# Research Papers — 2026-04 · bundle page 95 of 233 > Full-text markdown of papers #4701–4750 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/95 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/94.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/96.md) ### Consent Chain Degradation in Embodied Multi-Agent Systems: Bridging the Gap Between AI Agent Governance and Robot Ethics Authors: Mehmet Haklidir Published: 2026-04-17 Categories: cs.CY, cs.AI, cs.MA, cs.RO arXiv: https://arxiv.org/abs/2605.16300v1 Robotic systems are moving from isolated platforms to interconnected multi-agent ecosystems that operate in human environments. This shift raises a governance problem that existing frameworks do not address: how does consent propagate, degrade, and break down across chains of delegation between embodied autonomous agents? The AI ethics community has begun to study consent for digital software agents, and the HRI community has examined consent in dyadic human-robot encounters. Neither body of work covers what happens when physical robots delegate tasks to other robots in ways that affect humans. This paper introduces consent chain degradation (CCD), a conceptual framework for analyzing how the specificity, validity, and scope of human consent erodes as authority passes through multi-robot delegation chains. We propose a three-layer governance architecture, the Consent Runtime Verification Framework for Embodied Agents (CoRVE), which integrates consent scope modeling, delegation chain tracking, and physical irreversibility assessment. Three scenarios in healthcare, domestic, and industrial robotics show how CCD arises in practice, including a worked numerical example. A regulatory gap analysis covering the EU AI Act, the GDPR, the Machinery Regulation, and the Revised Product Liability Directive shows that all four instruments leave core CCD dimensions unaddressed. --- ### ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Authors: Yixu Huang, Xinglei Yu, Zhongyu Wei Published: 2026-04-17 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.16299v2 Large Language Models (LLMs) excel at code generation but remain heavily reliant on large-scale annotated solutions and verification-based supervision, which constrains scalability and hinders sustained self-improvement. Recent solver--verifier frameworks exploit program execution as an automatic supervision signal, but their effectiveness degrades as solvers become moderately strong: verifier-generated tests increasingly confirm semantic correctness rather than exposing the remaining failure modes. We propose \textbf{ACE}, a self-evolving code generation framework based on a solver--adversary architecture that prioritizes active failure discovery through execution-centric supervision. A single LLM alternates between generating candidate programs and producing adversarial unit test inputs optimized to induce execution-level failures, such as runtime errors, exceptions, or non-termination. Supervision is derived solely from execution outcomes: robust programs are selected for supervised fine-tuning, while adversarial tests are optimized via Kahneman--Tversky Optimization using execution-derived preferences. Notably, the entire training loop requires no ground-truth code or external reward models. Experiments on CodeContests, MBPP, and LiveCodeBench demonstrate that ACE consistently outperforms strong solver--verifier baselines, achieving 3--7\% absolute gains in pass@1, with larger improvements on out-of-distribution benchmarks, while maintaining competitive or improved inference efficiency. --- ### Data-Driven Variational Basis Learning Beyond Neural Networks: A Non-Neural Framework for Adaptive Basis Discovery Authors: Andrew Kiruluta Published: 2026-04-17 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.05221v1 Classical representation systems such as Fourier series, wavelets, and fixed dictionaries provide analytically tractable basis expansions, but they are not intrinsically adapted to the empirical structure of modern high-dimensional data. Neural networks overcome this limitation by learning features from data, yet they do so through layered nonlinear parameterizations that often sacrifice interpretability, explicit control over basis structure, and mathematical transparency. In this manuscript we develop a non-neural alternative that learns basis functions directly from data through variational optimization. The proposed framework, termed Data Driven Variational Basis Learning (DVBL), treats basis atoms as primary optimization variables and learns them jointly with sample-specific coefficients and, when appropriate, a latent linear evolution operator. This yields a data-adaptive basis expansion that remains explicit, interpretable, and amenable to rigorous analysis. We formulate the model, establish existence of minimizers, prove blockwise descent properties for an alternating minimization algorithm, give conditions for coefficient recovery and basis identifiability, and show how manifold and dynamical regularization can be integrated without invoking neural architectures. We also discuss the conceptual novelty of the framework relative to classical dictionary learning, spectral methods, Koopman operator methods, and deep representation learning. --- ### MidSteer: Optimal Affine Framework for Steering Generative Models Authors: Tatiana Gaintseva, Andrew Stepanov, Ziquan Liu, Martin Benning, Gregory Slabaugh, Jiankang Deng, Ismail Elezi Published: 2026-04-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.05220v3 Steering intermediate representations has emerged as a powerful strategy for controlling generative models, particularly in post-deployment alignment and safety settings. However, despite its empirical success, it currently lacks a comprehensive theoretical framework. In this paper, we bridge this gap by formalizing the theory of concept steering. First, we establish a link between steering and affine concept erasure, proving that the standard approach for removing unwanted behaviors is a special case of LEACE (a closed-form method for affine erasure). Next, we formulate a principled theoretical framework for concept switching, LEACE-Switch, and characterize the assumptions under which it provides an optimal affine solution. Building on this analysis, we then introduce MidSteer (Minimal Disturbance concept Steering), a more general affine framework for concept manipulation that relaxes these assumptions and enables directed, minimal-disturbance transformations. We demonstrate that MidSteer performs favorably across a range of tasks, modalities, and architectures, including vision diffusion models and large language models. --- ### Sparse Prefix Caching for Hybrid and Recurrent LLM Serving Authors: Mikhail Shirokikh, Sergey Nikolenko Published: 2026-04-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.05219v1 Prefix caching is a key latency optimization for autoregressive LLM serving, yet existing systems assume dense per-token key/value reuse. State-space models change the structure of the problem: a recurrent layer can resume from a single stored state rather than requiring the entire token history. This asymmetry opens a new design point between no reuse and dense caching: store exact recurrent states at a sparse set of checkpoint positions and, on a cache hit, resume from the deepest stored checkpoint and recompute the remaining suffix exactly. We formalize sparse prefix caching as checkpoint placement under a distribution over overlap depths, yielding an exact O(NM) dynamic program. For use cases where requests share a non-trivial prefix (e.g. asking different questions about a single long document), we show that our method consistently improves the Pareto frontier traced by standard heuristics on real-world data. Across QuALITY and System Prompts, distribution-aware placement dominates every fixed-budget baseline on the measured layer-group Pareto frontier and matches or outperforms the strongest heuristic (block caching) while typically using substantially fewer checkpoints, with the largest gains at low checkpoint budgets where the overlap distribution is most non-uniform. The method is most relevant when many requests share a substantial but not identical prefix within a retained cache entry. It preserves exact outputs, does not change the recurrent computation itself or require new recurrent update kernels, applies to recurrent/SSM layers whose hidden state can be extracted and restored exactly, and for hybrid models can be combined with existing KV-cache compression techniques. --- ### Horizon-Constrained Rashomon Sets for Chaotic Forecasting Authors: Gauri Kale, Rahul Vishwakarma, Holly Diamond, Ava Hedayatipour, Amin Rezaei Published: 2026-04-17 Categories: cs.LG, cs.AI, math.DS, nlin.CD arXiv: https://arxiv.org/abs/2605.05218v1 Predictive multiplicity and chaotic dynamics represent two fundamental challenges in machine learning that have evolved independently despite their conceptual connections. We bridge this gap by introducing horizon-constrained Rashomon sets, a theoretical framework that characterizes how model multiplicity evolves with prediction horizon in chaotic systems. Unlike static prediction tasks where the Rashomon set remains fixed, chaos induces exponential divergence among initially similar models, fundamentally transforming the nature of predictive equivalence. We prove that the effective Rashomon set contracts exponentially with lead time at a rate determined by the maximum Lyapunov exponent and introduce Lyapunov-weighted metrics that provide tighter bounds on predictive disagreement. Leveraging these insights, we develop decision-aligned selection algorithms that choose among near-optimal models based on downstream utility rather than forecast accuracy alone. Extensive experiments on synthetic chaotic systems (Lorenz-96, Kuramoto-Sivashinsky) and real-world applications (wind power, traffic, weather) demonstrate that our framework improves decision quality by 18-34\% while maintaining competitive predictive performance. This work establishes the first rigorous connection between chaos theory and predictive multiplicity, providing principled guidance for deploying machine learning in safety-critical chaotic domains. --- ### Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning Authors: Reza Pirayeshshirazinezhad Published: 2026-04-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.05217v1 We propose a self-supervised physics-informed neural network (PINN) framework that adaptively balances physics-based and data-driven supervision for scientific machine learning under data scarcity. Unlike prior PINNs that rely on fixed or heuristic weighting of physics residuals and data loss, our approach introduces a learnable blending neuron that dynamically adjusts the relative contribution of each term based on their uncertainties. This mechanism enables stable training and improved generalization without manual tuning. To further enhance efficiency, we integrate a transfer learning strategy that reuses representations from related domains and adapts them to new physical systems with limited data. We validate the framework for the prediction of heat transfer in liquid-metal miniature heat sinks using only 87 CFD datapoints, where the adaptive PINN achieves an error <8%, outperforming shallow neural networks, kernel methods, and physics-only baselines. Our framework provides a general recipe for embedding physics adaptively into neural networks, offering a robust and reproducible approach for data-scarce problems across various scientific domains, including fluid dynamics and material modeling. --- ### SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees Authors: Yi Xie, Yangyang Xu, Yi Fan, Bo Liu Published: 2026-04-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.05216v1 Large language models (LLMs) with a large number of parameters achieve strong performance but are often prohibitively expensive to deploy. Recent work explores using teams of smaller, more efficient LLMs that collectively match or even outperform a single large model. However, jointly updating multiple agents introduces compounding distribution shifts, making coordination and stability during training difficult. We address this by introducing Sequential Agent Tuning (SAT), a coordinator-free training paradigm. SAT represents the team as a factorized policy and employs block-coordinate updates over agents, enabling scalable, decentralized training without a central controller. Specifically, we develop a sequence-aware, on-policy advantage estimator that conditions on the evolving team policy, coupled with per-agent KL trust regions that isolate occupancy drift. Theoretically, this framework provides two critical guarantees. First, it ensures monotonic improvement, stabilizing the training process. Second, it establishes provable plug-and-play invariance: any agent can be upgraded to a stronger model without retraining the rest of the team, with a formal guarantee that the performance bound improves. Empirically, a team of three 4B agents (12B total) trained with SAT surpasses the much larger Qwen3-32B on AIME24/25 benchmarks by 3.9\% on average. We validate our plug-and-play theory by swapping in two 8B agents, which boosts the composite score by 10.4\%. We provide code and appendix of proof at https://github.com/Yydc/SAT-AAMAS --- ### Layout-Aware Representation Learning for Open-Set ID Fraud Discovery Authors: Jinxing Li, Nicholas Ren, Cathy Chang, Hongkai Pan, Daniel George Published: 2026-04-17 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.05215v1 Identity-document fraud detection is not a stationary binary classification problem. Adaptive attackers modify templates and fabrication pipelines, making historical fraud labels stale, and successful forgeries recur at scale as coherent campaigns. We therefore study layout-aware representation learning for open-set fraud discovery rather than only closed-set classification. We adapt DINOv3 to the document domain via context-aware SimMIM fine-tuning and supervised metric learning with composite loss that encourages inter-class separability and intra-class compactness. The model is trained with U.S. IDs only. With a lightweight MLP and softmax classifier, the embedding achieves 99.83% layout classification accuracy on Canadian layouts. Moreover, on a dataset of 20,448 Canadian IDs, embedding-space analysis surfaces 276 adaptive physical-fraud cases, including 222 not surfaced by incumbent detectors. The embedding supports similarity-based expansion from a single confirmed seed to additional related cases not linked by conventional metadata graphs. The layout-aware document embeddings provide a production-aligned basis for discovering novel and campaign-scale fraud under distribution shift. --- ### MedMamba: Recasting Mamba for Medical Time Series Classification Authors: ZhengXiao He, Huayu Li, Xiwen Chen, Janet M Roveda, Jinghao Wen, Siyuan Tian, Ao Li Published: 2026-04-17 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.05214v1 Medical time series, such as electrocardiograms (ECG) and electroencephalograms (EEG), exhibit complex temporal dynamics and structured cross-channel dependencies, posing fundamental challenges for automated analysis. Conventional convolutional and recurrent models struggle to capture long-range dependencies, while Transformer-based approaches incur quadratic complexity and often introduce redundant interactions that are misaligned with the intrinsic structure of physiological signals. To address these limitations, we propose MedMamba, a principle-driven multi-scale bidirectional state space architecture tailored for medical time series classification. Our design is guided by three key inductive biases of physiological signals: spatial centralization, multi-timescale temporal composition, and non-causal contextual dependency. These principles are instantiated through a lightweight channel-mixing module for cross-channel reparameterization, multi-scale convolutional tokenization for temporal decomposition, and bidirectional Mamba blocks for efficient global context modeling with linear complexity. Extensive experiments on six benchmark datasets spanning EEG, ECG, and human activity signals demonstrate that MedMamba consistently outperforms state-of-the-art methods across diverse modalities. Notably, it achieves 85.97% accuracy on PTB and establishes new state-of-the-art performance on the challenging ADFTD dataset (54.72% accuracy and 52.01% F1-score). Strong results on long-sequence benchmarks, such as SleepEDF, further validate its capability in modeling long-range dependencies. Moreover, MedMamba achieves a speedup of 4.6x in inference, highlighting its practicality for real-time clinical deployment. These results suggest that principle-guided state space modeling offers an effective and scalable alternative to Transformer-based approaches for medical time series analysis. --- ### Planar Gaussian Splatting with Bilinear Spatial Transformer for Wireless Radiance Field Reconstruction Authors: Jinghan Zhang, Xitao Gong, Qi Wang, Richard A. Stirling-Gallacher, Giuseppe Caire Published: 2026-04-17 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2604.25945v1 Wireless radiance field (WRF) reconstruction aims to learn a continuous, queryable representation of radio frequency characteristics over 3D space and direction, from which specific quantities, such as the spatial power spectrum (SPS) at a receiver given a transmitter position, can be predicted. While Gaussian splatting (GS)-based method has surpassed Neural Radiance Fields (NeRF)-based method for this task, existing adaptations largely transplant vision pipelines, limiting physical interpretability and accuracy. We introduce BiSplat-WRF, a planar GS framework that retains the expressiveness of 3D GS while removing unnecessary projections and incorporating global EM coupling and mutual scattering among primitives. Each primitive is a 2D planar Gaussian with 3D coordinates, rendered directly on the angular domain of the SPS. A bilinear spatial transformer (BST) aggregates inter-primitive relations on an angular grid and, via attention, captures long-range electromagnetic dependencies, thereby enforcing globally aware EM interactions that reflect the complex physics of the wireless environment. On spatial spectrum synthesis task, BiSplat-WRF surpasses NeRF-based and prior GS-based baselines with respect to the Structural Similarity Index (SSIM); comprehensive ablation studies validate the contribution of BST. We also provide a larger BiSplat-WRF+ variant that further increases SSIM at a higher computation cost, serving as a strong reference for future studies. --- ### A Randomized PDE Energy driven Iterative Framework for Efficient and Stable PDE Solutions Authors: Yi Bing, Zheng Ran, Fu Jinyang, Liu Long, Peng Xiang Published: 2026-04-17 Categories: cs.LG, cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2604.25943v1 Efficient and stable solution of partial differential equations (PDEs) is central to scientific and engineering applications, yet existing numerical solvers rely heavily on matrix based discretizations, while learning based methods require costly training and often suffer from limited generalization. In this work, we proposes a PDE energy driven framework that solves PDEs through physically constrained diffusion iterations, without relying on classical matrix based finite element assembly or data driven neural network training. The proposed method evolves arbitrary random initial fields through PDE energy driven implicit iterations combined with Gaussian smoothing, while strictly enforcing boundary conditions at each iteration. The proposed formulation is applied to representative one dimensional Poisson, Heat, and viscous Burgers equations, covering both steady state and transient problems. Numerical results demonstrate stable convergence to the unique physical solution from random initializations, with accurate resolution of sharp gradients and controlled Mean Squared Error (MSE) across a wide range of discretization parameters. Detailed comparisons with analytical solutions indicate that the framework achieves competitive accuracy and stability. Overall, the proposed framework provides a fast, flexible, and physically consistent alternative to traditional numerical solvers, offering a potential pathway for scalable PDE solutions in both research and engineering applications. --- ### A Multimodal and Explainable Machine Learning Approach to Diagnosing Multi-Class Ejection Fraction from Electrocardiograms Authors: Catherine Ning, Yu Ma, Cindy Beini Wang, Sean McMahon, Joseph Radojevic, Steven Zweibel, Dimitris Bertsimas Published: 2026-04-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.25942v1 Left ventricular ejection fraction (LVEF) assessment depends on echocardiography, limiting access in primary care and resource-constrained settings. We developed a multimodal machine-learning framework that combines engineered 12-lead ECG timeseries features with structured EHR variables to classify LVEF into four clinically used strata: normal (>50%), mildly reduced (40-50%), moderately reduced (30-40%), and severely reduced (<30%). To support model explainability, we identified the most influential ECG and EHR features via SHAP attributions. Using retrospective data from Hartford HealthCare, we trained XGBoost models on 36,784 ECG-echocardiogram pairs from 30,952 outpatients and evaluated temporal generalizability on 19,966 ECGs from a subsequent period. The multimodal model achieved one-vs-rest AUROCs of 0.95 (severe), 0.92 (moderate), 0.82 (mild), and 0.91 (normal), outperforming ECG-only and EHR-only baselines, and maintained performance under temporal validation. This work supports ECG-based, multimodal LVEF stratification as a practical screening and triage aid to prioritize confirmatory imaging where resources are limited. --- ### Application of a Mixture of Experts-based Foundation Model to the GlueX DIRC Detector Authors: Cristiano Fanelli, James Giroux, Cole Granger, Justin Stevens Published: 2026-04-17 Categories: physics.data-an, cs.LG, hep-ex, nucl-ex, physics.ins-det arXiv: https://arxiv.org/abs/2604.24775v1 We present a Mixture-of-Experts-based foundation model applied to the GlueX DIRC detector at Jefferson Lab, demonstrating its utility as a unified framework for fast simulation, particle identification, and hit-level noise filtering of Cherenkov photons. By leveraging a single shared transformer backbone across all tasks, the approach eliminates the fragmentation of task-specific pipelines while maintaining competitive-and in several cases superior-performance relative to established methods. The model operates directly on low-level detector inputs, performing hit-by-hit autoregressive generation over split spatial and temporal vocabularies with continuous kinematic conditioning, and supports class-conditional generation of pions and kaons through its Mixture-of-Experts architecture. We benchmark against the standard geometrical reconstruction and prior deep learning methods across the full kinematic phase space of the GlueX DIRC, demonstrating that the foundation model framework transfers effectively to this detector without architectural modification. This work positions the foundation model as a practical and scalable alternative to the suite of task-specific models currently proposed for GlueX DIRC analysis. --- ### Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Use Authors: Ramit Pahwa, Apoorva Beedu, Parivesh Priye, Rutu Gandhi, Saloni Takawale, Aruna Baijal, Zengli Yang Published: 2026-04-17 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2604.22821v2 Voice assistants increasingly rely on Speech Language Models (SpeechLMs) to interpret spoken queries and execute complex tasks, yet existing benchmarks lack domain breadth, acoustic diversity, and compositional reasoning complexity to evaluate tool-calling performance. We introduce Audio2Tool, a large-scale dataset comprising approximately 30,000 queries designed to assess tool-calling capabilities of SpeechLMs across three primary domains: Smart Car, Smart Home, and Wearables. Our benchmark features a multi-tier complexity hierarchy, ranging from simple direct commands to complex multi-intent and needle-in-a-haystack extraction to isolate distinct failure modes. To ensure realism, we employ zero-shot voice cloning text-to-speech synthesis and diverse noise profiles to simulate in-the-wild conditions. Evaluations of state-of-the-art SpeechLMs and ASR-LLM pipelines show strong performance on simple commands but significant degradation under compositional and acoustic challenges. Code and dataset are publicly available on the project page: https://audio2tool.github.io/. --- ### Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Long-Horizon Workflows Authors: Luay Gharzeddine, Samer Saab Published: 2026-04-17 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2604.22820v2 Long-horizon tool-using tasks sometimes benefit from revisiting earlier subtasks, but explicit revisitation also adds routing, coordination, and token cost. We study complete cyclic subtask graphs for large language model (LLM) agents: a workflow controller in which executable subtasks are fully connected and a unified state-analysis-and-routing agent selects transitions from natural-language criteria. We evaluate task-specific (Spec-Cyc) and benchmark-generic (Gen-Cyc) cyclic graphs on TextCraft, ALFWorld, and Finance-Agent against ReAct and dependency-directed workflows. Our main dependency-directed controller is DepDAG, which permits same-subtask retry while preserving forward dependency constraints. The evaluated case studies suggest three workflow signatures rather than a universal architecture ranking. TextCraft behaves like a prerequisite-chain setting, where cyclic routing often adds overhead. ALFWorld behaves like a partially observable recovery setting, where explicit revisitation improves exploration and success. Finance-Agent behaves like an open-ended evidence-synthesis setting, where workflow control alone is insufficient without stronger retrieval, grounding, and verification mechanisms. We add a qualified workflow-signature matrix, fault-injection robustness analysis, token-cost accounting, graph-stability reporting, transition-audit checks for DepDAG, and failure-mode structure for trajectory analysis. Overall, complete cyclic subtask graphs are best understood as a diagnostic workflow-control tool: they expose when flexible backtracking is worth its cost and when simpler, locally retrying, or sparsified controllers are preferable. --- ### Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows Authors: Luay Gharzeddine, Samer Saab Published: 2026-04-17 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2604.22820v1 Long-horizon tool-using tasks sometimes benefit from revisiting earlier subtasks for recovery and exploration, but added multi-agent workflow flexibility can also introduce coordination overhead and substantial inference cost. We study complete cyclic subtask graphs, a deliberately maximally flexible multi-agent architecture in which executable subtask nodes are fully connected and a unified state-analysis-and-routing agent selects transitions using natural-language criteria. This makes unrestricted revisitation explicit and directly analyzable at the subtask level. We evaluate task-specific (Spec-Cyc) and benchmark-generic (Gen-Cyc) graphs on TextCraft, ALFWorld, and Finance-Agent, with ablations over planner/executor/router strength, tool exposure (generalist vs specialized), $n$-shot successful trajectory summaries, and fault-injected random subtask perturbations. The benchmarks expose three distinct regimes. ALFWorld highlights a setting where explicit revisitation supports recovery and exploration; TextCraft, a largely prerequisite-chain domain, often favors the efficiency of simpler forward execution; and Finance-Agent remains bottlenecked by retrieval, grounding, and evidence synthesis more than by workflow flexibility alone. Shared-win token comparisons further show that the added flexibility can be substantially more expensive than a single ReAct agent. Overall, we use complete cyclic subtask graphs as a maximally flexible experimental lens for measuring when multi-agent revisitation helps, when it mainly adds coordination cost, and when external task bottlenecks dominate. --- ### Spectral Kernel Dynamics for Planetary Surface Graphs: Distinction Dynamics and Topological Conservation Authors: Jnaneshwar Das Published: 2026-04-17 Categories: math.DS, astro-ph.EP, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2604.20887v1 The spectral kernel field equation R(k) = T(k) lacks a conservation-law analog. We prove (i) the fixed-point flow is strictly volume-expanding (tr DF > 0), precluding automatic conservation, and (ii) the conservation deficit per mode equals the Hessian stability margin exactly: D_m = -Delta'. Closing the deficit requires a scene-side compensating contribution, which we formalise as the distinction dynamics equation dc/dt = G(c, h_t), with MaxCal-optimal realisation G_opt. On fixed-topology 3D surface graphs we derive a conditional topology-preserving compression theorem: retaining k >= beta_0 + beta_1 modes (under a spectral-ordering assumption) preserves all Betti-number charges; we include a worked short-cycle counterexample (figure-eight) calibrating when the assumption fails. A triple necessary spectral diagnostic -- Fiedler-mode concentration, elevated curl energy, anomalous beta_1 -- is derived for planetary drainage networks at O(N) cost. Two internal real-data sequences serve as preliminary consistency checks; full benchmarks and adaptive-topology extensions are deferred. --- ### KinetiDiff: Docking-Guided Diffusion for De Novo ACVR1 Inhibitor Design in Fibrodysplasia Ossificans Progressiva Authors: Aaryan Patel Published: 2026-04-17 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2604.20886v1 We present KinetiDiff, a structure-based framework for de novo kinase inhibitor design that integrates a Geometry-Complete Diffusion Model with real-time AutoDock Vina gradient guidance. By injecting physics-based docking gradients into the diffusion denoising loop, KinetiDiff steers molecule generation toward high-affinity conformations for ACVR1 (ALK2), the causative kinase in Fibrodysplasia Ossificans Progressiva. From 10,000 diffusion samples, the framework produced 9,997 valid molecules. The best candidate achieved $-11.05$ kcal/mol (pKd = 8.10), a 19.2% improvement over the crystallographic reference. The top 100 candidates all exceed the reference, with 100% Lipinski compliance, median synthetic accessibility of 2.67, and internal diversity of 0.790. Systematic ablation across four guidance strategies--Vina-Direct (physics), HNN-Denovo (neural proxy), multi-objective, and unguided--demonstrates that real-time docking guidance dominates on all metrics. We evaluate HNN-Denovo as a computationally efficient alternative (60-fold speedup per step), revealing a domain-mismatch limitation (r = 0.224 correlation with Vina) that explains its inferior performance. These results establish gradient-guided geometric diffusion as a practical approach for generating potent, synthetically accessible inhibitors against rare-disease kinase targets. --- ### What Makes a Bacterial Model a Good Reservoir Computer? Predicting Performance from Separability and Similarity Authors: Laura Alonso Bartolomé, Jean-Loup Faulon, Xavier Hinaut Published: 2026-04-17 Categories: cs.ET, cs.LG, cs.NE, q-bio.MN, q-bio.QM arXiv: https://arxiv.org/abs/2604.19850v1 Biological systems are promising substrates for computation because they naturally process environmental information through complex internal dynamics. In this study, we investigate whether bacterial metabolic models can act as physical reservoirs and whether their computational performance can be predicted from dynamical properties linked to separability and similarity. We simulated the growth dynamics of five bacterial species, one yeast species, and 29 Escherichia coli single-gene deletion mutants using dynamic flux balance analysis (dFBA), with glucose and xylose concentrations as inputs and growth curves as reservoir states. Computational performance was assessed on random nonlinear classification tasks using a linear readout, while reservoir properties linked to separability and similarity were characterised through kernel and generalisation ranks computed from growth-curve state matrices. Several microbial models achieved high classification accuracy, showing that bacterial metabolic dynamics can support nonlinear computation. Clear differences were observed between species, with some models converging more rapidly and others reaching higher maximum accuracy, revealing a trade-off between convergence speed and peak performance. In contrast, all E. coli mutants were dominated by the wild-type model, suggesting that gene deletions reduce the dynamical richness required for efficient computation. The difference between kernel and generalisation ranks was generally associated with improved accuracy, but deviations across models and sensitivity at low rank values limited its predictive power in practice. Overall, these results show that bacterial metabolic models constitute promising substrates for reservoir computing and provide a first step towards identifying microbial strains with favourable computational properties for future experimental implementations. --- ### Large Language Models Meet Biomedical Knowledge Graphs for Mechanistically Grounded Therapeutic Prioritization Authors: Chih-Hsuan Wei, Chi-Ping Day, Zhizheng Wang, Christine C. Alewine, Betty Tyler, Hasan Slika, David Saraf, Chin-Hsien Tai, Joey Chan, Robert Leaman, Zhiyong Lu Published: 2026-04-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.19815v1 Drug repurposing is often framed as a candidate identification task, but existing approaches provide limited guidance for distinguishing biologically plausible candidates from historically well-connected ones. Here we introduce DrugKLM, a hybrid framework that integrates biomedical knowledge graph structure with large language model-based mechanistic reasoning to enable mechanistically grounded therapeutic prioritization. Across benchmark datasets, DrugKLM outperforms knowledge graph-only and language model-only baselines, including TxGNN. Beyond improved recall, DrugKLM confidence scores exhibit functional alignment with molecular phenotypes: higher scores are associated with transcriptional signatures linked to improved survival across 12 TCGA cancers. The scoring framework preferentially captures biologically perturbational signals rather than historical indication patterns. Expert curation across five cancers further reveals systematic differences in prioritization behavior, with DrugKLM elevating candidates supported by coherent mechanistic rationale and disease-specific clinical context. Together, these results establish DrugKLM as an evidence-integrative framework that translates heterogeneous biomedical data into mechanistically interpretable and clinically grounded therapeutic hypotheses. --- ### Optimising Urban Flood Resilience Authors: James Mckenna, Christos Iliadis, Vassilis Glenis Published: 2026-04-17 Categories: cs.NE arXiv: https://arxiv.org/abs/2604.18620v1 Due to the increasing frequency and severity of storm events, driven by the escalation of anthropogenic climate change and urban expansion, there is a requirement for increasingly efficient flood risk management strategies. While Blue-Green Infrastructure (BGI) offers a sustainable solution for managing flood risk, optimal implementation is challenging. To help overcome this challenge, this study presents a novel multi-objective optimisation tool that couples a state-of-the-art hydrodynamic model with a bespoke evolutionary algorithm. The use of a fully dynamic hydrodynamic model enables the tool to accurately evaluate the effectiveness of proposed BGI features with respect to property scale flood vulnerability and hazard analysis. This contrasts with alternative approaches which utilise simplified models, which can only reliably predict inundation extents, thus the proposed optimisation tool provides greater certainty regarding the optimality of the solutions. As a hydrodynamic simulation is required to evaluate each candidate solution, the bespoke evolutionary algorithm is specifically designed to minimise the number of simulations required, ensuring the tool is computationally practical. The effectiveness of the tool in this regard is validated via the derivation of exact convergence measures, for a tractable search space, and via comparisons with benchmark algorithms, for an intractable search space. Compared with traditional design practices, the proposed tool offers an automated approach capable of efficiently exploring a wide range of solutions, providing decision-makers with a set of optimal solutions from which they can make informed investment decisions. The presented methods provide a robust framework for optimising a variety of BGI features in complex urban environments. --- ### Know When to Trust the Skill: Delayed Appraisal and Epistemic Vigilance for Single-Agent LLMs Authors: Eren Unlu Published: 2026-04-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16753v1 As large language models (LLMs) transition into autonomous agents integrated with extensive tool ecosystems, traditional routing heuristics increasingly succumb to context pollution and "overthinking". We argue that the bottleneck is not a deficit in algorithmic capability or skill diversity, but the absence of disciplined second-order metacognitive governance. In this paper, our scientific contribution focuses on the computational translation of human cognitive control - specifically, delayed appraisal, epistemic vigilance, and region-of-proximal offloading - into a single-agent architecture. We introduce MESA-S (Metacognitive Skills for Agents, Single-agent), a preliminary framework that shifts scalar confidence estimation into a vector separating self-confidence (parametric certainty) from source-confidence (trust in retrieved external procedures). By formalizing a delayed procedural probe mechanism and introducing Metacognitive Skill Cards, MESA-S decouples the awareness of a skill's utility from its token-intensive execution. Evaluated under an In-Context Static Benchmark Evaluation natively executed via Gemini 3.1 Pro, our early results suggest that explicitly programming trust provenance and delayed escalation mitigates supply-chain vulnerabilities, prunes unnecessary reasoning loops, and prevents offloading-induced confidence inflation. This architecture offers a scientifically cautious, behaviorally anchored step toward reliable, epistemically vigilant single-agent orchestration. --- ### Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents Authors: Eren Unlu Published: 2026-04-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16752v1 Current agent evaluations largely reward execution on fully specified tasks, while recent work studies clarification (11, 22, 2), capability awareness (9, 1), abstention (8, 14), and search termination (20, 5) mostly in isolation. This leaves open whether agents can diagnose why a task is blocked before acting. We introduce the Support-State Triage Audit (SSTA-32), a matched-item diagnostic framework in which minimal counterfactual edits flip the same base request across four support states: Complete (ANSWER), Clarifiable (CLARIFY), Support-Blocked (REQUEST SUPPORT), and Unsupported-Now (ABSTAIN). We evaluate a frontier model under four prompting conditions - Direct, Action-Only, Confidence-Only, and a typed Preflight Support Check (PSC) - using Dual-Persona Auto-Auditing (DPAA) with deterministic heuristic scoring. Default execution overcommits heavily on non-complete tasks (41.7% overcommitment rate). Scalar confidence mapping avoids overcommitment but collapses the three-way deferral space (58.3% typed deferral accuracy). Conversely, both Action-Only and PSC achieve 91.7% typed deferral accuracy by surfacing the categorical ontology in the prompt. Targeted ablations confirm that removing the support-sufficiency dimension selectively degrades REQUEST SUPPORT accuracy, while removing the evidence-sufficiency dimension triggers systematic overcommitment on unsupported items. Because DPAA operates within a single context window, these results represent upper-bound capability estimates; nonetheless, the structural findings indicate that frontier models possess strong latent triage capabilities that require explicit categorical decision paths to activate safely. --- ### ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection Authors: Benjamin Chou, Yi Zhu, Surya Koppisetti Published: 2026-04-17 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2604.16749v1 Audio deepfakes pose a significant security threat, yet current state-of-the-art (SOTA) detection systems do not generalize well to realistic in-the-wild deepfakes. We introduce a novel \textbf{I}n-\textbf{C}ontext \textbf{L}earning paradigm with comparison-guidance for \textbf{A}udio \textbf{D}eepfake detection (\textbf{ICLAD}). The framework enables the use of audio language models (ALMs) for training-free generalization to unseen deepfakes and provides textual rationales on the detection outcome. At the core of ICLAD is a pairwise comparative reasoning strategy that guides the ALM to discover and filter hallucinations and deepfake-irrelevant acoustic attributes. The ALM works alongside a specialized deepfake detector, whereby a routing mechanism feeds out-of-distribution samples to the ALM. On in-the-wild datasets, ICLAD improves macro F1 over the specialized detector, with up to $2\times$ relative improvement. Further analysis demonstrates the flexibility of ICLAD and its potential for deployment on recent open-source ALMs. --- ### TriTS: Time Series Forecasting from a Multimodal Perspective Authors: Xiang Ao Published: 2026-04-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16748v1 Time series forecasting plays a pivotal role in critical sectors such as finance, energy, transportation, and meteorology. However, Long-term Time Series Forecasting (LTSF) remains a significant challenge because real-world signals contain highly entangled temporal dynamics that are difficult to fully capture from a purely 1D perspective. To break this representation bottleneck, we propose TriTS, a novel cross-modal disentanglement framework that projects 1D time series into orthogonal time, frequency, and 2D-vision spaces.To seamlessly bridge the 1D-to-2D modality gap without the prohibitive $O(N^2)$ computational overhead of Vision Transformers (ViTs), we introduce a Period-Aware Reshaping strategy and incorporate Visual Mamba (Vim). This approach efficiently models cross-period dependencies as global visual textures while maintaining linear computational complexity. Complementing this, we design a Multi-Resolution Wavelet Mixing (MR-WM) module for the frequency modality, which explicitly decouples non-stationary signals into trend and noise components to achieve fine-grained time-frequency localization. Finally, a streaming linear branch is retained in the time domain to anchor numerical stability. By dynamically fusing these three complementary representations, TriTS effectively adapts to diverse data contexts. Extensive experiments across multiple benchmark datasets demonstrate that TriTS achieves state-of-the-art (SOTA) performance, fundamentally outperforming existing vision-based forecasters by drastically reducing both parameter count and inference latency. --- ### Incoherent Deformation, Not Capacity: Diagnosing and Mitigating Overfitting in Dynamic Gaussian Splatting Authors: Ahmad Droby Published: 2026-04-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16747v2 Dynamic 3D Gaussian Splatting methods achieve strong training-view PSNR on monocular video but generalize poorly: on the D-NeRF benchmark we measure an average train-test PSNR gap of 6.18 dB, rising to 11 dB on individual scenes. We report two findings that together account for most of that gap. Finding 1 (the role of splitting). A systematic ablation of the Adaptive Density Control pipeline (split, clone, prune, frequency, threshold, schedule) shows that splitting is responsible for over 80% of the gap: disabling split collapses the cloud from 44K to 3K Gaussians and the gap from 6.18 dB to 1.15 dB. Across all threshold-varying ablations, gap is log-linear in count (r = 0.995, bootstrap 95% CI (0.99, 1.00)), which suggests a capacity-based explanation. Finding 2 (the role of deformation coherence). We show that the capacity explanation is incomplete. A local-smoothness penalty on the per-Gaussian deformation field -- Elastic Energy Regularization (EER) -- reduces the gap by 40.8% while growing the cloud by 85%. Measuring per-Gaussian strain directly on trained checkpoints, EER reduces mean strain by 99.72% (median 99.80%) across all 8 scenes; on 8/8 scenes the median Gaussian under EER is less strained than the 1st-percentile (best-behaved) Gaussian under baseline. Alongside EER, we evaluate two further regularizers: GAD, a loss-rate-aware densification threshold, and PTDrop, a jitter-weighted Gaussian dropout. GAD+EER reduces the gap by 48%; adding PTDrop and a soft growth cap reaches 57%. We confirm that coherence generalizes to (a) a different deformation architecture (Deformable-3DGS, +40.6% gap reduction at re-tuned lambda), and (b) real monocular video (4 HyperNeRF scenes, reducing the mean PSNR gap by 14.9% at the same lambda as D-NeRF, with near-zero quality cost). The overfitting in dynamic 3DGS is driven by incoherent deformation, not parameter count. --- ### Why Training-Free Token Reduction Collapses: The Inherent Instability of Pairwise Scoring Signals Authors: Yang Shanglin Published: 2026-04-17 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.16745v1 Training-free token reduction methods for Vision Transformers (ToMe, ToFu, PiToMe, and MCTF) employ different scoring mechanisms, yet they share a closely matched cliff-like collapse at high compression. This paper explains \emph{why}. We develop a diagnostic framework with two tools, ranking consistency $ρ_s$ and off-diagonal correlation $ρ_\text{off}$, that decomposes the collapse into (1)a signal-agnostic error amplifier inherent to layer-wise reduction, predicting convex Pareto curves and $r_{\text{crit}} \propto 1/L$; and (2)shared reliance on \emph{pairwise} similarity signals whose ranking consistency degrades from $ρ_s{=}0.88$ to $0.27$ in deep layers. Pairwise rankings are inherently unstable ($O(N_p^2)$ joint perturbations) while unary signals enjoy greater stability ($O(N_p)$ perturbations, CLT). From three design principles derived from this diagnosis, we construct CATIS as a constructive validation: unary signals raise the trigger threshold, triage suppresses the gain. On ViT-Large at 63% FLOPs reduction, CATIS retains 96.9% of vanilla accuracy (81.0%) on ImageNet-1K where all baselines collapse to 43--65%. --- ### Evaluating Adaptive Personalization of Educational Readings with Simulated Learners Authors: Ryan T. Woo, Anmol Rao, Aryan Keluskar, Yinong Chen Published: 2026-04-17 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.16744v2 We present a framework for evaluating adaptive personalization of educational reading materials with theory-grounded simulated learners. The system builds a learning-objective and knowledge-component ontology from open textbooks, curates it in a browser-based Ontology Atlas, labels textbook chunks with ontology entities, and generates aligned reading-assessment pairs. Simulated readers learn from passages through a Construction-Integration-inspired memory model with DIME-style reader factors, KREC-style misconception revision, and an open New Dale-Chall readability signal. Answers are produced by score-based option selection over the learner's explicit memory state, while BKT drives adaptation. Across three sampled subject ontologies and matched cohorts of 50 simulated learners per condition, adaptive reading significantly improved outcomes in computer science, yielded smaller positive but inconclusive gains in inorganic chemistry, and was neutral to slightly negative in general biology. --- ### Automated Palynological Analysis System: Integrating Deep Metric Learning, Detection and Classification in Bright Field Microscopy Authors: J. Staforelli-Vivanco, R. Jofré, P. Coelho, I. Sanhueza, L. Viafora, C. Toro, J. Troncoso, M. Rondanelli-Reyes, I. Lamas, Andy Banegas-Medina, Isis-Yelena Montes, B. Muñoz-Cepeda et al. Published: 2026-04-17 Categories: cs.CV, physics.optics arXiv: https://arxiv.org/abs/2604.16743v2 Traditional melissopalynology is a time-consuming and subjective process, often taking 4-6 hours per sample. We present an automated, high-throughput microscopy system that integrates H_\infty robust mechanical control with advanced deep learning pipelines for the precise counting, classification, and morphological analysis of pollen grains from Bio Bio region in south central territory in Chile. Our system employs U^2-Net for salient object detection and a DINOv2 Vision Transformer backbone trained via Deep Metric Learning for classification. By integrating Gradient-Weighted Attention, the model provides human-interpretable texture and diagnostic feature annotations. The system achieves a 95.8% classification recall and at least 6x processing speedup compared to manual expert analysis. --- ### Automated Palynological Analysis System: Integrating Deep Metric Learning and $U^{2}$-Net Detection in $H\infty$ bright field microscopy Authors: J. Staforelli-Vivanco, R. Jofré, B. Muñoz, V. Salamanca, P. Coelho, I. Sanhueza, L. Viafora, C. Toro, J. Troncoso, M. Rondanelli-Reyes, I. Lamas Published: 2026-04-17 Categories: cs.CV, physics.optics arXiv: https://arxiv.org/abs/2604.16743v1 Traditional melissopalynology is a time-consuming and subjective process, often taking 4-6 hours per sample. We present an automated, high-throughput microscopy system that integrates $H\infty$ robust mechanical control with advanced deep learning pipelines for the precise counting, classification, and morphological analysis of pollen grains from Bio Bio region in south central territory in Chile. Our system employs $U^{2}$-Net for salient object detection and a DINOv2 Vision Transformer backbone trained via Deep Metric Learning for classification. By integrating Gradient-Weighted Attention, the model provides human-interpretable texture and diagnostic feature annotations. The system achieves a 95.8$\%$ classification recall and a 6x processing speedup compared to manual expert analysis. --- ### CT Open: An Open-Access, Uncontaminated, Live Platform for the Open Challenge of Clinical Trial Outcome Prediction Authors: Jianyou Wang, Youze Zheng, Longtian Bao, Hanyuan Zhang, Qirui Zheng, Yuhan Chen, Yang Zhang, Matthew Feng, Maxim Khan, Aditya K. Sehgal, Christopher D. Rosin, Ramamohan Paturi et al. Published: 2026-04-17 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.16742v2 Scientists have long sought to accurately predict outcomes of real-world events before they happen. Can AI systems do so more reliably? We study this question through clinical trial outcome prediction, a high-stakes open challenge even for domain experts. We introduce CT Open, an open-access, live platform that will run four challenge every year. Anyone can submit predictions for each challenge. CT Open evaluates those submissions on trials whose outcomes were not yet public at the time of submission but were made public afterwards. Determining if a trial's outcome is public on the internet before a certain date is surprisingly difficult. Outcomes posted on official registries may lag behind by years, while the first mention may appear in obscure articles. To address this, we propose a novel, fully automated decontamination pipeline that uses iterative LLM-powered web search to identify the earliest mention of trial outcomes. We validate the pipeline's quality and accuracy by human expert's annotations. Since CT Open's pipeline ensures that every evaluated trial had no publicly reported outcome when the prediction was made, it allows participants to use any methodology and any data source. In this paper, we release a training set and two time-stamped test benchmarks, Winter 2025 and Summer 2025. We believe CT Open can serve as a central hub for advancing AI research on forecasting real-world outcomes before they occur, while also informing biomedical research and improving clinical trial design. CT Open Platform is hosted at $\href{https://ct-open.net/}{https://ct-open.net/}$ --- ### When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis Authors: Justice Owusu Agyemang, Michael Agyare, Miriam Kobbinah, Nathaniel Agbugblah, Prosper Addo Published: 2026-04-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16736v1 LLM-powered coding agents suffer from a poorly understood failure mode we term output stalling: the agent silently produces empty responses when attempting to generate large, format-heavy documents. We present a theoretical framework that explains and prevents this failure through three contributions. (1) We introduce Output Generation Capacity (OGC), a formal measure of an agent's effective ability to produce output given its current context state - distinct from and empirically smaller than the raw context window. (2) We prove a Format-Cost Separation Theorem showing that deferred template rendering is always at least as token-efficient as direct generation for any format with overhead multiplier $μ_f > 1$, and derive tight bounds on the savings. (3) We formalize Adaptive Strategy Selection, a decision framework that maps the ratio of estimated output cost to available OGC into an optimal generation strategy (direct, chunked, or deferred). We validate the theory through controlled experiments across three models (Claude 3.5 Sonnet, GPT-4o, Llama 3.1 70B), four document types, and an ablation study isolating each component's contribution. Deferred rendering reduces LLM generation tokens by 48-72% across all conditions and eliminates output stalling entirely. We instantiate the framework as GEN-PILOT, an open-source MCP server, demonstrating that the theory translates directly into a practical tool. --- ### Reducing Peak Memory Usage for Modern Multimodal Large Language Model Pipelines Authors: Junwan Kim, Hyunkyung Bae Published: 2026-04-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16734v1 Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale to richer visual representations, inference increasingly relies on storing large numbers of vision tokens in the key-value (KV) cache, making memory consumption a central bottleneck. Existing methods address this issue by identifying redundancy in vision tokens and compressing the cache, but such compression is typically applied only after all inputs are processed, resulting in high peak memory usage during the prefill stage. In this work, we show that MLLMs exhibit inherent structural regularities and representational redundancy that can be exploited to control memory growth throughout inference. Based on this insight, we propose a sequential input-compression mechanism that enforces a fixed memory budget by performing structure-aware key-value cache compression during the prefill process. This approach substantially reduces peak memory usage while maintaining generative performance with only minimal degradation, enabling more practical and memory-efficient multimodal inference. --- ### Active World-Model with 4D-informed Retrieval for Exploration and Awareness Authors: Elaheh Vaezpour, Amirhosein Javadi, Tara Javidi Published: 2026-04-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16733v1 Physical awareness, especially in a large and dynamic environment, is shaped by sensing decisions that determine observability across space, time, and scale, while observations impact the quality of sensing decisions. This loopy information structure makes physical awareness a fundamentally challenging decision problem with partial observations. While in the past decade we have witnessed the unprecedented success of reinforcement learning (RL) in problems with full observability, decision problems with partial observation, such as POMDPs, remain largely open: real-world explorations are excessively costly, while sim-to-real pipeline suffer from unobserved viewpoints. We introduce AW4RE (Active World-model with 4D-informed Retrieval for Exploration), an awareness-centric generative world model that provides a sensor-native surrogate environment for exploring sensing queries. Conditioned on a queried sensing action, AW4RE estimates the action-conditioned observation process. This is done by combining 4D-informed evidence retrieval, action-conditioned geometric support with temporal coherence, and conditional generative completion. Experiments demonstrate that AW4RE produces more grounded and consistent predictions than geometry-aware generative baselines under extreme viewpoint shifts, temporal gaps, and sparse geometric support. --- ### Agentic Large Language Models for Training-Free Neuro-Radiological Image Analysis Authors: Ayhan Can Erdur, Daniel Scholz, Jiazhen Pan, Benedikt Wiestler, Daniel Rueckert, Jan C. Peeken Published: 2026-04-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16729v2 State-of-the-art large language models (LLMs) show high performance in general visual question answering. However, a fundamental limitation remains: current architectures lack the native 3D spatial reasoning required to directly analyze volumetric medical imaging, such as CT or MRI. Emerging agentic AI offers a new solution, eliminating the need for intrinsic 3D processing by enabling LLMs to orchestrate and leverage specialized external tools. Yet, the feasibility of such agentic frameworks in complex, multi-step radiological workflows remains underexplored. In this work, we present a training-free agentic pipeline for automated brain MRI analysis. Validating our methodology on several LLMs (GPT-5.4, Gemini 3.1 Pro, Claude Sonnet 4.6) with off-the-shelf domain-specific tools, our system autonomously executes complex end-to-end workflows, including preprocessing (skull stripping, registration), pathology segmentation (glioma, meningioma, metastases), and volumetric reasoning. We evaluate our framework across increasingly complex radiological tasks, from single-scan tumor and anatomy analysis to longitudinal response assessment requiring multi-timepoint comparisons. We analyze the impact of architectural design by comparing single-agent models against multi-agent "domain-expert" collaborations. To support rigorous evaluation of future agentic systems, we release a benchmark dataset of image-prompt-answer tuples derived from public data. Our results demonstrate that agentic AI can solve highly neuro-radiological image analysis tasks through tool use without the need for training or fine-tuning. --- ### Agentic Large Language Models for Training-Free Neuro-Radiological Image Analysis Authors: Ayhan Can Erdur, Daniel Scholz, Jiazhen Pan, Benedikt Wiestler, Daniel Rueckert, Jan C. Peeken Published: 2026-04-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16729v1 State-of-the-art large language models (LLMs) show high performance in general visual question answering. However, a fundamental limitation remains: current architectures lack the native 3D spatial reasoning required for direct analysis of volumetric medical imaging, such as CT or MRI. Emerging agentic AI offers a new solution, eliminating the need for intrinsic 3D processing by enabling LLMs to orchestrate and leverage specialized external tools. Yet, the feasibility of such agentic frameworks in complex, multi-step radiological workflows remains underexplored. In this work, we present a training-free agentic pipeline for automated brain MRI analysis. Validating our methodology on several LLMs (GPT-5.1, Gemini 3 Pro, Claude Sonnet 4.5) with off-the-shelf domain-specific tools, our system autonomously executes complex end-to-end workflows, including preprocessing (skull stripping, registration), pathology segmentation (glioma, meningioma, metastases), and volumetric analysis. We evaluate our framework across increasingly complex radiological tasks, from single-scan segmentation and volumetric reporting to longitudinal response assessment requiring multi-timepoint comparisons. We analyze the impact of architectural design by comparing single-agent models against multi-agent "domain-expert" collaborations. Finally, to support rigorous evaluation of future agentic systems, we introduce and release a benchmark dataset of image-prompt-answer tuples derived from public BraTS data. Our results demonstrate that agentic AI can solve highly neuro-radiological image analysis tasks through tool use without the need for training or fine-tuning. --- ### iDocV2: Leveraging Self-Supervision and Open-Set Detection for Improving Pattern Spotting in Historical Documents Authors: Jose M. Saavedra, Crhistopher Stears, Marcelo Pizarro, Cristóbal Loyola, Luis Aros Published: 2026-04-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16726v1 Considering the imminent massification of digital books, it has become critical to facilitate searching collections through graphical patterns. Current strategies for document retrieval and pattern spotting in historical documents still need to be improved. State-of-the-art strategies achieve an overall precision of $0.494$ for pattern spotting, where the precision for small non-square queries reaches 0.427. In addition, the processing time is excessive, requiring up to 7 seconds for searching in the DocExplore dataset due to a dense-based strategy used by SOTA models. Therefore, we propose a new model based on a better encoder (iDoc), trained under a self-supervised strategy, and an open-set detector to accelerate searching. Our model achieves competitive results with state-of-the-art pattern spotting and document retrieval, improving speed by 10x. Furthermore, our model reaches a new SOTA performance on the small non-square queries, achieving a new precision of 0.612.Different from the previous version, this leverages non-maximum suppression to reduce false positives. --- ### Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training Authors: Moein Salimi, Babak Hosseini Mohtasham, Amin Aghakasiri, Mahdi Naieni, Amir Hossein Qeysarbeigi, Mohammad Masih Shalchian Nazer, Zahra Azar, Mahdi Jafari Siavoshani, Mohammad Hossein Rohban Published: 2026-04-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16723v1 Large Language Models (LLMs) have demonstrated potential in automating scientific ideation, yet current approaches relying on iterative prompting or complex multi-agent architectures often suffer from hallucination or computational inefficiency. A critical bottleneck in applying Reinforcement Learning (RL) to this open-ended domain is reward hacking -- where models exploit imperfect evaluation proxies to maximize scores without producing genuine scientific innovation. To address these limitations, we propose an RL framework explicitly tailored for high-quality scientific idea generation. We propose the first multi-agent reward function designed to serve as a judge, decoupling methodological validation from implementation details while providing strict binary rewards that are robust to reward hacking. To effectively optimize against this sparse signal, we utilize an unbiased variant of Group Relative Policy Optimization to mitigate artificial length bias. We grounded our training in ICLR-320, a curated dataset of problem-solution pairs extracted from ICLR 2024 proceedings. Experiments demonstrate that our framework significantly outperforms state-of-the-art baselines across expert-evaluated metrics of novelty, feasibility, and effectiveness. --- ### Neuroscience Inspired Graph Operators Towards Edge-Deployable Virtual Sensing for Irregular Geometries Authors: William Howes, Farid Ahmed, Kazuma Kobayashi, Souvik Chakraborty, Syed Bahauddin Alam Published: 2026-04-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.16722v1 Predicting full-field physics through the real-time virtual sensing of engineering systems can enhance limited physical sensors but often requires sparse-to-dense reconstruction, complex multiphysics, and highly irregular geometries as well as strict latency and energy constraints for edge-deployability. Neural operators have been presented as a potential candidate for such applications but few architectures exist that explicitly address power consumption. Spiking neuron integration can provide a potential solution when integrated on neuromorphic hardware but the current existing neuron models result in severe performance degradation towards regression-based virtual sensing. To address the performance concerns and edge-constraints, we present the Variable Spiking Graph Neural Operator (VS-GNO) which integrates a sophisticated spectral-spatial convolutional analysis and a previously developed Variable Spiking Neuron (VSN) and energy-error balance loss function. With a non-spiking $L_2$ error baseline of $0.4\%$, VS-GNO can provide a reconstruction error of $0.71\%$ with $15\%$ average spiking in its spectral-only form and $1.04\%$ with $24.5\%$ spiking in its entire form. These results position VS-GNO as a promising step towards energy-efficient, edge-deployable neural operators for real-time sparse-to-dense virtual sensing in complex, highly irregular engineering environments. --- ### Late Fusion Neural Operators for Extrapolation Across Parameter Space in Partial Differential Equations Authors: Eva van Tegelen, Taniya Kapoor, George A. K. van Voorn, Peter van Heijster, Ioannis N. Athanasiadis Published: 2026-04-17 Categories: cs.LG, cs.AI, math.DS arXiv: https://arxiv.org/abs/2604.16721v1 Developing neural operators that accurately predict the behavior of systems governed by partial differential equations (PDEs) across unseen parameter regimes is crucial for robust generalization in scientific and engineering applications. In practical applications, variations in physical parameters induce distribution shifts between training and prediction regimes, making extrapolation a central challenge. As a result, the way parameters are incorporated into neural operator models plays a key role in their ability to generalize, particularly when state and parameter representations are entangled. In this work, we introduce the Late Fusion Neural Operator, an architecture that disentangles learning state dynamics from parameter effects, improving predictive performance both within and beyond the training distribution. Our approach combines neural operators for learning latent state representations with sparse regression to incorporate parameter information in a structured manner. Across four benchmark PDEs including advection, Burgers, and both 1D and 2D reaction-diffusion equations, the proposed method consistently outperforms Fourier Neural Operator and CAPE-FNO. Late Fusion Neural Operators achieve consistently the best performance in all experiments, with an average RMSE reduction of 72.9% in-domain and 71.8% out-domain compared to the second-best method. These results demonstrate strong generalization across both in-domain and out-domain parameter regimes. --- ### Chronax: A Jax Library for Univariate Statistical Forecasting and Conformal Inference Authors: Xan Carey, Yash Deshmukh, Aileen Huang, Sunit Jadhav, Omkar Tekawade, Lorraine Yang, Anvesha Tiwary, Gerardo Riano, Amy Greenwald, Denizalp Goktas Published: 2026-04-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.16719v1 Time-series forecasting is central to many scientific and industrial domains, such as energy systems, climate modeling, finance, and retail. While forecasting methods have evolved from classical statistical models to automated, and neural approaches, the surrounding software ecosystem remains anchored to the traditional Python numerical stack. Existing libraries rely on interpreter-driven execution and object-oriented abstractions, limiting composability, large-scale parallelism, and integration with modern differentiable and accelerator-oriented workflows. Meanwhile, today's forecasting increasingly involves large collections of heterogeneous time series data, irregular covariates, and frequent retraining, placing new demands on scalability and execution efficiency. JAX offers an alternative paradigm to traditional stateful numerical computation frameworks based on pure functions and program transformations such as just-in-time compilation and automatic vectorization, enabling end-to-end optimization across CPUs, GPUs, and TPUs. However, this modern paradigm has not yet been fully incorporated into the design of forecasting systems. We introduce Chronax, a JAX-native time-series forecasting library that rethinks forecasting abstractions around functional purity, composable transformations, and accelerator-ready execution. By representing preprocessing, modeling, and multi-horizon prediction as pure JAX functions, Chronax enables scalable multi-series forecasting, model-agnostic conformal uncertainty quantification, and seamless integration with modern machine learning and scientific computing pipelines. --- ### Detecting Alarming Student Verbal Responses using Text and Audio Classifier Authors: Christopher Ormerod, Gitit Kehat Published: 2026-04-17 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2604.16717v1 This paper addresses a critical safety gap in the use Automated Verbal Response Scoring (AVRS). We present a novel hybrid framework for troubled student detection that combines a text classifier, trained to detect responses based on their content, and an audio classifier, trained to detect responses using prosodic markers. This approach overcomes key limitations of traditional AVRS systems by considering both content and prosody of responses, achieving enhanced performance in identifying potentially concerning responses. This system can expedite the review process by humans, which can be life-saving particularly when timely intervention may be crucial. --- ### Scalable and Adaptive Parallel Training of Graph Transformer on Large Graphs Authors: Jun-Liang Lin, Kamesh Madduri, Mahmut Taylan Kandemir Published: 2026-04-17 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16715v1 Graph foundation models have demonstrated remarkable adaptability across diverse downstream tasks through large-scale pretraining on graphs. However, existing implementations of the backbone model, graph transformers, are typically limited to single-GPU systems, leading to long training times or out-of-memory issues on large graphs. Moreover, parallelizing graph transformer training over the full graph is challenging, as efficiency depends heavily on both the graph structure and system characteristics, such as bandwidth and memory capacity. In this work, we introduce a distributed training framework for graph transformers, which automatically selects and optimizes parallelization strategies based on the graph structure and hardware configuration. With our implementation of distributed sparse operations, we accelerate sparse graph attention by up to 3.8x and reduce memory consumption by 78% compared to state-of-the-art frameworks. On large graph benchmarks, our proposed framework achieves up to 6x speedup with system scaling up to 8 GPUs. These results demonstrate that the proposed framework improves the scalability of graph transformers, bringing them closer to serving as practical graph foundation models. --- ### How to Approximate Inference with Subtractive Mixture Models Authors: Lena Zellinger, Nicola Branchini, Lennert De Smet, Víctor Elvira, Nikolay Malkin, Antonio Vergari Published: 2026-04-17 Categories: cs.LG, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2604.16714v1 Classical mixture models (MMs) are widely used tractable proposals for approximate inference settings such as variational inference (VI) and importance sampling (IS). Recently, mixture models with negative coefficients, called subtractive mixture models (SMMs), have been proposed as a potentially more expressive alternative. However, how to effectively use SMMs for VI and IS is still an open question as they do not provide latent variable semantics and therefore cannot use sampling schemes for classical MMs. In this work, we study how to circumvent this issue by designing several expectation estimators for IS and learning schemes for VI with SMMs, and we empirically evaluate them for distribution approximation. Finally, we discuss the additional challenges in estimation stability and learning efficiency that they carry and propose ways to overcome them. Code is available at: https://github.com/april-tools/delta-vi. --- ### Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents Authors: Bhaskar Gurram Published: 2026-04-17 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2604.16706v2 Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation. We present AgentProp-Bench, a diagnostic benchmark of 14,750 execution traces from thirteen LLM agents (nine proprietary, four open-weight) across four domains, and use it to audit three questions. First, substring-heuristic judging of agent outputs agrees with human annotation only at chance level (Cohen's kappa = 0.049 against each of two annotators), while a three-LLM ensemble reaches moderate agreement (kappa = 0.432) and a single GPT-4o-mini judge is in fact the strongest (kappa = 0.567); dual-annotator agreement is almost perfect (kappa = 0.835). Second, under validated judging a parameter-level error propagates to a wrong final answer with human-calibrated probability approximately 0.62, replicated across proprietary and open-weight models, and a model's ability to reject corrupted inputs and to recover from them are statistically indepen1). Third, severalagents fabricate tool executions -- asserting tool-derived renever obtained (up toilure invisible toend-to-end scores, and a lightweight runtime interceptor reduhallucination on everto 24 percentagepoints) at a tunable operating point that is net-positive on open-weight models. Ini-2.0-Flash, whichrarely emits an injectable tool call. All code, data, traces, and human labels are relehttps://github.com/bhaskargurram-ai/agenthallu-bench --- ### Evaluating Tool-Using Language Agents: Judge Reliability, Propagation Cascades, and Runtime Mitigation in AgentProp-Bench Authors: Bhaskar Gurram Published: 2026-04-17 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2604.16706v1 Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, but this assumption has rarely been validated against human annotation. We introduce AgentProp-Bench, a 2,000-task benchmark with 2,300 traces across four domains, nine production LLMs, and a 100-label human-validated subset. We quantify judge reliability, characterize error propagation, and evaluate a runtime mitigation. Substring-based judging agrees with human annotation at kappa=0.049 (chance-level); a three-LLM ensemble reaches kappa=0.432 (moderate) with a conservative bias. Under validated evaluation, a parameter-level injection propagates to a wrong final answer with human-calibrated probability approximately 0.62 (range 0.46-0.73 across models). Rejection (catching bad parameters) and recovery (correcting after acceptance) are independent model capabilities (Spearman rho=0.126, p=0.747). A tuned runtime interceptor reduces hallucination on GPT-4o-mini by 23.0 percentage points under a concurrent n=600 control, but shows no significant effect on Gemini-2.0-Flash, whose aggressive parameter rejection eliminates the target failure mode. All code, data, traces, and human labels are released at https://github.com/bhaskargurram-ai/agenthallu-bench. --- ### The impact of postediting on AI generative translation in Yemeni context: Translating literary prose by ChatGPT Authors: Nasim Al-wagieh, Mohammed Q. Shormani Published: 2026-04-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.16704v1 This study examines the role of artificial intelligence in translation, focusing on ChatGPT, specifically ChatGPT-4, and the extent to which human postediting is required in literary translation. A mixed-method approach was adopted, involving 30 professional translators who evaluated and postedited AI-generated translations of selected Arabic and English literary texts. The results show that although AI improves translation speed and accessibility, it remains limited in handling cultural, stylistic, and figurative aspects of language. Participants generally confirmed the necessity of human postediting, particularly in novels and drama. The findings indicate that emerging human-machine collaboration model rather than replacement of human translators. The study concludes that AI should be used as a supportive tool, while human expertise remains essential for ensuring translation quality and cultural appropriateness. --- ### Surgical Repair of Insecure Code Generation in LLMs Authors: Gustavo Sandoval, Brendan Dolan-Gavitt, Siddharth Garg Published: 2026-04-17 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.16697v1 Large language models write production code, and yet they routinely introduce well-known vulnerabilities. We show that this is not a knowledge deficit: the same models that generate insecure code, correctly identify and explain the vulnerability when asked directly, this is a gap we call the Format-Reliability Gap. Mechanistic analysis reveals the cause: security representations are encoded from the earliest layers but remain computationally inert until the final layer, where format-compliance demands compete with them. Because the failure is localized to a single layer, per-vulnerability steering vectors reduce insecure generation by up to 74% with negligible overhead. The mechanism and the fix generalize across five models, three architecture families, and six vulnerability types, suggesting insecure code generation is an interpretability problem, not a training artifact. --- ### LOD-Net: Locality-Aware 3D Object Detection Using Multi-Scale Transformer Network Authors: Mustaqeem Khan, Aidana Nurakhmetova, Wail Gueaieb, Abdulmotaleb El Saddik Published: 2026-04-17 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2604.16696v1 3D object detection in point cloud data remains a challenging task due to the sparsity and lack of global structure inherent in the input. In this work, we propose a novel Multi-Scale Attention (MSA) mechanism integrated into the 3DETR architecture to better capture both local geometry and global context. Our method introduces an upsampling operation that generates high-resolution feature maps, enabling the network to better detect smaller and semantically related objects. Experiments conducted on the ScanNetv2 dataset demonstrate that our 3DETR + MSA model improves detection performance, achieving a gain of almost 1% in mAP@25 and 4.78% in mAP@50 over the baseline. While applying MSA to the 3DETR-m variant shows limited improvement, our analysis reveals the importance of adapting the upsampling strategy for lightweight models. These results highlight the effectiveness of combining hierarchical feature extraction with attention mechanisms in enhancing 3D scene understanding. ---