# Research Papers — 2026-04 · bundle page 198 of 233 > Full-text markdown of papers #9851–9900 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/198 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/197.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/199.md) ### REAM: Merging Improves Pruning of Experts in LLMs Authors: Saurav Jha, Maryam Hashemzadeh, Ali Saheb Pasand, Ali Parviz, Min-Joong Lee, Boris Knyazev Published: 2026-04-06 Categories: cs.AI, cs.CL, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2604.04356v1 Mixture-of-Experts (MoE) large language models (LLMs) are among the top-performing architectures. The largest models, often with hundreds of billions of parameters, pose significant memory challenges for deployment. Traditional approaches to reduce memory requirements include weight pruning and quantization. Motivated by the Router-weighted Expert Activation Pruning (REAP) that prunes experts, we propose a novel method, Router-weighted Expert Activation Merging (REAM). Instead of removing experts, REAM groups them and merges their weights, better preserving original performance. We evaluate REAM against REAP and other baselines across multiple MoE LLMs on diverse multiple-choice (MC) question answering and generative (GEN) benchmarks. Our results reveal a trade-off between MC and GEN performance that depends on the mix of calibration data. By controlling the mix of general, math and coding data, we examine the Pareto frontier of this trade-off and show that REAM often outperforms the baselines and in many cases is comparable to the original uncompressed models. --- ### Talk2AI: A Longitudinal Dataset of Human--AI Persuasive Conversations Authors: Alexis Carrillo, Enrique Taietta, Ali Aghazadeh Ardebili, Giuseppe Alessandro Veltri, Massimo Stella Published: 2026-04-06 Categories: cs.HC, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2604.04354v1 Talk2AI is a large-scale longitudinal dataset of 3,080 conversations (totaling 30,800 turns) between human participants and Large Language Models (LLMs), designed to support research on persuasion, opinion change, and human-AI interaction. The corpus was collected from 770 profiled Italian adults across four weekly sessions in Spring 2025, using a within-subject design in which each participant conversed with a single model (GPT-4o, Claude Sonnet 3.7, DeepSeek-chat V3, or Mistral Large) on three socially relevant topics: climate change, math anxiety, and health misinformation. Each conversation is linked to rich contextual data, including sociodemographic characteristics and psychometric profiles. After each session, participants reported on opinion change, conviction stability, perceived humanness of the AI, and behavioral intentions, enabling fine-grained longitudinal analysis of how AI-mediated dialogue shapes beliefs and attitudes over time. --- ### ReFinE: Streamlining UI Mockup Iteration with Research Findings Authors: Donghoon Shin, Bingcan Guo, Jaewook Lee, Lucy Lu Wang, Gary Hsieh Published: 2026-04-06 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.04353v2 Although HCI research papers offer valuable design insights, designers often struggle to apply them in design workflows due to difficulties in finding relevant literature, understanding technical jargon, the lack of contextualization, and limited actionability. To address these challenges, we present ReFinE, a Figma plugin that supports real-time design iteration by surfacing contextualized insights from research papers. ReFinE identifies and synthesizes design implications from HCI literature relevant to the mockup's design context, and tailors this research evidence to a specific design mockup by providing actionable visual guidance on how to update the mockup. To assess the system's effectiveness, we conducted a technical evaluation and a user study. Results show that ReFinE effectively synthesizes and contextualizes design implications, reducing cognitive load and improving designers' ability to integrate research evidence into UI mockups. This work contributes to bridging the gap between research and design practice by presenting a tool for embedding scholarly insights into the UI design process. --- ### Adversarial Robustness Analysis of Cloud-Assisted Autonomous Driving Systems Authors: Maher Al Islam, Amr S. El-Wakeel Published: 2026-04-06 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2604.04349v1 Autonomous vehicles increasingly rely on deep learning-based perception and control, which impose substantial computational demands. Cloud-assisted architectures offload these functions to remote servers, enabling enhanced perception and coordinated decision-making through the Internet of Vehicles (IoV). However, this paradigm introduces cross-layer vulnerabilities, where adversarial manipulation of perception models and network impairments in the vehicle-cloud link can jointly undermine safety-critical autonomy. This paper presents a hardware-in-the-loop IoV testbed that integrates real-time perception, control, and communication to evaluate such vulnerabilities in cloud-assisted autonomous driving. A YOLOv8-based object detector deployed on the cloud is subjected to whitebox adversarial attacks using the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD), while network adversaries induce delay and packet loss in the vehicle-cloud loop. Results show that adversarial perturbations significantly degrade perception performance, with PGD reducing detection precision and recall from 0.73 and 0.68 in the clean baseline to 0.22 and 0.15 at epsilon= 0.04. Network delays of 150-250 ms, corresponding to transient losses of approximately 3-4 frames, and packet loss rates of 0.5-5 % further destabilize closed-loop control, leading to delayed actuation and rule violations. These findings highlight the need for cross-layer resilience in cloud-assisted autonomous driving systems. --- ### OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text Authors: Weiguo Pian, Saksham Singh Kushwaha, Zhimin Chen, Shijian Deng, Kai Wang, Yunhui Guo, Yapeng Tian Published: 2026-04-06 Categories: cs.SD, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2604.04348v1 In this paper, we propose Universal Holistic Audio Generation (UniHAGen), a task for synthesizing comprehensive auditory scenes that include both on-screen and off-screen sounds across diverse domains (e.g., ambient events, musical instruments, and human speech). Prior video-conditioned audio generation models typically focus on producing on-screen environmental sounds that correspond to visible sounding events, neglecting off-screen auditory events. While recent holistic joint text-video-to-audio generation models aim to produce auditory scenes with both on- and off-screen sound but they are limited to non-speech sounds, lacking the ability to generate or integrate human speech. To overcome these limitations, we introduce OmniSonic, a flow-matching-based diffusion framework jointly conditioned on video and text. It features a TriAttn-DiT architecture that performs three cross-attention operations to process on-screen environmental sound, off-screen environmental sound, and speech conditions simultaneously, with a Mixture-of-Experts (MoE) gating mechanism that adaptively balances their contributions during generation. Furthermore, we construct UniHAGen-Bench, a new benchmark with over one thousand samples covering three representative on/off-screen speech-environment scenarios. Extensive experiments show that OmniSonic consistently outperforms state-of-the-art approaches on both objective metrics and human evaluations, establishing a strong baseline for universal and holistic audio generation. Project page: https://weiguopian.github.io/OmniSonic_webpage/ --- ### RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgets Authors: Andrew Borthwick, Stephen Ash, Anthony Galczak Published: 2026-04-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.04347v1 2026 has brought an explosion of interest in LLM-guided evolution of agentic artifacts, with systems like GEPA and Autoresearch demonstrating that LLMs can iteratively improve prompts, code, and agent architectures across diverse domains. As adoption accelerates, a central question emerges: given the same information, the same seed agent, and the same objective, which optimization algorithm yields the best results under the same evaluation budget? This question becomes critical when evaluations are expensive, such as when they require human judgment or multiple LLM calls. We present the first systematic comparison of three optimization paradigms -- Elo tournament selection (RoboPhD), Pareto-based selection (GEPA), and greedy hill-climbing (Autoresearch) -- across four benchmarks spanning abstract reasoning, cloud scheduling, SQL generation, and financial QA, all under a fixed budget of 1,500 evaluations. RoboPhD introduces validation-free evolution: instead of splitting the budget between training and validation, it uses Elo competition on training data to simultaneously evaluate agents and drive evolution. All three systems receive seed agents with diagnostic print() statements that evolution can grow, enabling self-instrumenting agents that develop increasingly informative diagnostics for the benefit of their evolutionary successors. Using a single default configuration, RoboPhD outperforms both GEPA and Autoresearch on three of four benchmarks, losing only on the simplest task, where the winning solution (from our Autoresearch adaptation) required under 90 lines of code. On ARC-AGI, RoboPhD evolves a 22-line seed agent into a 1,013-line multi-strategy system, improving accuracy from 27.8% to 65.8% using Gemini 3.1 Flash Lite as the solver. We release RoboPhD as a versatile toolkit under the MIT license with a simple optimize_anything() API for evolving diverse complex agents. --- ### Domain-Contextualized Inference: A Computable Graph Architecture for Explicit-Domain Reasoning Authors: Chao Li, Yuru Wang, Chunyi Zhao Published: 2026-04-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.04344v3 We establish a computation-substrate-agnostic inference architecture in which domain is an explicit first-class computational parameter. This produces domain-scoped pruning that reduces per-query search space from O(N) to O(N/K), substrate-independent execution over symbolic, neural, vector, and hybrid substrates, and transparent inference chains where every step carries its evaluative context. The contribution is architectural, not logical. We formalize the computational theory across five dimensions: a five-layer architecture; three domain computation modes including chain indexing, path traversal as Kleisli composition, and vector-guided computation as a substrate transition; a substrate-agnostic interface with three operations Query, Extend, Bridge; reliability conditions C1 to C4 with three failure mode classes; and validation through a PHQ-9 clinical reasoning case study. The computational theory including operational semantics, complexity bounds, monad structure, substrate transitions, and boundary conditions is the contribution of this paper. --- ### Deep Kuratowski Embedding Neural Networks for Wasserstein Metric Learning Authors: Andrew Qing He Published: 2026-04-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.04343v1 Computing pairwise Wasserstein distances is a fundamental bottleneck in data analysis pipelines. Motivated by the classical Kuratowski embedding theorem, we propose two neural architectures for learning to approximate the Wasserstein-2 distance ($W_2$) from data. The first, DeepKENN, aggregates distances across all intermediate feature maps of a CNN using learnable positive weights. The second, ODE-KENN, replaces the discrete layer stack with a Neural ODE, embedding each input into the infinite-dimensional Banach space $C^1((0,1), \mathbb{R}^d)$ and providing implicit regularization via trajectory smoothness. Experiments on MNIST with exact precomputed $W_2$ distances show that ODE-KENN achieves a 28% lower test MSE than the single-layer baseline and 18% lower than DeepKENN under matched parameter counts, while exhibiting a smaller generalization gap. The resulting fast surrogate can replace the expensive $W_2$ oracle in downstream pairwise distance computations. --- ### Generative models for decision-making under distributional shift Authors: Xiuyuan Cheng, Yunqin Zhu, Yao Xie Published: 2026-04-06 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.04342v2 Many data-driven decision problems are formulated using a nominal distribution estimated from historical data, while performance is ultimately determined by a deployment distribution that may be shifted, context-dependent, partially observed, or stress-induced. This tutorial presents modern generative models, particularly flow- and score-based methods, as mathematical tools for constructing decision-relevant distributions. From an operations research perspective, their primary value lies not in unconstrained sample synthesis but in representing and transforming distributions through transport maps, velocity fields, score fields, and guided stochastic dynamics. We present a unified framework based on pushforward maps, continuity, Fokker-Planck equations, Wasserstein geometry, and optimization in probability space. Within this framework, generative models can be used to learn nominal uncertainty, construct stressed or least-favorable distributions for robustness, and produce conditional or posterior distributions under side information and partial observation. We also highlight representative theoretical guarantees, including forward-reverse convergence for iterative flow models, first-order minimax analysis in transport-map space, and error-transfer bounds for posterior sampling with generative priors. The tutorial provides a principled introduction to using generative models for scenario generation, robust decision-making, uncertainty quantification, and related problems under distributional shift. --- ### Implementing surrogate goals for safer bargaining in LLM-based agents Authors: Caspar Oesterheld, Maxime Riché, Filip Sondej, Jesse Clifton, Vincent Conitzer Published: 2026-04-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.04341v1 Surrogate goals have been proposed as a strategy for reducing risks from bargaining failures. A surrogate goal is goal that a principal can give an AI agent and that deflects any threats against the agent away from what the principal cares about. For example, one might make one's agent care about preventing money from being burned. Then in bargaining interactions, other agents can threaten to burn their money instead of threatening to spending money to hurt the principal. Importantly, the agent has to care equally about preventing money from being burned as it cares about money being spent to hurt the principal. In this paper, we implement surrogate goals in language-model-based agents. In particular, we try to get a language-model-based agent to react to threats of burning money in the same way it would react to "normal" threats. We propose four different methods, using techniques of prompting, fine-tuning, and scaffolding. We evaluate the four methods experimentally. We find that methods based on scaffolding and fine-tuning outperform simple prompting. In particular, fine-tuning and scaffolding more precisely implement the desired behavior w.r.t. threats against the surrogate goal. We also compare the different methods in terms of their side effects on capabilities and propensities in other situations. We find that scaffolding-based methods perform best. --- ### Thermodynamic-Inspired Explainable GeoAI: Uncovering Regime-Dependent Mechanisms in Heterogeneous Spatial Systems Authors: Sooyoung Lim, Zhenlong Li, Zi-Kui Liu Published: 2026-04-06 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.04339v1 Modeling spatial heterogeneity and associated critical transitions remains a fundamental challenge in geography and environmental science. While conventional Geographically Weighted Regression (GWR) and deep learning models have improved predictive skill, they often fail to elucidate state-dependent nonlinearities where the functional roles of drivers represent opposing effects across heterogeneous domains. We introduce a thermodynamics-inspired explainable geospatial AI framework that integrates statistical mechanics with graph neural networks. By conceptualizing spatial variability as a thermodynamic competition between system Burden (E) and Capacity (S), our model disentangles the latent mechanisms driving spatial processes. Using three simulation datasets and three real-word datasets across distinct domains (housing markets, mental health prevalence, and wildfire-induced PM2.5 anomalies), we show that the new framework successfully identifies regime-dependent role reversals of predictors that standard baselines miss. Notably, the framework explicitly diagnoses the phase transition into a Burden-dominated regime during the 2023 Canadian wildfire event, distinguishing physical mechanism shifts from statistical outliers. These findings demonstrate that thermodynamic constraints can improve the interpretability of GeoAI while preserving strong predictive performance in complex spatial systems. --- ### Boosted Distributional Reinforcement Learning: Analysis and Healthcare Applications Authors: Zequn Chen, Wesley J. Marrero Published: 2026-04-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.04334v2 Researchers and practitioners are increasingly considering reinforcement learning to optimize decisions in complex domains like robotics and healthcare. To date, these efforts have largely utilized expectation-based learning. However, relying on expectation-focused objectives may be insufficient for making consistent decisions in highly uncertain situations involving multiple heterogeneous groups. While distributional reinforcement learning algorithms have been introduced to model the full distributions of outcomes, they can yield large discrepancies in realized benefits among comparable agents. This challenge is particularly acute in healthcare settings, where physicians (controllers) must manage multiple patients (subordinate agents) with uncertain disease progression and heterogeneous treatment responses. We propose a Boosted Distributional Reinforcement Learning (BDRL) algorithm that optimizes agent-specific outcome distributions while enforcing comparability among similar agents and analyze its convergence. To further stabilize learning, we incorporate a post-update projection step formulated as a constrained convex optimization problem, which efficiently aligns individual outcomes with a high-performing reference within a specified tolerance. We apply our algorithm to manage hypertension in a large subset of the US adult population by categorizing individuals into cardiovascular disease risk groups. Our approach modifies treatment plans for median and vulnerable patients by mimicking the behavior of high-performing references in each risk group. Furthermore, we find that BDRL improves the number and consistency of quality-adjusted life years compared with reinforcement learning baselines. --- ### GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction Authors: Yedong Shen, Shiqi Zhang, Sha Zhang, Yifan Duan, Xinran Zhang, Wenhao Yu, Lu Zhang, Jiajun Deng, Yanyong Zhang Published: 2026-04-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.04331v1 Reconstructing static 3D scene from monocular video with dynamic objects is important for numerous applications such as virtual reality and autonomous driving. Current approaches typically rely on background for static scene reconstruction, limiting the ability to recover regions occluded by dynamic objects. In this paper, we propose GA-GS, a Generation-Assisted Gaussian Splatting method for Static Scene Reconstruction. The key innovation of our work lies in leveraging generation to assist in reconstructing occluded regions. We employ a motion-aware module to segment and remove dynamic regions, and thenuse a diffusion model to inpaint the occluded areas, providing pseudo-ground-truth supervision. To balance contributions from real background and generated region, we introduce a learnable authenticity scalar for each Gaussian primitive, which dynamically modulates opacity during splatting for authenticity-aware rendering and supervision. Since no existing dataset provides ground-truth static scene of video with dynamic objects, we construct a dataset named Trajectory-Match, using a fixed-path robot to record each scene with/without dynamic objects, enabling quantitative evaluation in reconstruction of occluded regions. Extensive experiments on both the DAVIS and our dataset show that GA-GS achieves state-of-the-art performance in static scene reconstruction, especially in challenging scenarios with large-scale, persistent occlusions. --- ### Soft Tournament Equilibrium Authors: Saad Alqithami Published: 2026-04-06 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2604.04328v3 The evaluation of general-purpose artificial agents, particularly those based on LLMs, presents a significant challenge due to the non-transitive nature of their interactions. When agent A defeats B, B defeats C, and C defeats A, traditional ranking methods that force a linear ordering can be misleading and unstable. We argue that for such cyclic domains, the fundamental object of evaluation should not be a ranking alone but a set-valued core, as conceptualized in classical tournament theory. This paper introduces Soft Tournament Equilibrium (STE), a differentiable framework for learning and computing set-valued tournament solutions directly from pairwise comparison data. STE first learns a probabilistic tournament model, potentially conditioned on rich contextual information. It then employs differentiable operators for soft reachability and soft covering to compute continuous analogues of two seminal tournament solutions: the Top Cycle and the Uncovered Set. The output is a set of core agents, each with a continuous membership score that can be calibrated when suitable validation labels or repeated-sampling evidence are available. We develop the theoretical foundation for STE by proving consistency with classical solutions in the zero-temperature limit, establishing Condorcet-inclusion properties, and analyzing stability and sample complexity. We evaluate the method on a planted cyclic core benchmark and on real preference/execution diagnostics. This work provides a self-contained account that re-centers general-agent evaluation on a robust tournament-theoretic foundation, moving from unstable rankings toward stable, set-valued equilibria. --- ### Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction Authors: Jinrui Fang, Runhan Chen, Xu Yang, Jian Yu, Jiawei Xu, Ashwin Vinod, Wenqi Shi, Tianlong Chen, Heng Ji, ChengXiang Zhai, Ying Ding, Yuji Zhang Published: 2026-04-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.04325v1 Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn, yet how they behave under multi-turn evidence accumulation closer to real clinical reasoning remains unexplored. We introduce MINT (Medical Incremental N-Turn Benchmark), a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases with clinically labeled evidence shards, controlled turn granularity, and information-preserving decomposition. Through systematic evaluation of 11 LLMs on MINT, we uncover three persistent behavioral patterns that significantly impact diagnostic decisions: (1) intent to answer, models rush to answer before sufficient evidence has been observed, with over 55% of answers committed within the first two turns; (2) self-correction, incorrect-to-correct answer revisions occur at up to 10.6 times the rate of correct-to-incorrect flips, revealing a latent capacity for self-correction that premature commitment forecloses; and (3) strong lures, clinically salient information such as laboratory results trigger premature answering even when models are explicitly instructed to wait. We translate these findings into clinically actionable guidance: deferring the diagnostic question to later turns reduces premature answering and improves accuracy at the first point of commitment by up to 62.6%, while reserving salient clinical evidence for later turns prevents a catastrophic accuracy drop of up to 23.3% caused by premature commitment. Our work provides both a controlled evaluation framework and concrete recommendations for improving the reliability of LLMs in multi-turn medical diagnosis. --- ### RESCORE: LLM-Driven Simulation Recovery in Control Systems Research Papers Authors: Vineet Bhat, Shiqing Wei, Ali Umut Kaypak, Prashanth Krishnamurthy, Ramesh Karri, Farshad Khorrami Published: 2026-04-06 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2604.04324v1 Reconstructing numerical simulations from control systems research papers is often hindered by underspecified parameters and ambiguous implementation details. We define the task of Paper to Simulation Recoverability, the ability of an automated system to generate executable code that faithfully reproduces a paper's results. We curate a benchmark of 500 papers from the IEEE Conference on Decision and Control (CDC) and propose RESCORE, a three component LLM agentic framework, Analyzer, Coder, and Verifier. RESCORE uses iterative execution feedback and visual comparison to improve reconstruction fidelity. Our method successfully recovers task coherent simulations for 40.7% of benchmark instances, outperforming single pass generation. Notably, the RESCORE automated pipeline achieves an estimated 10X speedup over manual human replication, drastically cutting the time and effort required to verify published control methodologies. We will release our benchmark and agents to foster community progress in automated research replication. --- ### How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings Authors: Yujian Liu, Jiabao Ji, Li An, Tommi Jaakkola, Yang Zhang, Shiyu Chang Published: 2026-04-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.04323v1 Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage performance remains scarce. Existing skill benchmarking efforts focus on overly idealized conditions, where LLMs are directly provided with hand-crafted, narrowly-tailored task-specific skills for each task, whereas in many realistic settings, the LLM agent may have to search for and select relevant skills on its own, and even the closest matching skills may not be well-tailored for the task. In this paper, we conduct the first comprehensive study of skill utility under progressively challenging realistic settings, where agents must retrieve skills from a large collection of 34k real-world skills and may not have access to any hand-curated skills. Our findings reveal that the benefits of skills are fragile: performance gains degrade consistently as settings become more realistic, with pass rates approaching no-skill baselines in the most challenging scenarios. To narrow this gap, we study skill refinement strategies, including query-specific and query-agnostic approaches, and we show that query-specific refinement substantially recovers lost performance when the initial skills are of reasonable relevance and quality. We further demonstrate the generality of retrieval and refinement on Terminal-Bench 2.0, where they improve the pass rate of Claude Opus 4.6 from 57.7% to 65.5%. Our results, consistent across multiple models, highlight both the promise and the current limitations of skills for LLM-based agents. Our code is available at https://github.com/UCSB-NLP-Chang/Skill-Usage. --- ### Minimising Willmore Energy via Neural Flow Authors: Edward Hirst, Henrique N. Sá Earp, Tomás S. R. Silva Published: 2026-04-06 Categories: math.DG, cs.LG arXiv: https://arxiv.org/abs/2604.04321v1 The neural Willmore flow of a closed oriented $2$-surface in $\mathbb{R}^3$ is introduced as a natural evolution process to minimise the Willmore energy, which is the squared $L^2$-norm of mean curvature. Neural architectures are used to model maps from topological $2d$ domains to $3d$ Euclidean space, where the learning process minimises a PINN-style loss for the Willmore energy as a functional on the embedding. Training reproduces the expected round sphere for genus $0$ surfaces, and the Clifford torus for genus $1$ surfaces, respectively. Furthermore, the experiment in the genus $2$ case provides a novel approach to search for minimal Willmore surfaces in this open problem. --- ### Optimal Adaptive Market Making: A Theoretical Framework for High-Yield Liquidity Provision in Perpetual Futures Markets Authors: Minmin Zeng, Yi Liu Published: 2026-04-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.11888v1 We develop a rigorous theoretical framework for optimal market making in perpetual futures markets with zero maker fees. We model the market maker's problem as a stochastic optimal control problem on a filtered probability space, where the controls are adaptive bid-ask spreads and inventory hedging decisions across two exchanges. Our contributions include: (i) a PnL decomposition theorem separating revenue into spread income, adverse selection loss, inventory carrying cost, hedging friction, and funding rate exposure; (ii) the Hamilton-Jacobi-Bellman equation for the joint spread-inventory-hedging control problem under CARA utility with a verification theorem; (iii) High-APY Regime Theorems characterizing profitable regions via five dimensionless parameters, culminating in a Master APY Formula; (iv) analysis of zero-fee economics on decentralized perpetual exchanges with optimal entry-exit thresholds; (v) optimal cross-exchange hedging policies with funding rate dynamics and a hedge regime trichotomy; (vi) a robustness margin quantifying parameter uncertainty tolerance; (vii) exponential drawdown probability bounds and a universal APY-VaR identity; (viii) ergodic inventory distribution under optimal control with Bayesian adaptive estimation; (ix) Kelly-optimal leverage with ruin boundaries; and (x) multi-pair portfolio allocation with diversification saturation results. Numerical analysis with twenty-three figures reveals phase transitions between profitable and unprofitable regimes. Our framework unifies and extends the Avellaneda-Stoikov, Gueant-Lehalle-Fernandez-Tapia, and Glosten-Milgrom paradigms for modern decentralized venue microstructure. --- ### meta-pipe: An LLM-agent pipeline for end-to-end automated systematic review and meta-analysis Authors: Hsieh-Ting Lin, Jiunn-Tyng Yeh Published: 2026-04-05 Categories: cs.IR, cs.AI, cs.DL arXiv: https://arxiv.org/abs/2606.28363v1 Objective: To describe the architecture and design rationale of meta-pipe, an open-source large language model (LLM)-agent pipeline that integrates the complete systematic review and meta-analysis (SR/MA) workflow -- from literature search through statistical analysis, manuscript generation, and quality assurance -- with mandatory human oversight at critical decision points. Study Design and Setting: We developed a 10-stage modular pipeline integrating Claude (Anthropic; Opus 4 for reasoning, Haiku 3.5 for classification) for LLM-assisted screening and extraction, Python (~3,600 lines of code) for automation, R (meta, metafor, gemtc, netmeta) for statistical analysis, and Quarto for manuscript rendering. Five mandatory human decision points enforce oversight. We systematically compared meta-pipe's capabilities with five existing SR automation tools based on published documentation as of March 2026. Results: meta-pipe offers four capabilities not available in any single existing tool: automated manuscript generation from analysis outputs, semi-automated GRADE assessment, overclaim detection (12 predefined patterns), and dual-paradigm network meta-analysis (Bayesian and frequentist). Estimated API cost is $15-30 per typical 5-10 study review. No validation data are reported; this is a system description, not a validation study. Conclusion: End-to-end AI-assisted evidence synthesis is architecturally feasible as an open-source tool with mandatory human oversight. Formal validation reproducing published Cochrane reviews is underway and essential before routine use. --- ### A Reproducible Semantic Benchmark for Multivendor DSM-to-CLI Translation Authors: Jerônimo Menezes, Leonardo Bitzki, Diego Kreutz, Gefte Almeida, Marcio Pohlmann, Rodrigo Mansilha Published: 2026-04-05 Categories: cs.NI, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2606.20564v1 Translating high-level network intents into correct multivendor configurations remains a central challenge in network automation, as syntactically valid outputs may still violate the intended operational state. Despite recent advances in Large Language Models (LLMs), the field still lacks reproducible semantic benchmarks for rigorous cross-vendor evaluation. This paper presents a reproducible DSM-to-CLI semantic benchmark covering five cloud LLMs, three vendors, five representative use cases, and ten repeated runs per experimental cell under fixed judges and an explicit failure taxonomy. Our results show that semantic quality and operational reliability are orthogonal, vendor effects dominate use-case effects, and repeated-run dispersion strongly predicts vote instability, with Huawei VRP exposing failure modes hidden by aggregate metrics. These findings demonstrate that multivendor, repeated-execution semantic benchmarks are essential for scientifically rigorous comparison of LLM-based network configuration systems. --- ### Advanced Machine Learning and Deep Learning Techniques for Enhanced Cattle Identification and Detection: A Comprehensive Review Authors: Fayazunnesa Chowdhury, Syed Md. Galib, Md Nasim Adnan, Md. Moradul Siddique, Md Robiul Karim, K M Tanvir Anjum Published: 2026-04-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.15655v1 The need for effective cattle identification technology is now more acutely felt than ever in maintaining biosecurity, food safety, and supply chain efficacy in livestock management. This paper presents a systematic review of recent research in cattle identification using machine learning and deep learning techniques. The present systematic review measures the effectiveness of traditional and modern cattle identification techniques using studies from major academic databases, where articles were subjected to full-text review. Among these techniques, classical Machine Learning Techniques such as K-Nearest Neighbors and Support Vector Machines have demonstrated good results in cattle identification; however, Deep Learning Techniques, such as Convolutional Neural Networks, Residual Networks, and You Only Look Once, are better in cognition, detection, and identification tasks. Feature extraction relies on common techniques like Local Binary Pattern (LBP), Speeded-Up Robust Features (SURF), and Scale-Invariant Feature Transform (SIFT), while key features commonly used in these studies include muzzle prints and coat patterns. The review highlights key hurdles involving cattle identification, such as the limited number of publicly accessible datasets, issues with data quality susceptible to environmental changes and animal mobility, and high demand for real-time processing ability. The paper aims to inform researchers, policymakers, and stakeholders about implementing scalable, humane, and effective cattle identification systems to achieve sustainable livestock management. --- ### AnonShield: Scalable On-Premise Pseudonymization for CSIRT Vulnerability Data Authors: Cristhian Kapelinski, Douglas Lautert, Beatriz Machado, Diego Kreutz, Isadora Garcia Ferrão Published: 2026-04-05 Categories: cs.CR, cs.AI, cs.PF arXiv: https://arxiv.org/abs/2606.15650v1 We present AnonShield, a high-throughput, on-premise pseudonymization system that combines GPU-accelerated NER, streaming processing, caching, and schema-aware configuration. Evaluated on datasets up to 550 MB (70,951 records), AnonShield reduces processing time from over 92 hours to under 10 minutes (up to 738x speedup) while achieving up to 94.2% F1-score and 96.7% recall. Our results show that scalable pseudonymization of vulnerability data is feasible without sacrificing analytical utility, enabling compliant data sharing in operational CSIRT environments. --- ### Towards Next-Generation Healthcare: A Survey of Medical Embodied AI for Perception, Decision-Making, and Action Authors: Cheng Zhang, Qing Cai, Xingzheng Wu, Xun Yang, Xiaojun Chang, Bingkun Bao, Liqiang Nie, Xinwang Liu, Yi Yang Published: 2026-04-05 Categories: cs.AI, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2606.15647v1 Foundation models have demonstrated impressive performance in enhancing healthcare efficiency across a wide range of medical applications. Nevertheless, their limited ability to perceive, understand, and interact with the physical world significantly constrains their effectiveness in real-world clinical workflows, where safety-critical decision-making and physical execution are tightly coupled. Recently, embodied artificial intelligence (AI) has emerged as a promising physical-interactive paradigm for intelligent healthcare, enabling agents to operate in complex medical environments. As research in this area rapidly expands, understanding how intelligent agents function as integrated, end-to-end systems in clinical environments becomes increasingly critical. However, existing surveys on medical embodied AI largely emphasize individual aspects or functional components, lacking a unified system-level organization of the field. To support and consolidate recent advances, we systematically survey the core components of medical embodied AI, with a particular emphasis on the coordinated integration of perception, decision-making, and action. We further review representative medical applications and relevant datasets, and we analyze the major challenges encountered in real-world clinical practice. Finally, we discuss key directions for future research in this rapidly evolving field. The associated project can be found at https://github.com/VMVLab/Medical_Embodied_AI_Paper_List. --- ### NeuroSymbolic AI for Legal AI-TRISM: Trustworthy, Reliable, Interpretable, Safe Models Authors: Deepa Tilwani, Yash Saxena, Ankur Padia, Srinivasan Parthasarathy, Manas Gaur Published: 2026-04-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.15646v1 Large Language Models (LLMs) have transformed natural language processing, but their lack of interpretable reasoning and tendency to hallucinate pose significant challenges for legal applications. While LLMs show promise for legal text analysis and generation, they struggle with accurate citation attribution and precedent verification. For example, in legal contexts, a single incorrect precedent can jeopardize a case. Current approaches to improve LLM reliability in legal domains suffer from two key limitations: inadequate integration of structured legal knowledge during training or fine-tuning, and insufficient verification mechanisms for generated legal content. To address these challenges, we propose the TRISM (Trustworthy, Reliable, Interpretable, Safe Models) framework, which integrates NeuroSymbolic AI principles with LLMs to leverage both neural learning capabilities and symbolic reasoning over structured legal knowledge. The TRISM approach addresses the above limitations while maintaining interpretable decision pathways. Our framework formalizes the extraction of symbolic knowledge from legal textual documents and incorporates Retrieval-Augmented Generation (RAG) as a core component for grounding LLM outputs in verified legal sources. In this position paper, we make the following contributions: (1) An analysis of the limitations of AI in law; (2) Introduce RASOR RAG which creates foundations for neurosymbolic RAG by generating explicit interpretable rationales that could be formalized into symbolic representations; (3) A formalized methodology for creating symbolic legal knowledge bases that support both interpretable reasoning and output verification in LLMs; and (4) The TRISM framework for integrating symbolic legal knowledge with LLMs. --- ### Your Agent Has a Genome: Sequence-Level Behavioral Analysis and Runtime Governance of LLM-Powered Autonomous Agents Authors: Sidi Deng Published: 2026-04-05 Categories: cs.AI, cs.LG, cs.MA, cs.SE arXiv: https://arxiv.org/abs/2606.15579v1 We propose Base Sequence Analysis, a framework that encodes the runtime behavior of LLM-powered autonomous agents into compact symbolic sequences using a four-letter alphabet: X (Explore), E (Execute), P (Plan), and V (Verify). Drawing an analogy to genomic sequence analysis, we apply n-gram pattern mining, Markov transition matrices, and point-biserial correlation to 347 real-world execution traces collected from a production ReAct agent system over 8 days. Our analysis reveals that (1) the trigram P-X-P is the only statistically significant high-risk pattern, lowering success rate by 10.4%; (2) P-ratio is the strongest negative predictor of success (r=-0.256, p<0.0001); and (3) the E->V transition probability is only 2.1%, indicating a systemic verification deficit. Based on these findings, we design Governor, a three-layer runtime intervention system comprising a rule engine, a statistical accumulator, and a chi-square-based threshold adaptor. In a natural before/after deployment evaluation (N=101 vs. N=246), Governor achieves a +6.2% absolute increase in task success rate while simultaneously reducing average token consumption by 44%. To validate cross-system generality, we apply the XEPV encoding to 2,000 public SWE-agent trajectories on SWE-bench, confirming that exploration spirals and the E->V verification deficit replicate in an independent system. We outline six research directions including base sequence language models, cross-agent behavioral fingerprinting, and reward shaping, and release an open-source toolkit for reproducibility. --- ### MedicalBench: Evaluating Large Language Models Toward Improved Medical Concept Extraction Authors: Zhichao Yang, Gregory D. Lyng, Sanjit Singh Batra, Robert E. Tillman Published: 2026-04-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.20197v1 Medical concept extraction from electronic health records underpins many downstream applications, yet remains challenging because medically meaningful concepts are frequently implied rather than explicitly stated in medical narratives. Existing benchmarks with human-annotated evidence spans underscore the importance of grounding extracted concepts in medical text. However, they predominantly focus on explicitly stated concepts instead of implicit concepts. We present MedicalBench, a benchmark for medical concept extraction with evidence grounding that evaluates implicit medical reasoning. MedicalBench formulates medical concept extraction as a verification task over medical note-concept pairs, coupled with sentence-level evidence identification. Built from MIMIC-IV discharge summaries and human-verified ICD-10 codes, the dataset is curated through a multi-stage large language model (LLM) triage pipeline followed by medical annotation and expert review. It deliberately includes implicit positives, semantically confusable negatives, and cases where LLM judgments disagree with medical expert assessments. We define two complementary evaluation tasks: (1) medical concept extraction and (2) sentence-level evidence retrieval, enabling assessment of both correctness and interpretability. Benchmarking state-of-the-art LLMs reveals that performance remains modest, highlighting the difficulty of extracting implicitly expressed concepts. We further show that performance is largely invariant to note length, indicating that MedicalBench isolates reasoning difficulty rather than superficial confounders. MedicalBench provides the first systematic benchmark for implicit, evidence-grounded medical concept extraction, offering a foundation for developing medical language models that can both identify medically relevant concepts and justify their predictions in a transparent and medically faithful manner. --- ### Data Scaling as Progressive Coverage of a Predictive Contribution Spectrum Authors: Zihui Song, Shihao Ji, Hongxi Li, Shuaizhi Cheng, Chunlin Huang Published: 2026-04-05 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.20196v1 We investigate the hypothesis that real-data scaling laws are governed by progressive coverage of a latent predictive contribution spectrum rather than by token-frequency tails alone. We work with a suffix-automaton representation of text corpora and define a data-intrinsic global-KL predictive contribution spectrum, in which each state contributes according to its empirical mass times its KL deviation from a global next-token baseline. Across 12 real corpora, the tail slope of this spectrum is already strongly correlated with the empirical data-scaling exponent of a fixed small GPT learner. We then go beyond slope correlation and define, for each training size N, an effective truncation rank K(N) by matching the observed excess loss to the residual tail mass of the prepared 1000k global-KL spectrum. Empirically, log K is close to linear in log N, with pooled R^2 about 0.96 for the raw spectrum and R^2 about 0.90 for the smoothed spectrum. These findings provide strong empirical support for a simple mechanism picture: training scale advances an effective frontier through a predictive state spectrum, and the residual tail mass of that spectrum tracks the remaining excess loss. --- ### Interoceptive Divergence in Aesthetic Evaluation and Implications for Human-AI Alignment Authors: Yoshia Abe, Tatsuya Daikoku, Yasuo Kuniyoshi Published: 2026-04-05 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2605.18759v1 Artificial intelligence (AI), exemplified by large language models (LLMs), is rapidly approaching and in some cases surpassing human performance across a wide range of cognitive tasks. However, human nature is not limited to intelligence alone; it also encompasses sensibility, including the capacity to perceive and experience beauty in visual scenes. This raises a fundamental question: how humans and AI systems converge or diverge in such aesthetic experiences. Aesthetic evaluation depends not only on objective properties of images but also on internal processes within the observer. As part of ongoing efforts in AI alignment, building upon prior human studies that have examined the relationship between beauty ratings, bodily sensations, and emotions, we adopt a comparable set of questionnaire items and present them to LLMs, enabling a direct comparison between human and AI responses. Our comparative analyses revealed that, while humans and AI exhibited broadly similar patterns in the correlations between beauty ratings and emotions, as well as in the image features they prioritized, notable divergences emerged in both the distribution of emotional responses and the relationship between beauty ratings and bodily sensations. These findings suggest that state-of-the-art LLMs, trained on large-scale textual data, can approximate average human tendencies in aesthetic evaluation to a certain extent. However, they also indicate limitations, particularly in relation to interoceptive aspects, which may reflect insufficient representation in training data or unintended consequences of alignment processes. These findings highlight key challenges for AI alignment and suggest important directions for developing AI systems with human-like aesthetic processing. --- ### StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing Authors: Roberto Tacconelli Published: 2026-04-05 Categories: cs.LG, cs.IT arXiv: https://arxiv.org/abs/2605.02904v1 We present StateSMix, a fully self-contained lossless compressor that couples an online-trained Mamba-style State Space Model (SSM) with sparse n-gram context mixing and arithmetic coding. The model is initialised from scratch and trained token-by-token on the file being compressed, requiring no pre-trained weights, no GPU, and no external dependencies. The SSM (DM=32, NL=2, approximately 120K active parameters per file) provides a continuously-updated probability estimate over BPE tokens, while nine sparse n-gram hash tables (bigram through 32-gram, 16M slots each) add exact local and long-range pattern memorisation via a softmax-invariant logit-bias mechanism that updates only non-zero-count tokens. An entropy-adaptive scaling mechanism modulates the n-gram contribution based on the SSM's predictive confidence, preventing over-correction when the neural model is already well-calibrated. On the standard enwik8 benchmark, StateSMix achieves 2.123 bpb on 1 MB, 2.149 bpb on 3 MB, and 2.162 bpb on 10 MB, beating xz -9e (LZMA2) by 8.7%, 5.4%, and 0.7% respectively. Ablation experiments establish the SSM as the dominant compression engine: it alone accounts for a 46.6% size reduction over a frequency-count baseline and beats xz without any n-gram component, while n-gram tables provide a complementary 4.1% gain through exact context memorisation. OpenMP parallelisation of the training loop yields 1.9x speedup on 4 cores. The system is implemented in pure C with AVX2 SIMD and processes approximately 2,000 tokens per second on commodity x86-64 hardware. --- ### AI Agents for Sustainable SMEs: A Green ESG Assessment Framework Authors: Viet Trinh, Tan Nguyen, Minh-Huyen Phan, Quan Luu Published: 2026-04-05 Categories: cs.AI, econ.GN arXiv: https://arxiv.org/abs/2605.00841v1 This study presents a novel, AI-driven framework for assessing Environmental, Social, and Governance (ESG) performance in European small and medium-sized enterprises (SMEs). An initial phase established expert-validated ESG baseline scores from a subset of the Flash Eurobarometer FL549 survey data. In the second phase, a scalable AI agent system, built on the n8n automation platform, applied these baselines to perform automated ESG classification and generate contextual recommendations using large language models (LLMs). The results demonstrate the AI system's high consistency with human-derived outputs, thereby supporting more effective monitoring and intervention strategies aligned with the European Green Deal. --- ### 2026 Roadmap on Artificial Intelligence and Machine Learning for Smart Manufacturing Authors: Jay Lee, Hanqi Su, Marco Macchi, Adalberto Polenghi, Wei Wu, Zhiheng Zhao, George Q. Huang, Kiva Allgood, Devendra Jain, Benedikt Gieger, Vibhor Pandhare, Soumyabrata Bhattacharjee et al. Published: 2026-04-05 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.00839v1 The evolution of artificial intelligence (AI) and machine learning (ML) is reshaping smart manufacturing by providing new capabilities for efficiency, adaptability, and autonomy across industrial value chains. However, the deployment of AI and ML in industrial settings still faces critical challenges, including the complexity of industrial big data, effective data management, integration with heterogeneous sensing and control systems, and the demand for trustworthy, explainable, and reliable operation in high-stakes industrial environments. In this roadmap, we present a comprehensive perspective on the foundations, applications, and emerging directions of AI and ML in smart manufacturing. It is structured in three parts. The first highlights the foundations and trends that frame the evolution of AI in smart manufacturing. The second focuses on key topics where AI is already enabling advances, including industrial big data analytics, advanced sensing and perception, autonomous systems, additive and laser-based manufacturing, digital twins, robotics, supply chain and logistics optimization, and sustainable manufacturing. The third section explores non-traditional ML approaches that are opening new frontiers, such as physics-informed AI, generative AI, semantic AI, advanced digital twins, explainable AI, RAMS, data-centric metrology, LLMs, and foundation models for highly connected and complex manufacturing systems. By identifying both opportunities and remaining barriers across these areas, this roadmap outlines the advances needed in methods, integration strategies, and industrial adoption. We hope this roadmap will serve as a guide for researchers, engineers, and practitioners to accelerate innovation, align academic and industrial priorities, and ensure that AI-driven smart manufacturing delivers reliable, sustainable, and scalable impact for the future of manufacturing ecosystems. --- ### Simulating Validity: Modal Decoupling in MLLM Generated Feedback on Science Drawings Authors: Arne Bewersdorff, Nejla Yuruk, Xiaoming Zhai Published: 2026-04-05 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.26957v1 In science education, students frequently construct hand-drawn visual models of scientific phenomena. These drawings rely on a visual structure where information is encoded through visual objects, their attributes, and relationships. Multimodal large language models (MLLMs) are increasingly used to generate feedback on students' hand-drawn scientific models. However, the validity of such feedback depends on whether model claims are grounded in the specific visual evidence of the student drawing. This study uncovers grounding failures, consistent with modal decoupling, in off-the-shelf MLLM feedback, where outputs remain pedagogically plausible in form while contradicting the drawing or treating depicted elements as missing. Using N = 150 middle school drawings from a kinetic molecular theory unit spanning five modeling tasks and three competence levels, we generated N = 300 feedback instances with GPT-5.1. All outputs were coded for four grounding error types: object mismatch, attribute mismatch, relation mismatch, and false absence. Grounding failures were common: 41.3% of feedback instances contained at least one error. An inventory-list-first workflow reduced several error categories and lowered the overall error rate, but it did not resolve the underlying limitation: approximately one in three outputs remained flawed, with false absence as the dominant failure mode. Moreover, feedback that appears visually grounded offered little diagnostic value for identifying invalid instances. The findings indicate that modal decoupling is a substantial limitation and that valid feedback will require grounding mechanisms beyond common prompting strategies. --- ### Non-Destructive Prediction of Fruit Ripeness and Firmness Using Hyperspectral Imaging and Lightweight Machine Learning Models Authors: Phongsakon Mark Konrad, Casper Kunstmann-Olsen, Jacek Fiutowski, Serkan Ayvaz Published: 2026-04-05 Categories: eess.IV, cs.LG arXiv: https://arxiv.org/abs/2604.22788v1 Post-harvest fruit quality assessment is essential for reducing food waste, yet reliable non-destructive methods typically depend on expensive hyperspectral cameras and computationally intensive deep learning models. These systems typically require GPU resources, large-scale training data, and domain expertise, limiting their feasibility for many real-world agricultural settings. This study systematically evaluates 20 classical machine learning algorithms on hyperspectral imaging data for simultaneous ripeness classification and firmness prediction across five fruit species, using cross-validated experimental design with Bayesian hyperparameter optimization. Data preprocessing strategy, particularly class balancing and spectral transformations, contributes as much to prediction accuracy as algorithm choice. Our results show that tree-based machine learning models can outperform state-of-the-art deep earning models reported in Fruit-HSNet. Moreover, the findings indicate that only three visible-range wavelengths are needed to recover over 94% of full-spectrum accuracy, demonstrating that low-cost multispectral sensors combined with lightweight machine learning models can serve as practical alternatives to expensive hyperspectral cameras and complex deep learning approaches for practical fruit quality sorting. --- ### Conformal PM2.5 Mapping Under Spatial Covariate Shift: Satellite-Reanalysis Fusion for Africa's Green Industrial Transition Authors: Yaw Osei Adjei, Davis Opoku, Ephraim Abotsi, Kwadwo Owusu Amanqua, Oliver Kornyo, Elisha Soglo-Ahianyo, Cephas Anertey Abbey Published: 2026-04-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.22787v1 Africa's green industrialization imperative demands reliable infrastructure for monitoring air quality. We present a satellite-reanalysis PM2.5 fusion system trained on 2,068,901 records from 404 monitoring locations in 29 African countries (OpenAQ, 2017-2022), combining LightGBM with leakage-resistant spatial cross-validation and conformal prediction to quantify predictions and their geographic applicability limits. Under 5-fold location-grouped spatial cross-validation, LightGBM achieves RMSE = 30.83 +/- 5.07 ug/m3, MAE = 14.54 +/- 1.66 ug/m3, R2 = 0.134 +/- 0.023, and macro F1 = 0.336 +/- 0.018. This R2 is substantially below random-split benchmarks (>0.90) but reflects true geographic generalisation difficulty rather than model failure. Split conformal prediction targeting 90% marginal coverage reveals severe East Africa degradation (actual PICP = 65.3% vs. nominal 90%), consistent with medium-strength covariate shift (humidity KS = 0.2237, sat_pblh KS = 0.2558). We operationalise these findings through regional reliability flags (High/Medium/Low/Unreliable) and a monitor prioritisation score directing infrastructure expansion toward highest-burden unmonitored populations, directly supporting Africa's green industrial transition and SDGs 3.9, 7.1.2, 9, 11.6.2, and 13. --- ### Towards Verified and Targeted Explanations through Formal Methods Authors: Hanchen David Wang, Diego Manzanas Lopez, Preston K. Robinette, Ipek Oguz, Taylor T. Johnson, Meiyi Ma Published: 2026-04-05 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2604.14209v1 As deep neural networks are deployed in safety-critical domains such as autonomous driving and medical diagnosis, stakeholders need explanations that are interpretable but also trustworthy with formal guarantees. Existing XAI methods fall short: heuristic attribution techniques (e.g., LIME, Integrated Gradients) highlight influential features but offer no mathematical guarantees about decision boundaries, while formal methods verify robustness yet remain untargeted, analyzing the nearest boundary regardless of whether it represents a critical risk. In safety-critical systems, not all misclassifications carry equal consequences; confusing a "Stop" sign for a "60 kph" sign is far more dangerous than confusing it with a "No Passing" sign. We introduce ViTaX (Verified and Targeted Explanations), a formal XAI framework that generates targeted semifactual explanations with mathematical guarantees. For a given input (class y) and a user-specified critical alternative (class t), ViTaX: (1) identifies the minimal feature subset most sensitive to the y->t transition, and (2) applies formal reachability analysis to guarantee that perturbing these features by epsilon cannot flip the classification to t. We formalize this through Targeted epsilon-Robustness, certifying whether a feature subset remains robust under perturbation toward a specific target class. ViTaX is the first method to provide formally guaranteed explanations of a model's resilience against user-identified alternatives. Evaluations on MNIST, GTSRB, EMNIST, and TaxiNet demonstrate over 30% fidelity improvement with minimal explanation cardinality. --- ### Belief-Aware VLM Model for Human-like Reasoning Authors: Anshul Nayak, Shahil Shaik, Yue Wang Published: 2026-04-05 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.09686v2 Traditional neural network models for intent inference rely heavily on observable states and struggle to generalize across diverse tasks and dynamic environments. Recent advances in Vision Language Models (VLMs) and Vision Language Action (VLA) models introduce common-sense reasoning through large-scale multimodal pretraining, enabling zero-shot performance across tasks. However, these models still lack explicit mechanisms to represent and update belief, limiting their ability to reason like humans or capture the evolving human intent over long-horizon. To address this, we propose a belief-aware VLM framework that integrates retrieval-based memory and reinforcement learning. Instead of learning an explicit belief model, we approximate belief using a vector-based memory that retrieves relevant multimodal context, which is incorporated into the VLM for reasoning. We further refine decision-making using a reinforcement learning policy over the VLM latent space. We evaluate our approach on publicly available VQA datasets such as HD-EPIC and demonstrate consistent improvements over zero-shot baselines, highlighting the importance of belief-aware reasoning. --- ### A Modular Zero-Shot Pipeline for Accident Detection, Localization, and Classification in Traffic Surveillance Video Authors: Amey Thakur, Sarvesh Talele Published: 2026-04-05 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.09685v1 We describe a zero-shot pipeline developed for the ACCIDENT @ CVPR 2026 challenge. The challenge requires predicting when, where, and what type of traffic accident occurs in surveillance video, without labeled real-world training data. Our method separates the problem into three independent modules. The first module localizes the collision in time by running peak detection on z-score normalized frame-difference signals. The second module finds the impact location by computing the weighted centroid of cumulative dense optical flow magnitude maps using the Farneback algorithm. The third module classifies collision type by measuring cosine similarity between CLIP image embeddings of frames near the detected peak and text embeddings built from multi-prompt natural language descriptions of each collision category. No domain-specific fine-tuning is involved; the pipeline processes each video using only pre-trained model weights. Our implementation is publicly available as a Kaggle notebook. --- ### The Art of Building Verifiers for Computer Use Agents Authors: Corby Rosset, Pratyusha Sharma, Andrew Zhao, Miguel Gonzalez-Fernandez, Ahmed Awadallah Published: 2026-04-05 Categories: cs.CR, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.06240v1 Verifying the success of computer use agent (CUA) trajectories is a critical challenge: without reliable verification, neither evaluation nor training signal can be trusted. In this paper, we present lessons learned from building a best-in-class verifier for web tasks we call the Universal Verifier. We design the Universal Verifier around four key principles: 1) constructing rubrics with meaningful, non-overlapping criteria to reduce noise; 2) separating process and outcome rewards that yield complementary signals, capturing cases where an agent follows the right steps but gets blocked or succeeds through an unexpected path; 3) distinguishing between controllable and uncontrollable failures scored via a cascading-error-free strategy for finer-grained failure understanding; and 4) a divide-and-conquer context management scheme that attends to all screenshots in a trajectory, improving reliability on longer task horizons. We validate these findings on CUAVerifierBench, a new set of CUA trajectories with both process and outcome human labels, showing that our Universal Verifier agrees with humans as often as humans agree with each other. We report a reduction in false positive rates to near zero compared to baselines like WebVoyager ($\geq$ 45\%) and WebJudge ($\geq$ 22\%). We emphasize that these gains stem from the cumulative effect of the design choices above. We also find that an auto-research agent achieves 70\% of expert quality in 5\% of the time, but fails to discover all strategies required to replicate the Universal Verifier. We open-source our Universal Verifier system along with CUAVerifierBench; available at https://github.com/microsoft/fara. --- ### Learning Stable Predictors from Weak Supervision under Distribution Shift Authors: Mehrdad Shoeibi, Elias Hossain, Ivan Garibay, Niloofar Yousefi Published: 2026-04-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.05002v3 Learning from weak, proxy, or relative supervision is common when ground-truth labels are unavailable, but robustness under distribution shift remains poorly understood because the supervision mechanism itself may change across environments. We formalize this phenomenon as supervision drift, defined as changes in $P(y \mid x, c)$ across contexts, and study it in CRISPR-Cas13d transcriptomic perturbation experiments where guide efficacy is inferred indirectly from RNA-seq responses. Using publicly available data spanning two human cell lines and multiple post-induction timepoints, we construct a controlled non-IID benchmark with explicit domain (cell line) and temporal shifts, while reusing a fixed weak-label construction across all contexts to avoid changing targets. Across linear and tree-based models, weak supervision supports meaningful learning in-domain (ridge $R^2 = 0.356$, Spearman $ρ= 0.442$) and partial cross-cell-line transfer ($ρ\approx 0.40$). In contrast, temporal transfer collapses across all model classes considered, yielding negative $R^2$ and weak or near-zero $ρ$ (ridge $R^2 = -0.145$, $ρ= 0.008$; XGBoost $R^2 = -0.155$, $ρ= 0.056$; random forest $R^2 = -0.322$, $ρ= 0.139$). Additional robustness analyses using externally recomputed weak labels, shift-score quantification, and simple mitigation baselines preserve the same qualitative pattern. Feature-label association and feature-importance analyses remain relatively stable across cell lines but change sharply over time, indicating that failures arise from supervision drift rather than model capacity or simple covariate shift. These results show that strong in-domain performance under weak supervision can be misleading and motivate feature stability as a lightweight diagnostic for non-transferability before deployment. --- ### Closed-Loop Autonomous Software Development via Jira-Integrated Backlog Orchestration: A Case Study in Deterministic Control and Safety-Constrained Automation Authors: Elias Calboreanu Published: 2026-04-05 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.05000v1 This paper presents a closed-loop system for software lifecycle management framed as a control architecture rather than a code-generation tool. The system manages a backlog of approximately 1,602 rows across seven task families, ingests 13 structured source documents, and executes a deterministic seven-stage pipeline implemented as seven scheduled automation lanes. The automation stack comprises approximately 12,661 lines of Python across 23 scripts plus 6,907 lines of versioned prompt specifications, with checkpoint-based time budgets, 101 exception handlers, and 12 centralized lock mechanisms implemented through four core functions and eight reusable patterns. A Jira Status Contract provides externally observable collision locking, and a degraded-mode protocol supports continued local operation when Jira is unavailable. Artificial-intelligence assistance is bounded by structured context packages, configured resource caps, output re-validation, and human review gates. A formal evaluation of the initial 152-run window yielded 100% terminal-state success with a 95% Clopper-Pearson interval of (97.6%, 100%); the system has since accumulated more than 795 run artifacts in continuous operation. Three rounds of adversarial code review identified 51 findings, all closed within the study scope (48 fully remediated, 3 closed with deferred hardening), with zero false negatives within the injected set. In an autonomous security ticket family of 10 items, six were completed through pipeline-autonomous dispatch and verification, two required manual remediation, and two were closed by policy decision. The results indicate that bounded, traceable lifecycle automation is practical when autonomy is embedded within explicit control, recovery, and audit mechanisms. --- ### PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities Authors: Kai Yu, Shuang Zhou, Yiran Song, Zaifu Zhan, Jie Peng, Kaixiong Zhou, Tianlong Chen, Feng Xie, Meng Wang, Huazhu Fu, Mingquan Lin, Rui Zhang Published: 2026-04-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.04999v1 Multimodal self-supervised pretraining offers a promising route to cancer prognosis by integrating histopathology whole-slide images, gene expression, and pathology reports, yet most existing approaches require fully paired and complete inputs. In practice, clinical cohorts are fragmented and often miss one or more modalities, limiting both supervised fusion and scalable multimodal pretraining. We propose PRIME, a missing-aware multimodal self-supervised pretraining framework that learns robust and transferable representations from partially observed cohorts. PRIME maps heterogeneous modality embeddings into a unified token space and introduces a shared prototype memory bank for latent-space semantic imputation via patient-level consensus retrieval, producing structurally aligned tokens without reconstructing raw signals. Two complementary pretraining objectives: inter-modality alignment and post-fusion consistency under structured missingness augmentation, jointly learn representations that remain predictive under arbitrary modality subsets. We evaluate PRIME on The Cancer Genome Atlas with label-free pretraining on 32 cancer types and downstream 5-fold evaluation on five cohorts across overall survival prediction, 3-year mortality classification, and 3-year recurrence classification. PRIME achieves the best macro-average performance among all compared methods, reaching 0.653 C-index, 0.689 AUROC, and 0.637 AUROC on the three tasks, respectively, while improving robustness under test-time missingness and supporting parameter-efficient and label-efficient adaptation. These results support missing-aware multimodal pretraining as a practical strategy for prognosis modeling in fragmented clinical data settings. --- ### El Nino Prediction Based on Weather Forecast and Geographical Time-series Data Authors: Viet Trinh, Ha-Vy Luu, Quoc-Khiem Nguyen-Pham, Hung Tong, Thanh-Huyen Tran, Hoai-Nam Nguyen Dang Published: 2026-04-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.04998v1 This paper proposes a novel framework for enhancing the prediction accuracy and lead time of El Niño events, crucial for mitigating their global climatic, economic, and societal impacts. Traditional prediction models often rely on oceanic and atmospheric indices, which may lack the granularity or dynamic interplay captured by comprehensive meteorological and geographical datasets. Our framework integrates real-time global weather forecast data with anomalies, subsurface ocean heat content, and atmospheric pressure across various temporal and spatial resolutions. Leveraging a hybrid deep learning architecture that combines a Convolutional Neural Network (CNN) for spatial feature extraction and a Long Short-Term Memory (LSTM) network for temporal dependency modeling, the framework aims to identify complex precursors and evolving patterns of El Niño events. --- ### Evaluation of Embedding-Based and Generative Methods for LLM-Driven Document Classification: Opportunities and Challenges Authors: Rong Lu, Hao Liu, Song Hou Published: 2026-04-05 Categories: cs.IR, cs.AI, cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.04997v1 This work presents a comparative analysis of embedding-based and generative models for classifying geoscience technical documents. Using a multi-disciplinary benchmark dataset, we evaluated the trade-offs between model accuracy, stability, and computational cost. We find that generative Vision-Language Models (VLMs) like Qwen2.5-VL, enhanced with Chain-of-Thought (CoT) prompting, achieve superior zero-shot accuracy (82%) compared to state-of-the-art multimodal embedding models like QQMM (63%). We also demonstrate that while supervised fine-tuning (SFT) can improve VLM performance, it is sensitive to training data imbalance. --- ### Learning-Based Multi-Criteria Decision Making Model for Sawmill Location Problems Authors: Mahid Ahmed, Ali Dogru, Chaoyang Zhang, Chao Meng Published: 2026-04-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.04996v1 Strategically locating a sawmill is vital for enhancing the efficiency, profitability, and sustainability of timber supply chains. Our study proposes a Learning-Based Multi-Criteria Decision-Making (LB-MCDM) framework that integrates machine learning (ML) with GIS-based spatial location analysis via MCDM. The proposed framework provides a data-driven, unbiased, and replicable approach to assessing site suitability. We demonstrate the utility of the proposed model through a case study in Mississippi (MS). We apply five ML algorithms (Random Forest Classifier, Support Vector Classifier, XGBoost Classifier, Logistic Regression, and K-Nearest Neighbors Classifier) to identify the most suitable sawmill locations in Mississippi. Among these models, the Random Forest Classifier achieved the highest performance. We use the SHAP (SHapley Additive exPlanations) technique to determine the relative importance of each criterion, revealing the Supply-Demand Ratio, a composite feature that reflects local market competition dynamics, as the most influential factor, followed by Road, Rail Line and Urban Area Distance. The validation of suitability maps generated by our LB-MCDM model suggests that 10-11% of the MS landscape is highly suitable for sawmill location. --- ### The Hiremath Early Detection (HED) Score: A Measure-Theoretic Evaluation Standard for Temporal Intelligence Authors: Prakul Sunil Hiremath Published: 2026-04-05 Categories: stat.ML, cs.CR, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2604.04993v1 We introduce the Hiremath Early Detection (HED) Score, a principled, measure-theoretic evaluation criterion for quantifying the time-value of information in systems operating over non-stationary stochastic processes subject to abrupt regime transitions. Existing evaluation paradigms, chiefly the ROC/AUC framework and its downstream variants, are temporally agnostic: they assign identical credit to a detection at t + 1 and a detection at t + tau for arbitrarily large tau. This indifference to latency is a fundamental inadequacy in time-critical domains including cyber-physical security, algorithmic surveillance, and epidemiological monitoring. The HED Score resolves this by integrating a baseline-neutral, exponentially decaying kernel over the posterior probability stream of a target regime, beginning precisely at the onset of the regime shift. The resulting scalar simultaneously encodes detection acuity, temporal lead, and pre-transition calibration quality. We prove that the HED Score satisfies three axiomatic requirements: (A1) Temporal Monotonicity, (A2) Invariance to Pre-Attack Bias, and (A3) Sensitivity Decomposability. We further demonstrate that the HED Score admits a natural parametric family indexed by the Hiremath Decay Constant (lambda_H), whose domain-specific calibration constitutes the Hiremath Standard Table. As an empirical vehicle, we present PARD-SSM (Probabilistic Anomaly and Regime Detection via Switching State-Space Models), which couples fractional Stochastic Differential Equations (fSDEs) with a Switching Linear Dynamical System (S-LDS) inference backend. On the NSL-KDD benchmark, PARD-SSM achieves a HED Score of 0.0643, representing a 388.8 percent improvement over a Random Forest baseline (0.0132), with statistical significance confirmed via block-bootstrap resampling (p < 0.001). We propose the HED Score as the successor evaluation standard to ROC/AUC. --- ### FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment Authors: Daniel Kuznetsov, Ofir Cohen, Karin Shistik, Rami Puzis, Asaf Shabtai Published: 2026-04-05 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.04992v1 Safety-aligned LLMs go through refusal training to reject harmful requests, but whether these mechanisms remain effective under emotionally charged stimuli is unexplored. We introduce FreakOut-LLM, a framework investigating whether emotional context compromises safety alignment in adversarial settings. Using validated psychological stimuli, we evaluate how emotional priming through system prompts affects jailbreak susceptibility across ten LLMs. We test three conditions (stress, relaxation, neutral) using scenarios from established psychological protocols, plus a no-prompt baseline, and evaluate attack success using HarmBench on AdvBench prompts. Stress priming increases jailbreak success by 65.2\% compared to neutral conditions (z = 5.93, p < 0.001; OR = 1.67, Cohen's d = 0.28), while relaxation priming produces no effect (p = 0.84). Five of ten models show significant vulnerability, with the largest effects concentrated in open-weight models. Logistic regression on 59,800 queries confirms stress as the sole significant condition predictor after controlling for prompt length (p = 0.61) and model identity. Measured psychological state strongly predicts attack success (|r|\geq0.70 across five instruments; all p < 0.001 in individual-level logistic regression). These results establish emotional context as a measurable attack surface with implications for real-world AI deployment in high-stress domains. --- ### Architecture Without Architects: How AI Coding Agents Shape Software Architecture Authors: Phongsakon Mark Konrad, Tim Lukas Adam, Riccardo Terrenzi, Serkan Ayvaz Published: 2026-04-05 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.04990v1 AI coding agents select frameworks, scaffold infrastructure, and wire integrations, often in seconds. These are architectural decisions, yet almost no one reviews them as such. We identify five mechanisms by which agents make implicit architectural choices and propose six prompt-architecture coupling patterns that map natural-language prompt features to the infrastructure they require. The patterns range from contingent couplings (structured output validation) that may weaken as models improve to fundamental ones (tool-call orchestration) that persist regardless of model capability. An illustrative demonstration confirms that prompt wording alone produces structurally different systems for the same task. We term the phenomenon vibe architecting, architecture shaped by prompts rather than deliberate design, and outline review practices, decision records, and tooling to bring these hidden decisions under governance. --- ### Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression Authors: Longsheng Zhou, Yu Shen Published: 2026-04-05 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.04988v1 Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression proxies such as parameter count or FLOPs do not reliably predict wall-clock inference time. In particular, unstructured sparsity can reduce model storage while failing to accelerate (and sometimes slightly slowing down) standard CPU execution due to irregular memory access and sparse kernel overhead. Motivated by this gap between compression and acceleration, we study a practical, ordered pipeline that targets measured latency by combining three widely used techniques: unstructured pruning, INT8 quantization-aware training (QAT), and knowledge distillation (KD). Empirically, INT8 QAT provides the dominant runtime benefit, while pruning mainly acts as a capacity-reduction pre-conditioner that improves the robustness of subsequent low-precision optimization; KD, applied last, recovers accuracy within the already constrained sparse INT8 regime without changing the deployment form. We evaluate on CIFAR-10/100 using three backbones (ResNet-18, WRN-28-10, and VGG-16-BN). Across all settings, the ordered pipeline achieves a stronger accuracy-size-latency frontier than any single technique alone, reaching 0.99-1.42 ms CPU latency with competitive accuracy and compact checkpoints. Controlled ordering ablations with a fixed 20/40/40 epoch allocation further confirm that stage order is consequential, with the proposed ordering generally performing best among the tested permutations. Overall, our results provide a simple guideline for edge deployment: evaluate compression choices in the joint accuracy-size-latency space using measured runtime, rather than proxy metrics alone. --- ### Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling Authors: Yongchang Hao, Lili Mou Published: 2026-04-05 Categories: cs.LG, cs.AI, math.OC, stat.ML arXiv: https://arxiv.org/abs/2604.04987v1 Speculative sampling (SpS) has been successful in accelerating the decoding throughput of auto-regressive large language models by leveraging smaller draft models. SpS strictly enforces the generated distribution to match that of the verifier LLM. This is unnecessarily restrictive as slight variations of the verifier's distribution, such as sampling with top-$k$ or temperature, would also be acceptable. Typical acceptance sampling (TAS) alleviates this issue by accepting more tokens using entropy-based heuristics. However, this approach distorts the verifier distribution, potentially degrading output quality when the verifier encodes critical information. In this work, we formalize the speculative sampling algorithm through the lens of constrained optimization. Based on this formulation, we propose Cactus (constrained acceptance speculative sampling), a method that guarantees controlled divergence from the verifier distribution and increasing acceptance rates. Empirical results across a wide range of benchmarks confirm the effectiveness of our approach. ---