delorme
Published: 2026-04-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.23091v1

Scaling EEG foundation models requires pooling data across heterogeneous electrode montages, a prerequisite both for larger pretraining corpora and for downstream deployment. We present the first systematic comparison of four channel adaptation methods (Conv1d projection, spherical spline interpolation (SSI), source-space decomposition, and Riemannian re-centering) across five pretrained EEG foundation models (5M--157M parameters), five downstream tasks, and two training regimes with 10--15 random seeds each. We find that rigid-montage models (BENDR, Neuro-GPT) require external adaptation, while flexible models (EEGPT, CBraMod) match or exceed it natively when fine-tuned but benefit from external methods under frozen-encoder deployment. A probe-SFT asymmetry exists: external adaptation can cause severe negative transfer during fine-tuning of flexible models. The optimal method is architecture-dependent (Conv1d for BENDR, SSI/Riemannian for Neuro-GPT, source-space decomposition for depression detection), and 5M-parameter CBraMod outperforms models up to 31$\times$ larger on 4/5 datasets, consistent with independent findings that compact EEG-specific architectures can match larger models.

---

### Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach

Authors: Abid Talukder, Maruf Ahmed Mridul, Oshani Seneviratne
Published: 2026-04-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.23090v1

Automatically generating formal ontologies from unstructured natural language remains a central challenge in knowledge engineering. While large language models (LLMs) show promise, it remains unclear which architectural design choices drive generation quality and why current approaches fail. We present a controlled experimental study using domain-specific insurance contracts to investigate these questions. We first establish a single-agent LLM baseline, identifying key failure modes such as poor Ontology Design Pattern compliance, structural redundancy, and ineffective iterative repair. We then introduce a multi-agent architecture that decomposes ontology construction into four artifact-driven roles: Domain Expert, Manager, Coder, and Quality Assurer. We evaluate performance across architectural quality (via a panel of heterogeneous LLM judges) and functional usability (via competency question driven SPARQL evaluation with complementary retrieval augmented generation based assessment). Results show that the multi-agent approach significantly improves structural quality and modestly enhances queryability, with gains driven primarily by front-loaded planning. These findings highlight planning-first, artifact-driven generation as a promising and more auditable path toward scalable automated ontology engineering.

---

### Code Broker: A Multi-Agent System for Automated Code Quality Assessment

Authors: Samer Attrah
Published: 2026-04-25
Categories: cs.SE, cs.AI, cs.CL, cs.PL
arXiv: https://arxiv.org/abs/2604.23088v2

We present Code Broker, a multi agent system built on Google s Agent Development Kit ADK that analyses Python source code from individual files, local directory trees, or remote GitHub repositories and generates structured, actionable quality assessment reports. The system realises a hierarchical five agent architecture in which a root orchestrator coordinates a sequential pipeline agent that, in turn, dispatches three specialised agents concurrently a Correctness Assessor, a Style Assessor, and a Description Generator before synthesising their findings through an Improvement Recommender. Reports quantify four quality dimensions correctness, security, style, and maintainability on a normalised scale and are rendered in both Markdown and HTML for integration into diverse developer workflows. Code Broker fuses LLM based semantic reasoning with deterministic static analysis signals from Pylint, employs asynchronous execution with exponential backoff retry logic to improve robustness under transient API failures, and explores lightweight session memory for retaining and querying prior assessment context across runs. We frame this paper as a technical report on system design, prompt engineering, and tool orchestration, and present a preliminary qualitative evaluation on representative Python codebases of varying scale. The results indicate that parallel specialised agents produce readable, developer oriented feedback that complements traditional linting, while also foregrounding current limitations in evaluation depth, security tooling, large repository handling, and the exclusive reliance on in memory persistence. All code and reproducibility materials are publicly available: https://github.com/Samir-atra/agents_intensive_dev.

---

### Turtle shell clustering: A mixture approach to discriminative clustering with applications to flow cytometry and other data

Authors: Mackenzie R. Neal, Paul D. McNicholas, Arthur White
Published: 2026-04-25
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2604.23083v2

Generative approaches to clustering provide information on geometric properties of clusters, whereas discriminative approaches provide boundaries between clusters. Ideas from both approaches are incorporated to present a fully unsupervised, probabilistic, and discriminative clustering method via a regularized mutual information objective function, wherein a mixture of mixtures of Gaussian and uniform distributions is used for formulation of the conditional model. Overfitting is avoided by the introduction of a regularizing term and a cluster merge step, similar to those applied in reversible jump Markov chain Monte Carlo methods used in Bayesian clustering. Consequently, the turtle shell method -- a fully unsupervised clustering method capable of estimating non-linear boundary lines, automatically selecting the number of components, and capturing intuitive clusters in the presence of data abnormalities such as noise and/or irregular cluster shapes -- is introduced. We test this method on various simulated and real datasets commonly explored in clustering research, and extend the analysis to datasets arising from flow cytometry experiments and image analysis.

---

### Usable Agent Discovery for Decentralized AI Systems

Authors: Patrizio Dazzi, Emanuele Carlini, Matteo Mordacchini, Saul Urso
Published: 2026-04-25
Categories: cs.MA, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2604.23080v1

Large-scale agentic systems run on distributed infrastructures where many software agents share physical hosts and are discovered via peer-to-peer mechanisms. Discovery must handle node-level churn from failures and host departures and agent-level churn from demand-driven activation, deactivation, and state changes. Their interaction reshapes classic trade-offs between structured and unstructured overlays. We study decentralized agent discovery under this two-level churn, assuming nodes host multiple agents, overlays are structured or gossip-based, and agents switch between warm and cold states. Using Kademlia as a structured and Cyclon+Vicinity as a gossip baseline, we compare stable, node-churn-only, agent-cooling-only, and combined regimes to see when routing efficiency, resilience, and service readiness align or favor different designs. Structured overlays are more robust and efficient in stable and node-churn regimes, while gossip-based overlays remain competitive and can be faster when readiness dominates.

---

### From Pixels to Explanations: Interpretable Diabetic Retinopathy Grading with CNN-Transformer Ensembles, Visual Explainability and Vision-Language Models

Authors: Pir Bakhsh Khokhar, Carmine Gravino, Fabio Palomba, Sule Yildirim Yayilgan, Sarang Shaikh
Published: 2026-04-25
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.23079v1

The quality of diabetic retinopathy (DR) screening relies on the ability to correctly grade severity; however, many deep-learning (DL) classifiers cannot be easily interpreted in the clinical context. This study presents a methodology that combines strong discriminative models with multimodal explanations, converting retinal pixels into clinically interpretable outputs. Using the APTOS 2019 benchmark, we evaluated six representative CNN- and transformer-based backbones under a controlled protocol with stratified five-fold cross-validation. We then compared ensembling strategies (hard voting, weighted soft voting, stacking) and investigated a hybrid class-level fusion variant to exploit grade-specific advantages. For interpretability, we produced Grad-CAM++ visual attribution maps and short textual rationales using vision-language models (VLMs) conditioned on the fundus image and classifier outputs under conservative prompting constraints. Modern CNN backbones (ResNet-50 and ConvNeXt-Tiny) provided the strongest single-model baselines, with cross-validated QWK up to 0.919 and 0.914, respectively. Ensembling improved ordinal agreement, and weighted soft voting was the most consistent across folds (QWK 0.934 +/- 0.017). Hybrid class-level fusion was competitive but did not yield a statistically reliable improvement over standard fusion in paired fold comparisons (Holm-adjusted p >= 1.000). For explanation quality, Grad-CAM++ offered plausible but coarse localization, and VLM rationales were generally grade-consistent. Quantitatively, VLM variants showed a trade-off between clinical completeness and template-level semantic similarity (coverage 0.700 vs. BERTScore 0.072), while image-text alignment was comparable (CLIPScore approximately 0.34).

---

### Some Large Language Models Exhibit Consistent Risk Attitudes

Authors: Bowen Sun, Rui Min, Yuxi Wang, Brian Odegaard, Qi Wang, Jing Du
Published: 2026-04-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.16197v1

As artificial intelligence systems are deployed in open-ended, high-stakes settings, a critical dimension remains unmeasured: how perceived risk is translated into action. We test whether large language models (LLMs) exhibit systematic and consistent risk attitudes under uncertainty. We introduce a cross-domain framework that decouples contextual risk belief from categorical decision, and apply it to six representative LLMs and 100 human participants across spatial navigation, clinical triage, and financial allocation tasks. Using regression models, we extract each agents belief-to-decision mapping and quantify risk sensitivity and risk attitude bias. We find that most tested LLMs exhibit (i) robust intra-task consistency, indicating stable mappings from contextual belief to risk decision within a fixed task domain; (ii) cross-domain rank-order stability, preserving relative risk posture across tasks; and (iii) a convergence toward a restricted risk-attitude distribution relative to the broader human baseline. These results reveal risk attitude as a stable and previously uncharacterized dimension of LLM behavior, establishing a foundation for evaluating and aligning AI systems in open-ended decision-making and motivating further investigation into the origins of these intrinsic behavioral dispositions.

---

### Scaling Point-in-Time Language Models

Authors: Bryan Kelly, Semyon Malamud, Johannes Schwab, Teng Andrea Xu
Published: 2026-04-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2607.11889v2

Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromises the validity of backtests and causal inference in finance and the social sciences. Point-in-time language models--trained exclusively on text available up to each calendar date--eliminate this leakage by construction, but existing efforts typically produce models that lag substantially behind their unconstrained counterparts. We show that this performance gap can be substantially narrowed through scale. Training decoder-only transformers with up to 4 billion parameters on 1 trillion chronologically filtered tokens from FineWeb, we construct a sequence of monthly model checkpoints spanning 2013-2024. Across a range of common-sense reasoning and language understanding benchmarks, our models approach the performance of leading open-weight models of comparable size (e.g., Gemma-3-4B and LLaMA-7B) trained on temporally unrestricted data, although a performance gap remains on several tasks. Instruction fine-tuning via LoRA further improves downstream usability. We release the complete pipeline--including dataset construction, training infrastructure, and evaluation code--to enable reproducible point-in-time language modeling and to support research applications that require strict temporal validity.

---

### On the Identifiability of User Adaptation in Co-Adaptive Neural Interfaces

Authors: Philip Waggoner
Published: 2026-04-24
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2606.20569v1

We analyze identifiability in co-adaptive human-machine systems. We show that closed-loop encoder estimates do not uniquely identify user adaptation, but instead reflect properties of the joint system. We discuss implications for interpreting behavioral adaptation and propose conditions for identification.

---

### Ensembles of Large Language Models for Identifying EQ-5D Studies in PubMed Based on Their Abstracts

Authors: Zhyar Rzgar K. Rostam, Márta Péntek, János Tibor Czere, Zsombor Zrubka, László Gulácsi, Gábor Kertész
Published: 2026-04-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.19345v1

The rapid increase in scientific publications leads to the fact that manual study screening in systematic literature reviews (SLRs) is increasingly resource consuming, inefficient, and inconsistent. Classifying studies that clearly report health-related quality-of-life results, such as EQ-5D data, requires a high level of clinical interpretation and poses challenges for human reviewers. This study investigates the use of Google's Gemini and Gemma large language models (LLMs) in automating EQ-5D detection in the PubMed biomedical database based only on published abstracts. A multi-phase framework is proposed that integrates few-shot prompting, weight ensembling aggregation, and a soft stacking meta-classifier. Nine LLMs are evaluated on a dataset of PubMed studies manually labeled by two experts regarding EQ-5D reporting. The weighted ensemble of gemini-2.5-pro, gemma-3-12b, and gemma-3-27b obtained a 0.74 weighted F1-score and 0.74 accuracy, exceeding individually attained results. The ensembling of top-performing models improved the balance between precision and recall compared to individual models, while the soft stacking approach provided greater reliability and interpretability. Feature analysis shows that the probability results from the models are important in guiding the final predictions. The findings suggest that an ensemble-based LLM setup is a reliable and scalable approach for automating screening in biomedical research.

---

### Exposing the Unsaid: Visualizing Hidden LLM Bias through Stochastic Path Aggregation

Authors: Matteo Pelossi, Rita Sevastjanova, Thilo Spinner, Mennatallah El-Assady
Published: 2026-04-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.19344v1

Large Language Models (LLMs) exhibit representational and syntactic biases that are difficult to evaluate due to the stochastic nature of text generation. Standard auditing methods rely on a single output inspection or static automated metrics. These approaches obscure the underlying probability distributions and fail to capture biases hidden in lower-probability generation branches. This paper introduces TreeTracer, a visual analytics tool designed to evaluate LLM bias through aggregated comparison. Using a systematic perturbation analysis pipeline, the tool replaces ontology-defined terms in each input prompt, aggregates hundreds of stochastic generations into a syntax-aligned hierarchical structure, and then performs classification-aware node merging with an auxiliary language model. The resulting structure is visualized through a custom Sankey diagram. By juxtaposing two ontology-driven trees, the workspace enables direct comparison between semantic contexts and supports systematic bias detection. Because any visualization reflects only a subset of the model's learned behavior, the system further applies contrastive inference to compute and directly display counterfactual token probabilities across contexts, reducing the risk of misinterpreting the presence of bias. We validate the workspace through case studies comparing an unaligned baseline model GPT-2 XL against the constitutionally aligned Apertus models. The visual aggregation successfully exposes hidden representational harms, such as counterfactual pronoun suppression and conversational marginalization of individuals. A preliminary user study confirms that the aggregated comparative interface reduces cognitive load and effectively supports analysts in detecting systemic biases.

---

### EverydayGPT: Confidence-Gated Routing for Efficient and Safe Hybrid GPT-RAG Conversational QA

Authors: Jaspreet Singh Nahal
Published: 2026-04-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.11212v1

Standard Retrieval-Augmented Generation (RAG) pipelines route every query through retrieval and generation unconditionally, incurring unnecessary computation and propagating low-quality context to the generator. We introduce EverydayGPT, a lightweight conversational QA system built around a Confidence-Gated Routing (CGR) mechanism that formalises the routing decision as a joint policy over retrieval distance and extraction adequacy. The backbone is a 205M-parameter GPT trained from scratch on 10B tokens of FineWeb-Edu. CGR avoids invoking the costly GPT pathway (~5.9s) for 85 percent of queries by resolving them via fast RAG extraction (~45 ms), yielding over 120x latency reduction on the majority of queries while maintaining answer quality. On a 500-question in-domain benchmark, the system achieves F1 = 0.226 +/- 0.004 compared to 0.171 for GPT-only and 0.210 for unconditional RAG. Gains over strong baselines are modest but consistent, while efficiency improvements are substantial (6.3x mean latency reduction). A structured grounding audit finds no unsupported claims in the sampled set, with explicit scope limitations. We position this work as a study of routing strategies under resource constraints rather than a claim of state-of-the-art performance.

---

### Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

Authors: Prakul Sunil Hiremath, Harshit R. Hiremath
Published: 2026-04-24
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2606.11211v1

The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment. Chain-of-thought (CoT) reasoning is widely used to improve accuracy and reliability, but its effect on calibration is not fully understood. We show that this picture is incomplete: in some settings, increasing the reasoning budget beyond a task-specific threshold can cause models to become systematically overconfident, assigning high confidence to incorrect answers. We call this phenomenon Calibration Drift Under Reasoning (CDUR) and study it both theoretically and empirically. We define reasoning budget B and analyze conditions under which Expected Calibration Error ECE(B) follows a non-monotonic pattern: it first decreases as reasoning corrects errors, then increases as longer reasoning produces internally consistent but incorrect explanations. We propose a Hypothesis Lock-In model based on autoregressive generation to explain this behavior. We evaluate Llama-3.1-8B and Llama-3.3-70B on 47 reasoning-trap questions across four reasoning budgets and three seeds (1,368 API calls; 574 valid responses). The 8B model shows non-monotonic calibration behavior, while results for the 70B model are limited to baseline evaluation and are inconclusive for budget-dependent effects. We introduce CABStop, a calibration-aware stopping rule that halts reasoning when confidence diverges from an auxiliary accuracy estimate. These results suggest that increasing reasoning depth does not always improve reliability and should be monitored carefully.

---

### T2MM: An LLM Supported Architecture For Inquiry-Based Modeling

Authors: John Kos, Rudra Singh, Ashok Goel
Published: 2026-04-24
Categories: cs.CL, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2606.11210v1

Model Construction is a foundational practice in science learning that relies on visualization and interactivity. Large Language Models, increasingly augmented with multimodal capabilities, have been integrated in education contexts to support learning. However, these tools lack visual interactivity that is required by some learning contexts. We introduce Text to Multimodal Model (T2MM), a robust, dynamic LLM supported architecture that assists in model construction within the open inquiry ecology-based modeling software Virtual Experimental Research Assistant (VERA). T2MM accounts for the current context of the learner's model and creates interactive models, rather than static images, enabling the model to remain responsive to manual adjustment. To measure technical feasibility, we evaluate T2MM through a custom procedurally generated dataset of natural language learner modeling requests and target models within the VERA system. T2MM outperforms a baseline model generation architecture implemented through LLM-supported full code generation, common in the literature, across all measured success metrics. Our contribution not only outlines LLM integration into a inquiry-based learning modeling tool, but also describes a possible architecture through which more interactive multimodal LLM tools can be created.

---

### An LLM-Native Psychometric Instrument Reveals a Self-Report--Behavior Gap Across 25 Models

Authors: Juan Manuel Contreras
Published: 2026-04-24
Categories: cs.HC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.09843v3

Large language models (LLMs) give stable answers to personality questionnaires, yet these self-reports fail to predict how the models behave. Is this gap an artifact of forcing human trait categories onto LLMs, or something deeper about LLM self-report? To find out, we built the first psychometric instrument whose dimensions are derived from LLM behavior rather than human psychology. Administering 300 items (240 Likert + 60 scenario) to 25 LLMs across 17 model families, 30 times each, exploratory factor analysis revealed five reliable, replicable factors: Responsiveness, Deference, Boldness, Guardedness, and Verbosity (all Tucker $φ\geq .957$, all $α\geq .930$). We collected 2,500 open-ended samples and had them rated by 151 humans and a three-judge LLM ensemble. Humans and judges agreed ($\bar{r} = .51$), but self-report predicted neither the ratings nor objective text measures computed from them: the gap persists even for constructs native to LLMs, where a human-mismatch explanation no longer applies. The exception is Verbosity, whose self-report reaches 74% of the criterion-reliability ceiling against human ratings, but does not track raw output length. On Responsiveness, self-report tracked LLM judges ($r = .53$) but not humans ($r = .04$), even though humans and judges otherwise agreed ($r = .59$). This pattern formally rejects any single latent construct driving all three measurements ($p = .007$). Self-report items and LLM judges share a source of variance that human observers do not, and controlling for measurable surface features (length, formatting, enthusiasm markers) does not remove it. This confound is invisible to the within-ensemble reliability checks used to validate LLM judges, and it poses a concrete risk for the LLM-as-judge pipelines now central to model evaluation. We release the instrument as a diagnostic probe for alignment-shaped self-description.

---

### Multilingual Refusal Alignment for Safer Large Language Models

Authors: Aleksandra Krasnodębska, Wojciech Kusa, Aldo Lipani
Published: 2026-04-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.07535v1

As Large Language Models (LLMs) are deployed globally, ensuring their safety and alignment across multiple languages becomes paramount. However, safety behaviors often vary unpredictably between languages, posing significant challenges for consistent and ethical AI. In this work, we systematically investigate the dynamics of multilingual alignment, exploring whether single-language alignment transfers cross-lingually, how language consistency is preserved during training, and the resulting trade-offs with general knowledge capabilities. We introduce RefusEU, a novel refusal alignment dataset covering 12 European languages, including a dedicated test set for evaluating current state-of-the-art models. Our controlled Direct Preference Optimization (DPO) experiments provide two key insights: aligning models exclusively in English is insufficient to ensure cross-lingual safety, even for the same harm categories, whereas training on multilingual datasets can improve safety without degrading general performance, as measured by the Global MMLU benchmark.

---

### Real-Time AttentionBender: Granular Interactive Network Bending of Video Diffusion Transformers

Authors: Adam Cole, Rebecca Fiebrink, Mick Grierson
Published: 2026-04-24
Categories: cs.GR, cs.CV, cs.HC
arXiv: https://arxiv.org/abs/2606.06497v2

Generative video models have achieved remarkable visual fidelity, yet their prompt-only interface offers thin creative agency and obscures the model's material process from the artists working with it. We present Real-Time AttentionBender, a tool that extends the practice of network bending across the full depth of the video diffusion transformer (DiT) and brings it into live, interactive generation. Built as a plugin within the DayDream Scope ecosystem and wrapping open-source real-time Wan pipelines, the tool exposes self-attention, cross-attention, and the feed-forward network as independently manipulable surfaces, with targeting down to individual diffusion steps, DiT layers, prompt tokens, and hidden neurons. The immediacy of live manipulation affords what we call "material intimacy" with the model: a responsive, near-mechanistic feel for how specific layers and neurons shape generated video. We position the tool as simultaneously an XAIxArts probe into transformer internals and an expressive instrument for discovering aesthetics outside the model's default representational space.

---

### Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing

Authors: Michael Lan, Narmeen Fatimah Oozeer, Chaithanya Bandi, Philip Quirke, Austin Meek, Fazl Barez, Amirali Abdullah
Published: 2026-04-24
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2606.00033v1

While mechanistic interpretability (MI) has produced important insights into neural network internals, the field has yet to establish a standardized system to audit experiments. As such, many of its findings remain underutilized in safety-critical applications such as medical AI and autonomous systems, as stakeholders cannot certify their validity. Recent work demonstrates this concretely: two papers found conflicting conclusions for the same behavior, and a third study revealed that both were partially correct but incomparable due to methodological inconsistencies. Without standardized auditing, such ambiguities hinder adoption in high-stakes contexts requiring strong correctness guarantees. We call for the MI community to work towards developing a novel reviewing system that complements peer review via: (1) Continuous reviewing supported by a \emph{Collaborative Reviewing Platform} where meta-science results and discussions (such as critiques, negative results, post-hoc extensions, reproductions, replications, and partial results) that fit outside of papers are organized and discussed, allowing for comments and revisions to be made at any time (2) Generalizing good practices found on this platform into expert-verified guidelines and protocols to improve auditing efficiency, and (3) Source-based auditing systems that track arguments which claims depend on. This position paper encourages constructive debate over the necessity, design and implementation of such a framework, providing early concrete examples to help catalyze these dialogues. Overall, we propose that auditing MI itself is essential for its application in AI safety, industry, and governance.

---

### Smaller, Younger, and More Impactful: How AI-Assisted Writing Transforms Research Teams

Authors: Haoyang Wang, Mingze Zhang, Yi Bu, Star Xing Zhao, Meijun Liu
Published: 2026-04-24
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2605.27404v1

The era of Big Science has long been defined by increasingly large and specialized research teams pushing the frontiers of knowledge. However, recent advances in artificial intelligence (AI), particularly large language models (LLMs), are beginning to reshape academic writing and scientific research, potentially disrupting the longstanding trend toward ever-larger teams and transforming other dimensions of research team structure. Drawing on 147,074 full-text publications from the PLoS family and the Nature portfolio since 2020, we examined whether and how AI-assisted writing influences team structure and team outcomes in science. Using multiple methods, including ordinary least square, quantile regression, Poisson regression, logistic regression and propensity score matching, we found that research teams using AI-assisted writing tend to be younger and smaller. Importantly, this shift toward more compact, junior-leaning teams does not come at the expense of scientific impact. On the contrary, we observed a higher probability of research teams that employed AI-assisted writing producing highly impactful publications. These results highlight the significant role of AI-assisted writing in reshaping not only how research is produced, but also how research teams are formed and assembled. Our findings call for policy improvements in research evaluation, funding, and training to address this emerging trend.

---

### LLM-assisted sentiment analysis for integrated computational and qualitative mixed methods education research: A case study of students' written reflection assignments

Authors: Xiomara Gonzalez, Gabriella Coloyan Fleming, Andrew Katz, Maya Denton, Jessica Deters
Published: 2026-04-24
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2605.27403v1

Written reflection assignments give students valuable opportunities for critical self-assessment, meaning making, and learning processing. Additionally, such reflections provide rich data for qualitative education research. However, qualitative data can be time-consuming to analyze. It is even more time-intensive to qualitatively compare findings between different groups of participants, usually limiting comparison to, at most, one variable (e.g., binary gender). Large language models (LLMs) have recently begun to be critically evaluated for use as qualitative research assistants. Using a longitudinal case of written student reflections (n=151) from a study abroad program, we investigate how LLM-assisted sentiment analysis can enable longitudinal mixed-methods research combining computational and thematic analyses. First, statistical testing is used to quantitatively compare sentiment differences according to seven different student identity/lived experience variables. Then, these results inform qualitative data analysis to investigate the reasons underlying these differences. For the case of undergraduate students studying abroad, we found that prior experience living abroad was the only personal variable impacting students' sentiments of their verbal language and communication behaviors. This workflow has implications for how qualitative researchers can more easily probe multiple variables when comparing participants from different demographic groups.

---

### REC-CBM: Rubric-Aware Error-Correction Concept Bottleneck Models for Trustworthy Open-Ended Grading

Authors: Chengshuai Zhao, Fan Zhang, Kumar Satvik Chaudhary, Yiwen Li, Lo Pang-Yun Ting, Ying-Chih Chen, Huan Liu
Published: 2026-04-24
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.27402v1

Open-ended grading is central to equitable and personalized education, yet manual grading remains time-consuming and costly, underscoring the need for automated grading systems. Although recent neural and large language model (LLM) based systems have demonstrated superior performance, they are typically black-box models whose scoring processes and rationales are difficult for educators to verify and trust. Concept bottleneck models (CBMs) have emerged as a promising approach by routing predictions through human-interpretable concepts, providing a mechanistic guarantee of transparency. However, standard CBMs are not tailored to open-ended grading: they do not explicitly model fine-grained rubric dimensions, inadequately capture the ordinal semantics of scoring scales, and neglect inherent reliability issues in human concept annotations. To address these limitations, we propose REC-CBM, a rubric-aware error-correction concept bottleneck model for trustworthy open-ended grading. REC-CBM introduces a rubric-aware concept encoder that learns concept-specific representations over responses and an ordinal pairwise calibration objective that preserves ranking structure among rubric dimensions. It further incorporates a latent concept error-correction module that denoises concept predictions before final grade prediction while preserving interpretability. Comprehensive experiments on publicly available datasets show that REC-CBM consistently improves grading performance and produces more faithful concept-level reasoning than both state-of-the-art baselines. Further analyses validate the contribution of each component and demonstrate the applicability in realistic educational settings. Overall, this work provides a practical, interpretable grading solution that enables educators to inspect, intervene in, and trust automated decisions, advancing more transparent and trustworthy education.

---

### Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, and Execution Gating in Autonomous Agent Systems

Authors: Marcelo Fernandez - TraslaIA
Published: 2026-04-24
Categories: cs.AI, cs.CY, cs.MA, cs.SE, eess.SY
arXiv: https://arxiv.org/abs/2605.23935v1

Autonomous agent systems fail not only due to incorrect decisions, but due to executing decisions whose authority no longer holds at runtime. Prior work defined Reconstructive Authority (RAM) as a condition for valid execution: actions are permitted only if authority can be constructed from current state. This paper addresses enforcement at runtime: how to enforce this condition in a running system. We introduce a runtime execution model in which authority is evaluated at action time and execution is conditioned on its constructibility. This extends the execution state space beyond admit/deny with a third state, halt, representing cases where authority is undefined due to incomplete or uncertain observability. We define a concrete execution protocol including dynamic dependency resolution, authority reconstruction, and explicit decision semantics. We further introduce a Recovery Loop that integrates drift detection (IML) with execution control (ACP), allowing the system to suspend execution, acquire missing information, and re-attempt authority reconstruction. We show that this model guarantees safety -- no action is executed without constructible authority -- and conditional liveness: execution resumes when authority-defining variables become observable. This work operationalizes reconstructive authority as a runtime enforcement mechanism, providing the execution semantics required to apply RAM in real systems.

---

### Practical Quantum CIM Empowerment via All-Domestic-Core Agentic Large Model

Authors: Wang Rui, Lu Diannan
Published: 2026-04-24
Categories: cs.AI, quant-ph
arXiv: https://arxiv.org/abs/2605.23934v1

Quantum computing devices are recognized as powerful tools for solving NP-complete problems. However, the intricacy of their modeling presents notable barriers for non-specialists, while the tedious iteration of constraint weights and modeling methodologies also consumes substantial effort on the part of experts. To address these challenges, this study integrates a femtosecond laser-pumped Coherent Ising Machine (CIM) with an LLM-driven agentic system by leveraging the LangGraph and LangChain frameworks. Comprehensive investigations demonstrate that large language models (LLMs) can effectively perform such tasks in modeling as QUBO/Ising model calibration, constraint weight decision iteration and rapid validation of literature-reported schemes. Notably, all these tasks can be fully implemented based on domestic large models, combined with domestically developed CIM hardware, we truly achieve the practical empowerment of quantum CIM that fully relies on all-domestic agentic large models and hardware. This work successfully realizes robust technological integration, laying a solid foundation for subsequent research. Nevertheless, it also identifies the persisting challenges in the two cutting-edge fields of large models and quantum computing at the current stage. Encouragingly, we unexpectedly discover a promising new paradigm where accumulated knowledge from agent-assisted quantum computing iterations reciprocally enhances the agent's own problem-solving capability, thereby addressing these challenges.

---

### KT4EQG: Personalized Exercise Question Generation via Knowledge Tracing

Authors: Xinyi Gao, Qiucheng Wu, Lu Ding, Q. Vera Liao, Kaizhi Qian, Ying Xu, Shiyu Chang, Yang Zhang
Published: 2026-04-24
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2605.23933v2

Educational Question Generation (EQG) aims to synthesize customized exercise questions that enhance student learning. An effective EQG system should ideally personalize questions for each student by modeling the student's knowledge state and generating questions that provide the greatest learning benefit. However, few existing EQG approaches are able to achieve such fine-grained personalization. In this paper, we explore how EQG can benefit from knowledge tracing (KT), which models students' knowledge states based on historical performance and predicts future performance. We propose KT4EQG, a personalized EQG framework that generates effective questions for individual students under the guidance of a KT model. Specifically, KT4EQG seeks to maximize a student's potential improvement in overall knowledge mastery by leveraging the KT model to select the most suitable knowledge concept for the student to practice. An LLM-based question generator is then trained to produce a question faithfully grounded in the selected concept. Experimental results on XES3G5M and MOOCRadar show that KT4EQG consistently generates more effective questions than methods with limited or no personalization.

---

### RAG4Outcome: A Retrieval-Augmented Multimodal Framework for Prognostic Prediction in Chronic Osteomyelitis

Authors: Daqian Shi, Pei Han, Jishizhan Chen, Yang Wang, Xiaolei Diao, Xianyou Zheng, Pengfei Cheng
Published: 2026-04-24
Categories: cs.IR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.22833v1

Chronic osteomyelitis presents substantial prognostic challenges due to its high recurrence risk and complex postoperative recovery trajectories. Traditional assessment often relies on manual scoring systems, which limit scalability, efficiency, and consistency in clinical practice. Furthermore, the heterogeneous nature of clinical data poses challenges for current multimodal learning approaches that require aligned inputs and large annotated datasets. In this work, we propose RAG4Outcome, a retrieval-augmented generation (RAG) framework for prognostic prediction in chronic osteomyelitis. Our method integrates multimodal clinical data, including PET-CT imaging reports, structured surgical and diagnostic records, and unstructured follow-up notes, into a unified prediction pipeline. By combining a domain-specific retrieval corpus with expert-guided prompting, the framework enables more interpretable, evidence-grounded, and clinically reliable prognosis. Preliminary results on real-world cases demonstrate promising effectiveness and clinical alignment, highlighting the potential of RAG4Outcome for AI-assisted infection management and postoperative decision support.

---

### From Demographics to Survey Anchors: Evaluating LLM Agents for Modeling Retirement Attitudes

Authors: Rubén Garzón, Pauline Baron, Vincent Grari, Jonne Kamphorst, Michael Bernstein, Marcin Detyniecki
Published: 2026-04-24
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.16303v1

Large language models (LLM) agents may offer tools to predict human responses to surveys. A common technique for defining these agents uses only demographics, for example country, age, gender, employment status, income, education and marital status. We compare the predictive accuracy of demographic agents to that of survey agents defined with a larger set of in-domain survey responses. We test both approaches in predicting responses to the multidisciplinary, cross-national Survey of Health, Ageing and Retirement in Europe (SHARE), focusing on five variables from three policy-relevant constructs around personal finance. In these three constructs, we observe that, compared to survey agents trained on broader data, demographics-only agents (1) exhibited a central tendency bias, skewing answers toward population means, and (2) were unrealistically accurate, failing to reproduce the incorrect answers and "don't know" responses typical of human respondents. These performance differences are further substantiated through the replication of a hierarchical regression analysis from prior retirement planning research. Agents based solely on demographic information reproduce the outcome that financial risk tolerance, future time perspective, and knowledge of retirement planning each are predictive of retirement savings. However, only the survey-anchored agents succeed in reproducing the interaction among these three factors. These findings suggest caution in using only demographics to define LLM agents for predicting survey responses.

---

### Toeplitz MLP Mixers are Low Complexity, Information-Rich Sequence Models

Authors: Benjamin L. Badger, Ethan Roland
Published: 2026-04-24
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.06683v1

Transformer-based large language models are in some respects limited by the quadratic time and space computational complexity of attention. We introduce the Toeplitz MLP Mixer (TMM), a transformer-like architecture that swaps attention for triangular-masked Toeplitz matrix multiplication over the sequence dimension resulting in $\mathcal{O} (dn \log n)$ time and $\mathcal O(dn)$ space complexity during training and $\mathcal O(dn)$ time and space at inference prefill. Despite the lack of sophisticated input modulation or state maintenance present in other sub-quadratic architectures, TMMs yield greater training efficiency in terms of loss achieved per compute and device memory. We demonstrate that TMMs are capable of retaining more input information resulting in improved copying ability, which we argue results from a lack of architectural biases. Consistent with higher input information retention, TMMs exhibit superior information retrieval and in-context learning benchmark accuracy compared to comparable architectures. We conclude with an analysis from the perspective of operator index theory and show that, counterintuitively, trained Toeplitz layers of causal non-invertible models are more likely to be invertible or nearly so than models that are actually invertible over their inputs.

---

### Fast and Effective Redistricting Optimization via Composite-Move Tabu Search

Authors: Hai Jin, Diansheng Guo
Published: 2026-04-24
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2605.06682v1

Spatial redistricting is a practical combinatorial optimization problem that demands high-quality solutions, rapid turnaround, and flexibility to accommodate multi-criteria objectives and interactive refinement. A central challenge is the contiguity constraint: enforcing contiguity in integer-programming or heuristic search can severely shrink the feasible neighborhood, weaken exploration, and trap the search in poor local optima. We introduce a composite-move Tabu search (CM-Tabu) that systematically expands the feasible neighborhood space in Tabu search while preserving contiguity. When a boundary unit cannot be reassigned individually without disconnecting its district, our method identifies a minimal set of units that can move together, or a pair of units (or sets of units) that can be switched, as a contiguity-preserving composite move. Candidate single-unit and composite moves are generated in linear time by analyzing each district's contiguity graph using articulation points and biconnected components. Extensive experiments demonstrate that the proposed approach substantially improves solution quality, run-to-run robustness, and computational efficiency relative to traditional Tabu search and other baselines. For example, in the Philadelphia case, the approach can consistently attain the theoretical global optimum in population-equality and support multi-criteria trade-offs. CM-Tabu delivers optimization performance suitable for real-world practices and decision-support workflows.

---

### BRITE: A Benchmark for Reliable and Interpretable T2V Evaluation on Implausible Scenarios

Authors: Advait Tilak, Jiwon Choi, Nazifa Mouli, Wei Le
Published: 2026-04-24
Categories: cs.MM, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2605.00873v2

The rapid advancement of photorealistic Text-to-Video (T2V) generation brings in an urgent need for up-to-date evaluation methods. Existing benchmarks largely overlooked implausible scenarios and do not measure audio-visual alignment. We introduce BRITE, the first framework that unifies (1) implausible prompting, (2) fine-grained assessment of audio-visual consistency, and (3) QA-based interpretable evaluation into a comprehensive T2V benchmark. Unlike fully automated Multimodal LLM-based pipelines, which are prone to hallucination and prompt ambiguity, BRITE guarantees reliability through a rigorous human-in-the-loop protocol for benchmark creation. Evaluating five state-of-the-art models (Sora 2, Veo 3.1, Runway Gen4.5, Pixverse V5.5, and Qwen3Max), we reveal a critical performance gap: while models excel at static object composition, they exhibit significant degradation in object-action binding and audio-visual synchronization. Our framework offers the community a reliable, interpretable benchmark and evaluation framework that can detect and locate limitations in the next generation of T2V models, especially for off-manifold prompts

---

### Multi-View Hierarchical Representation Learning of Fetal Hemodynamics for Maternal Hypertension Detection at the Edge

Authors: Alireza Rafiei, Anahí Venzor Strader, Esteban Castro Aragón, Victoriana Rosibely Sut Serech, Enma Carolina Coyote Ixen, Reza Sameni, Peter Rohloff, Gari D. Clifford, Nasim Katebi
Published: 2026-04-24
Categories: eess.SP, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2605.00872v1

Hypertensive disorders of pregnancy remain a leading cause of maternal and fetal morbidity worldwide, yet diagnosis relies on intermittent cuff-based blood pressure measurements that are prone to bias and fail to capture continuous physiological dynamics. Growing evidence suggests that fetal cardiovascular activity is associated with maternal-placental hemodynamics and may encode markers of maternal hypertension. To analyze this, we collected a large-scale dataset of fetal one-dimensional Doppler ultrasound recordings paired with maternal blood pressure from 3,255 pregnant women across 8,170 antenatal visits in rural Guatemala. We developed AutoHyPE, a hierarchical attention network that models short- and long-term signal structure, incorporating a novel prototype-based contrastive learning and multi-view strategy to enhance representation robustness under long-tailed class distribution and biological variability. AutoHyPE achieved an AUROC of 0.80 for maternal hypertension detection, outperforming baseline approaches while maintaining balanced performance across classes, with no performance degradation in an edge deployment scenario. Our findings demonstrated that fetal cardiac mechanical activity contains hemodynamic features indicative of maternal hypertension status. This supports a promising paradigm shift toward continuous, objective monitoring of maternal health using existing, low-cost ultrasound technology and introduces a complementary approach to traditional methods based on blood pressure measurements, advancing scalable prenatal care.

---

### NAKUL-Med: Spectral-Graph State Space Models with Dynamics Kernels for Medical Signals

Authors: Badri N. Patro, Vijay S. Agneeswaran
Published: 2026-04-24
Categories: eess.SP, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.00871v1

State space models (SSMs) achieve linear-time complexity but struggle with multi-channel physiological signals due to three limitations: fixed kernels cannot capture multi-scale temporal dynamics (motor preparation over hundreds of milliseconds vs. execution transients in tens of milliseconds), Markovian state updates restrict global context for periodic oscillations, and channel-independent processing ignores spatial electrode topology. We introduce NAKUL, extending SSMs for medical signal analysis through three contributions: (1) Dynamic Kernel Generation-parallel SSM branches with varying kernel sizes (3, 5, 7, 11 timesteps) are weighted by a meta-network that analyzes input statistics, enabling adaptive temporal scale selection; (2) Spectral Context Modeling-FFT-based operations with learnable Gaussian frequency band filters capture global periodic patterns in $O(N \log N)$ complexity; (3) Graph-Guided Spatial Attention-fixed electrode topology provides spatial biases to multi-head attention for principled cross-channel interaction. On BCI Competition IV-2a motor imagery (our primary benchmark), NAKUL achieves 91.7$\pm$0.6\% accuracy, matching EEG-Conformer (92.1$\pm$0.7\%) while using 28\% fewer parameters (2.5M vs 3.5M) and 2.0$\times$ faster inference (4.3ms vs 8.7ms). The model generalizes to EEG emotion recognition (83.6\%), multimodal EEG-fMRI (91.4\%), and medical imaging (92.8\% on ultrasound), demonstrating architectural versatility. Ablations show dynamic kernels contribute +2.6\% and exhibit interpretable scale selection patterns correlated with known neural dynamics.

---

### An Algorithm for On-Sensor Agnostic Detection of Changes in Human Activity for Ultra-Low-Power Applications

Authors: Sara Rimoldi, Arianna De Vecchi, Hazem Hesham Yousef Shalby, Federica Villa
Published: 2026-04-24
Categories: eess.SP, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.00870v1

Wearable devices running Human Activity Recognition(HAR) on Inertial Measurement Units~(IMUs) waste energy by performing continuous classification for each window, even during long periods of unchanged activity. We address this with a lightweight change-detection gate: a non-parametric algorithm based on dynamic template matching that runs continuously at only approximately 16kFLOPs per step, requires no offline training, and does not need prior definition of target activity classes. The gate invokes the full HAR network only when it detects an activity change, reducing the computational load by over 67% in realistic monitoring settings. The algorithm is evaluated on smart glasses, smartwatch, and smartphone data, requiring only a brief device-specific calibration phase. The gate achieves 98% sensitivity on UCA-EHAR, ensuring no genuine activity transition is missed, while 75% specificity keeps unnecessary HAR invocations low. Results on WISDM are 97% sensitivity and 76% specificity, demonstrating robustness and flexibility to various settings.

---

### ROSA: Robust and Energy-Efficient Microring-Based Optical Neural Networks via Optical Shift-and-Add and Layer-Wise Hybrid Mapping

Authors: Huifan Zhang, Yun Hu, Caizhi Sheng, Yurui Qu, Pingqiang Zhou
Published: 2026-04-24
Categories: cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2605.00032v1

This work presents ROSA, a microring-based optical neural network architecture that improves robustness and energy efficiency using an optical shift-and-add (OSA) module and a layer-wise hybrid mapping strategy. It introduces a noise-aware voltage-to-weight model considering DAC and thermal variations, and a workload-aware framework to co-optimize MRR array size and layer-wise dataflow. Optimized arrays reduce the aggregated relative energy-delay product (EDP) by 64% and 26% compared with DEAP-CNNs and a general compact array, respectively. OSA further contributes 29% EDP reduction. The proposed hybrid mapping strategy improves CIFAR-10 accuracy by 8.3% over weight-stationary mapping while achieving an average 54.7% lower EDP than DEAP-CNNs.

---

### How Hard Is Continuous Clustering? Lower Bounds from the Existential Theory of the Reals

Authors: Angshul Majumdar
Published: 2026-04-24
Categories: cs.CC, cs.LG
arXiv: https://arxiv.org/abs/2604.26972v1

This paper studies the computational difficulty of clustering problems that are defined directly on a continuous probability density. Rather than working with finite samples, we assume the density is given as a polynomial and ask whether it contains certain cluster structures. Four natural questions are examined. First, do there exist several points with high density that are far apart from each other. Second, do two high density points have a midpoint with low density, creating a valley between them. Third, does the region where the density is above a threshold have at least a given number of separate connected pieces. Fourth, does that same region contain a hole, meaning a loop that cannot be shrunk to a point. We prove that the first two problems, separated points and valley detection, are exactly as hard as the existential theory of the reals, a complexity class that contains NP and is believed to be strictly larger. In contrast, the topological problems of counting connected pieces and detecting holes are at least as hard as the existential theory of the reals, but their exact complexity remains open. Placing them inside that class would need a major advance in real algebraic geometry. These results give the first rigorous classification of exact continuous clustering inside the real polynomial hierarchy. They also show that even basic clustering criteria are not NP complete unless unexpected collapses occur.

---