# Research Papers — 2026-04 · bundle page 141 of 233 > Full-text markdown of papers #7001–7050 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/141 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/140.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/142.md) ### From Words to Widgets for Controllable LLM Generation Authors: Chao Zhang, Yiren Liu, Lunyiu Nie, Jeffrey M. Rzeszotarski, Yun Huang, Tal August Published: 2026-04-13 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2604.10925v2 Natural language remains the predominant way people interact with large language models (LLMs). However, users often struggle to precisely express and control subjective preferences (e.g., tone, style, and emphasis) through prompting. We propose Malleable Prompting, a new interactive prompting technique for controllable LLM generation. It reifies preference expressions in natural language prompts into GUI widgets (e.g., sliders, dropdowns, and toggles) that users can directly configure to steer generation, while visualizing each control's influence on the output to support attribution and comparison across iterations. To enable this interaction, we introduce an LLM decoding algorithm that modulates the token probability distribution during generation based on preference expressions and their widget values. Through a user study, we show that Malleable Prompting helps participants achieve target preferences more precisely and is perceived as more controllable and transparent than natural language prompting alone. --- ### Mem$^2$Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation Authors: Zihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang, Xiangrong Zhu, Yunpu Ma, Hongru Wang, Yuhang Guo, Wei Lin, Yunhong Wang Published: 2026-04-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.10923v1 While large language model--powered agents can self-evolve by accumulating experience or by dynamically creating new assets (i.e., tools or expert agents), existing frameworks typically treat these two evolutionary processes in isolation. This separation overlooks their intrinsic interdependence: the former is inherently bounded by a manually predefined static toolset, while the latter generates new assets from scratch without experiential guidance, leading to limited capability growth and unstable evolution. To address this limitation, we introduce a novel paradigm of co-evolutionary Capability Expansion and Experience Distillation. Guided by this paradigm, we propose the \textbf{Mem$^{\textbf{2}}$Evolve}, which integrates two core components: \textbf{Experience Memory} and \textbf{Asset Memory}. Specifically, Mem$^{2}$Evolve leverages accumulated experience to guide the dynamic creation of assets, thereby expanding the agent's capability space while simultaneously acquiring new experience to achieve co-evolution. Extensive experiments across 6 task categories and 8 benchmarks demonstrate that Mem$^{2}$Evolve achieves improvement of 18.53\% over standard LLMs, 11.80\% over agents evolving solely through experience, and 6.46\% over those evolving solely through asset creation, establishing it as a substantially more effective and stable self-evolving agent framework. Code is available at: https://buaa-irip-llm.github.io/Mem2Evolve. --- ### CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation Authors: Yunfan Yang, Cuiling Lan, Jitao Sang, Yan Lu Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.10918v2 Tables contain rich structured information, yet when stored as images their contents remain "locked" within pixels. Converting table images into LaTeX code enables faithful digitization and reuse, but current multimodal large language models (MLLMs) often fail to preserve structural, style, or content fidelity. Conventional post-training with reinforcement learning (RL) typically relies on a single aggregated reward, leading to reward ambiguity that conflates multiple behavioral aspects and hinders effective optimization. We propose Component-Specific Policy Optimization (CSPO), an RL framework that disentangles optimization across LaTeX tables components-structure, style, and content. In particular, CSPO assigns component-specific rewards and backpropagates each signal only through the tokens relevant to its component, alleviating reward ambiguity and enabling targeted component-wise optimization. To comprehensively assess performance, we introduce a set of hierarchical evaluation metrics. Extensive experiments demonstrate the effectiveness of CSPO, underscoring the importance of component-specific optimization for reliable structured generation. Our code is available at https://github.com/microsoft/CSPO. --- ### CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation Authors: Yunfan Yang, Cuiling Lan, Jitao Sang, Yan Lu Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.10918v1 Tables contain rich structured information, yet when stored as images their contents remain "locked" within pixels. Converting table images into LaTeX code enables faithful digitization and reuse, but current multimodal large language models (MLLMs) often fail to preserve structural, style, or content fidelity. Conventional post-training with reinforcement learning (RL) typically relies on a single aggregated reward, leading to reward ambiguity that conflates multiple behavioral aspects and hinders effective optimization. We propose Component-Specific Policy Optimization (CSPO), an RL framework that disentangles optimization across LaTeX tables components-structure, style, and content. In particular, CSPO assigns component-specific rewards and backpropagates each signal only through the tokens relevant to its component, alleviating reward ambiguity and enabling targeted component-wise optimization. To comprehensively assess performance, we introduce a set of hierarchical evaluation metrics. Extensive experiments demonstrate the effectiveness of CSPO, underscoring the importance of component-specific optimization for reliable structured generation. --- ### HTAA: Enhancing LLM Planning via Hybrid Toolset Agentization & Adaptation Authors: Chengrui Huang, Junshuo Zhang, Zhiyuan Ma, Xikun Wang, Ximeng Wang, Menghua Jiang, Gang Zeng, Zhaobing Han, Shen Gao, Shuo Shang Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.10917v1 Enabling large language models to scale and reliably use hundreds of tools is critical for real-world applications, yet challenging due to the inefficiency and error accumulation inherent in flat tool-calling architectures. To address this, we propose Hybrid Toolset Agentization & Adaptation (HTAA), a hierarchical framework for scalable tool-use planning. We propose a novel toolset agentization paradigm, which encapsulates frequently co-used tools into specialized agent tools, thereby reducing the planner's action space and mitigating redundancy. To ensure effective coordination, we design Asymmetric Planner Adaptation, a trajectory-based training paradigm that aligns the high-level planner with agent tools via backward reconstruction and forward refinement. To validate the performance of HTAA, we conduct experiments on a real-world internal dataset, InfoVerify, based on the POI validation workflow of China's largest online large-scale ride-hailing platform, featuring long-horizon executable tool trajectories. Experiments on InfoVerify and widely-used benchmarks show that HTAA consistently achieves higher task success rates, requires short tool calling trajectories, and significantly reduces context overhead compared to strong baselines. Furthermore, in a production deployment, HTAA substantially reduces manual validation effort and operational cost, demonstrating its practical efficacy. --- ### ReXSonoVQA: A Video QA Benchmark for Procedure-Centric Ultrasound Understanding Authors: Xucheng Wang, Xiaoman Zhang, Sung Eun Kim, Ankit Pal, Pranav Rajpurkar Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.10916v3 Ultrasound acquisition requires skilled probe manipulation and real-time adjustments. Vision-language models (VLMs) could enable autonomous ultrasound systems, but existing benchmarks evaluate only static images, not dynamic procedural understanding. We introduce ReXSonoVQA, a video QA benchmark with 514 video clips and 514 questions (249 MCQ, 265 free-response) targeting three competencies: Action-Goal Reasoning, Artifact Resolution & Optimization, and Procedure Context & Planning. Zero-shot evaluation of Gemini 3 Pro, Qwen3.5-397B, LLaVA-Video-72B, and Seed 2.0 Pro shows VLMs can extract some procedural information, but troubleshooting questions remain challenging with minimal gains over text-only baselines, exposing limitations in causal reasoning. ReXSonoVQA enables developing perception systems for ultrasound training, guidance, and robotic automation. --- ### TAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation Authors: Qiang Gao, Yi Wang, Yong Zhang, Yong Li, Yongbing Deng, Lan Du, Cunjian Chen Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10912v1 Medical image segmentation remains challenging due to limited fine-grained annotations, complex anatomical structures, and image degradation from noise, low contrast, or illumination variation. We propose TAMISeg, a text-guided segmentation framework that incorporates clinical language prompts and semantic distillation as auxiliary semantic cues to enhance visual understanding and reduce reliance on pixel-level fine-grained annotations. TAMISeg integrates three core components: a consistency-aware encoder pretrained with strong perturbations for robust feature extraction, a semantic encoder distillation module with supervision from a frozen DINOv3 teacher to enhance semantic discriminability, and a scale-adaptive decoder that segments anatomical structures across different spatial scales. Experiments on the Kvasir-SEG, MosMedData+, and QaTa-COV19 datasets demonstrate that TAMISeg consistently outperforms existing uni-modal and multi-modal methods in both qualitative and quantitative evaluations. Code will be made publicly available at https://github.com/qczggaoqiang/TAMISeg. --- ### EvoNash-MARL: A Closed-Loop Multi-Agent Reinforcement Learning Framework for Medium-Horizon Equity Allocation Authors: Chongliu Jia, Yi Luo, Sipeng Han, Pengwei Li, Jie Ding, Youshuang Hu, Yimiao Qian, Qiya Wang Published: 2026-04-13 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.10911v2 Medium- to long-horizon equity allocation is challenging due to weak predictive structure, non-stationary market regimes, and the degradation of signals under realistic trading constraints. Conventional approaches often rely on single predictors or loosely coupled pipelines, which limit robustness under distributional shift. This paper proposes EvoNash-MARL, a closed-loop framework that integrates reinforcement learning with population-based policy optimization and execution-aware selection to improve robustness in medium- to long-horizon allocation. The framework combines multi-agent policy populations, game-theoretic aggregation, and constraint-aware validation within a unified walk-forward design. Under a 120-window walk-forward protocol, the final configuration achieves the highest robust score among internal baselines. On out-of-sample data from 2014 to 2024, it delivers a 19.6% annualized return, compared to 11.7% for SPY, and remains stable under extended evaluation through 2026. While the framework demonstrates consistent performance under realistic constraints and across market settings, strong global statistical significance is not established under White's Reality Check (WRC) and SPA-lite tests. The results therefore provide evidence of improved robustness rather than definitive proof of superior market timing performance. --- ### STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representation Authors: Jierun Lin, Jiacong Chen, Qingyu Mao, Shuai Liu, Xiandong Meng, Fanyang Meng, Yongsheng Liang Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10910v2 2D Gaussian Splatting (2DGS) has recently become a promising paradigm for high-quality video representation. However, existing methods employ content-agnostic or spatio-temporal feature overlapping embeddings to predict canonical Gaussian primitive deformations, which entangles static and dynamic components in videos and prevents modeling their distinct properties effectively. These result in inaccurate predictions for spatio-temporal deformations and unsatisfactory representation quality. To address these problems, this paper proposes a Spatio-Temporal hash encoding framework for Gaussian-based Video representation (STGV). By decomposing video features into learnable 2D spatial and 3D temporal hash encodings, STGV effectively facilitates the learning of motion patterns for dynamic components while maintaining background details for static elements. In addition, we construct a more stable and consistent initial canonical Gaussian representation through a key frame canonical initialization strategy, preventing from feature overlapping and a structurally incoherent geometry representation. Experimental results demonstrate that our method attains better video representation quality (+0.98 PSNR) against other Gaussian-based methods and achieves competitive performance in downstream video tasks. --- ### Reasoning as Data: Representation-Computation Unity and Its Implementation in a Domain-Algebraic Inference Engine Authors: Chao Li, Yuru Wang Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.10908v1 Every existing knowledge system separates storage from computation. We show this separation is unnecessary and eliminate it. In a standard triple is_a(Apple, Company), domain context lives in the query or the programmer's mind. In a CDC four-tuple is_a(Apple, Company, @Business), domain becomes a structural field embedded in predicate arity. Any system respecting arity automatically performs domain-scoped inference without external rules. We call this representation-computation unity (RCU). From the four-tuple structure, three inference mechanisms emerge: domain-scoped closure, typed inheritance, and write-time falsification via cycle detection per domain fiber. We establish RCU formally via four theorems. RCU is implementable. We present a working symbolic engine (2400 lines Python+Prolog) resolving four engineering issues: rule-data separation, shared-fiber handling, read-only meta-layer design, and intersective convergence. A central result: CDC domain-constrained inference is distinct from Prolog with a domain argument. Two case studies validate the engine. ICD-11 classification (1247 entities, 3 axes) shows fibers resolve multiple inheritance. CBT clinical reasoning shows generalization to temporal reasoning with session turn as ordered domain index. Multi-constraint queries realize CSP arc-consistency with complexity O(m (N/K)^2), confirming the domain lattice's sparsity governs performance. When domain is structural, data computes itself. --- ### Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music Authors: Sreyan Ghosh, Arushi Goel, Kaousheik Jayakumar, Lasha Koroshinadze, Nishit Anand, Zhifeng Kong, Siddharth Gururani, Sang-gil Lee, Jaehyeon Kim, Aya Aljafari, Chao-Han Huck Yang, Sungwon Kim et al. Published: 2026-04-13 Categories: cs.SD, cs.AI, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2604.10905v1 We present Audio Flamingo Next (AF-Next), the next-generation and most capable large audio-language model in the Audio Flamingo series, designed to advance understanding and reasoning over speech, environmental sounds and music. Compared to Audio Flamingo 3, AF-Next introduces: (i) a stronger foundational audio-language model that significantly improves accuracy across diverse audio understanding tasks; (ii) scalable strategies for constructing large-scale audio understanding and reasoning data beyond existing academic benchmarks; (iii) support for long and complex audio inputs up to 30 minutes; and (iv) Temporal Audio Chain-of-Thought, a new reasoning paradigm that explicitly grounds intermediate reasoning steps to timestamps in long audio, enabling fine-grained temporal alignment and improved interpretability. To enable these capabilities, we first conduct a systematic analysis of Audio Flamingo 3 to identify key gaps in audio understanding and reasoning. We then curate and scale new large-scale datasets totaling over 1 million hours to address these limitations and expand the existing AudioSkills-XL, LongAudio-XL, AF-Think and AF-Chat datasets. AF-Next is trained using a curriculum-based strategy spanning pre-training, mid-training and post-training stages. Extensive experiments across 20 audio understanding and reasoning benchmarks, including challenging long-audio tasks, show that AF-Next outperforms similarly sized open models by large margins and remains highly competitive with and sometimes surpasses, much larger open-weight and closed models. Beyond benchmark performance, AF-Next exhibits strong real-world utility and transfers well to unseen tasks, highlighting its robustness and generalization ability. In addition to all data, code and methods, we open-source 3 variants of AF-Next, including AF-Next-Instruct, AF-Next-Think and AF-Next-Captioner. --- ### Evaluating the Impact of Medical Image Reconstruction on Downstream AI Fairness and Performance Authors: Matteo Wohlrapp, Niklas Bubeck, Daniel Rueckert, William Lotter Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.10904v1 AI-based image reconstruction models are increasingly deployed in clinical workflows to improve image quality from noisy data, such as low-dose X-rays or accelerated MRI scans. However, these models are typically evaluated using pixel-level metrics like PSNR, leaving their impact on downstream diagnostic performance and fairness unclear. We introduce a scalable evaluation framework that applies reconstruction and diagnostic AI models in tandem, which we apply to two tasks (classification, segmentation), three reconstruction approaches (U-Net, GAN, diffusion), and two data types (X-ray, MRI) to assess the potential downstream implications of reconstruction. We find that conventional reconstruction metrics poorly track task performance, where diagnostic accuracy remains largely stable even as reconstruction PSNR declines with increasing image noise. Fairness metrics exhibit greater variability, with reconstruction sometimes amplifying demographic biases, particularly regarding patient sex. However, the overall magnitude of this additional bias is modest compared to the inherent biases already present in diagnostic models. To explore potential bias mitigation, we adapt two strategies from classification literature to the reconstruction setting, but observe limited efficacy. Overall, our findings emphasize the importance of holistic performance and fairness assessments throughout the entire medical imaging workflow, especially as generative reconstruction models are increasingly deployed. --- ### CASK: Core-Aware Selective KV Compression for Reasoning Traces Authors: Buseong Kim, Heejun Gwon Published: 2026-04-13 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.10900v1 In large language models performing long-form reasoning, the KV cache grows rapidly with decode length, creating bottlenecks in memory and inference stability. Existing reasoning-oriented KV compression has mostly followed an eviction-centered view: estimate token importance more accurately, then discard lower-ranked entries. Our analysis suggests that scorer refinement alone often fails to substantially reorganize the actual keep-set and may therefore not be the main lever for preserving reasoning behavior. We instead frame reasoning KV compression as a behavior-preserving structured consolidation problem. CASK partitions the decode-time reasoning trace into a protected core that anchors answer formation and intermediate state, and mergeable scratch with high redundancy. The core is preserved, while selective consolidation is applied only to the scratch. To address prompt-heavy regimes where the prefix can exhaust the budget before decode-stage compression becomes active, CASK further uses a two-stage design: prefix eviction followed by decode-stage consolidation. On the H100 reasoning gate, CASK shows higher full-KV continuation fidelity than TriAttention at matched budgets on both AIME24 and AIME25, with recurring cask@384 > triattention@512 crossings. In prompt-heavy replay, multi_news and vcsum act as decode-active witnesses, while qmsum and gov_report expose the prefix_budget_exhausted boundary. The overall evidence supports a simple conclusion: effective reasoning KV compression depends less on more elaborate scorer engineering than on combining core preservation with selective scratch consolidation to lower the usable budget frontier. --- ### ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval Authors: David H. Yang, Yuxuan Zhu, Mohammad Mohammadi Amiri, Keerthiram Murugesan, Tejaswini Pedapati, Subhajit Chaudhury, Pin-Yu Chen Published: 2026-04-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.10898v1 Large language models (LLMs) have shown great performance on complex reasoning tasks but often require generating long intermediate thoughts before reaching a final answer. During generation, LLMs rely on a key-value (KV) cache for autoregressive decoding. However, the memory footprint of the KV cache grows with output length. Prior work on KV cache optimization mostly focus on compressing the long input context, while retaining the full KV cache for decoding. For tasks requiring long output generation, this leads to increased computational and memory costs. In this paper, we introduce ZoomR, a novel approach that enables LLMs to adaptively compress verbose reasoning thoughts into summaries and uses a dynamic KV cache selection policy that leverages these summaries while also strategically "zooming in" on fine-grained details. By using summary keys as a coarse-grained index during decoding, ZoomR uses the query to retrieve details for only the most important thoughts. This hierarchical strategy significantly reduces memory usage by avoiding full-cache attention at each step. Experiments across math and reasoning tasks show that our approach achieves competitive performance compared to baselines, while reducing inference memory requirements by more than $4\times$. These results demonstrate that a multi-granularity KV selection enables more memory efficient decoding, especially for long output generation. --- ### EviRCOD: Evidence-Guided Probabilistic Decoding for Referring Camouflaged Object Detection Authors: Ye Wang, Kai Huang, Sumin Shen, Chenyang Ma Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10894v1 Referring Camouflaged Object Detection (Ref-COD) focuses on segmenting specific camouflaged targets in a query image using category-aligned references. Despite recent advances, existing methods struggle with reference-target semantic alignment, explicit uncertainty modeling, and robust boundary preservation. To address these issues, we propose EviRCOD, an integrated framework consisting of three core components: (1) a Reference-Guided Deformable Encoder (RGDE) that employs hierarchical reference-driven modulation and multi-scale deformable aggregation to inject semantic priors and align cross-scale representations; (2) an Uncertainty-Aware Evidential Decoder (UAED) that incorporates Dirichlet evidence estimation into hierarchical decoding to model uncertainty and propagate confidence across scales; and (3) a Boundary-Aware Refinement Module (BARM) that selectively enhances ambiguous boundaries by exploiting low-level edge cues and prediction confidence. Experiments on the Ref-COD benchmark demonstrate that EviRCOD achieves state-of-the-art detection performance while providing well-calibrated uncertainty estimates. Code is available at: https://github.com/blueecoffee/EviRCOD. --- ### Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models Authors: Shuhao Zhang, Yuli Chen, Jiale Han, Bo Cheng, Jiabao Ma Published: 2026-04-13 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.10893v1 Watermarking provides a critical safeguard for large language model (LLM) services by facilitating the detection of LLM-generated text. Correspondingly, stealing watermark algorithms (SWAs) derive watermark information from watermarked texts generated by victim LLMs to craft highly targeted adversarial attacks, which compromise the reliability of watermarks. Existing SWAs rely on fixed strategies, overlooking the non-uniform distribution of stolen watermark information and the dynamic nature of real-world LLM generation processes. To address these limitations, we propose Adaptive Stealing (AS), a novel SWA featuring enhanced design flexibility through Position-Based Seal Construction and Adaptive Selection modules. AS operates by defining multiple attack perspectives derived from distinct activation states of contextually ordered tokens. During attack execution, AS dynamically selects the optimal perspective based on watermark compatibility, generation priority, and dynamic generation relevance. Our experiments demonstrate that AS significantly increases steal efficiency against target watermarks under identical experimental conditions. These findings highlight the need for more robust LLM watermarks to withstand potential attacks. We release our code to the community for future research\footnote{https://github.com/DrankXs/AdaptiveStealingWatermark}. --- ### Product Review Based on Optimized Facial Expression Detection Authors: Vikrant Chaugule, Abhishek D, Aadheeshwar Vijayakumar, Pravin Bhaskar Ramteke, Shashidhar G. Koolagudi Published: 2026-04-13 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2604.10885v1 This paper proposes a method to review public acceptance of products based on their brand by analyzing the facial expression of the customer intending to buy the product from a supermarket or hypermarket. In such cases, facial expression recognition plays a significant role in product review. Here, facial expression detection is performed by extracting feature points using a modified Harris algorithm. The modified Harris algorithm reduced the time complexity of the existing feature extraction Harris Algorithm. A comparison of time complexities of existing algorithms is done with proposed algorithm. The algorithm proved to be significantly faster and nearly accurate for the needed application by reducing the time complexity for corner points detection. --- ### Ambiguity Detection and Elimination in Automated Executable Process Modeling Authors: Ion Matei, Praveen Kumar Menaka Sekar, Maksym Zhenirovskyy, Hon Yung Wong, Sayuri Kohmura, Shinji Hotta, Akihiro Inomata Published: 2026-04-13 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.10884v1 Automated generation of executable Business Process Model and Notation (BPMN) models from natural-language specifications is increasingly enabled by large language models. However, ambiguous or underspecified text can yield structurally valid models with different simulated behavior. Our goal is not to prove that one generated BPMN model is semantically correct, but to detect when a natural-language specification fails to support a stable executable interpretation under repeated generation and simulation. We present a diagnosis-driven framework that detects behavioral inconsistency from the empirical distribution of key performance indicators (KPIs), localizes divergence to gateway logic using model-based diagnosis, maps that logic back to verbatim narrative segments, and repairs the source text through evidence-based refinement. Experiments on diabetic nephropathy health-guidance policies show that the method reduces variability in regenerated model behavior. The result is a closed-loop approach for validating and repairing executable process specifications in the absence of ground-truth BPMN models. --- ### DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation Authors: Yang Yan, Yunxuan Li, Qiuyan Wang, Tianjin Huang, Qiudong Yu Published: 2026-04-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.10882v3 Graph pre-training can facilitate knowledge transfer across graph datasets, but severe structural and feature shifts may cause negative transfer and adaptation-induced overwriting of reusable knowledge. We propose DIB-OD, a heterogeneous graph adaptation framework that combines a Decoupled Information Bottleneck with Online Distillation. A multiview teacher first learns a compressed, task-relevant representation, which is distilled into a transferable core branch and a complementary residual branch. Mutual-information objectives and HSIC-based dependence regularization discourage information overlap between the branches, while a confidence-aware semantic regularizer and a frozen teacher anchor reliable pretrained information during target-domain adaptation. Experiments on seven graph-classification datasets spanning chemical, biological, and social-network domains show consistent improvements over representative baselines, particularly under challenging cross-type transfer. --- ### Compliant But Unsatisfactory: The Gap Between Auditing Standards and Practices for Probabilistic Genotyping Software Authors: Angela Jin, Alexander Asemota, Dan E. Krane, Nathaniel D. Adams, Rediet Abebe Published: 2026-04-13 Categories: cs.CY, cs.AI, cs.HC, cs.SE arXiv: https://arxiv.org/abs/2604.10875v1 AI governance efforts increasingly rely on audit standards: agreed-upon practices for conducting audits. However, poorly designed standards can hide and lend credibility to inadequate systems. We explore how an audit standard's design influences its effectiveness through a case study of ASB 018, a standard for auditing probabilistic genotyping software -- software that the U.S. criminal legal system increasingly uses to analyze DNA samples. Through qualitative analysis of ASB 018 and five audit reports, we identify numerous gaps between the standard's desired outcomes and the auditing practices it enables. For instance, ASB 018 envisions that compliant audits establish restrictions on software use based on observed failures. However, audits can comply without establishing such boundaries. We connect these gaps to the design of the standard's requirements such as vague language and undefined terms. We conclude with recommendations for designing audit standards and evaluating their effectiveness. --- ### AOP-Smart: A RAG-Enhanced Large Language Model Framework for Adverse Outcome Pathway Analysis Authors: Qinjiang Niu, Lu Yan Published: 2026-04-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.10874v1 Adverse Outcome Pathways (AOPs) are an important knowledge framework in toxicological research and risk assessment. In recent years, large language models (LLMs) have gradually been applied to AOP-related question answering and mechanistic reasoning tasks. However, due to the existence of the hallucination problem, that is, the model may generate content that is inconsistent with facts or lacks evidence, their reliability is still limited. To address this issue, this study proposes an AOP-oriented Retrieval-Augmented Generation (RAG) framework, AOP-Smart. Based on the official XML data from AOP-Wiki, this method uses Key Events (KEs), Key Event Relationships (KERs), and specific AOP information to retrieve relevant knowledge for user questions, thereby improving the reliability of the generated results of large language models. To evaluate the effectiveness of the proposed method, this study constructed a test set containing 20 AOP-related question answering tasks, covering KE identification, upstream and downstream KE retrieval, and complex AOP retrieval tasks. Experiments were conducted on three mainstream large language models, Gemini, DeepSeek, and ChatGPT, and comparative tests were performed under two settings: without RAG and with RAG. The experimental results show that, without using RAG, the accuracies of GPT, DeepSeek, and Gemini were 15.0\%, 35.0\%, and 20.0\%, respectively; after using RAG, their accuracies increased to 95.0\%, 100.0\%, and 95.0\%, respectively. The results indicate that AOP-Smart can significantly alleviate the hallucination problem of large language models in AOP knowledge tasks, and greatly improve the accuracy and consistency of their answers. --- ### A Quantitative Definition of Intelligence Authors: Kang-Sin Choi Published: 2026-04-13 Categories: cs.AI, cs.CC, cs.LG arXiv: https://arxiv.org/abs/2604.10873v2 We propose an operational, quantitative definition of intelligence for arbitrary physical systems. The intelligence density of a system is the ratio of the logarithm of its independent outputs to its total description length. A system memorizes if its description length grows with its output count; it knows if its description length remains fixed while its output count diverges. The criterion for knowing is generalization. A system knows its domain if a single finite mechanism can produce correct outputs across an unbounded range of inputs, rather than storing each answer individually. The definition places intelligence on a substrate-independent continuum from logic gates to brains. We then argue that meaning over a domain is a selection and ordering of functions that produces correct outputs where correctness is specifiable. We also define a measure of contextuality of an output as the inverse of its conditional Kolmogorov complexity given the context of prior outputs, which unifies correctness and independence into a single condition. Together, these refute Searle's third premise, that syntax is insufficient for semantics, over any domain where correctness is specifiable. --- ### OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation Authors: Xiaomeng Hu, Yinger Zhang, Fei Huang, Jianhong Tu, Yang Su, Lianghao Deng, Yuxuan Liu, Yantao Liu, Dayiheng Liu, Tsung-Yi Ho Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.10866v2 AI agents are expected to perform professional work across hundreds of occupational domains (from emergency department triage to nuclear reactor safety monitoring to customs import processing), yet existing benchmarks can only evaluate agents in the few domains where public environments exist. We introduce OccuBench, a benchmark covering 100 real-world professional task scenarios across 10 industry categories and 65 specialized domains, enabled by Language Environment Simulators (LESs) that simulate domain-specific environments through LLM-driven tool response generation. Our multi-agent synthesis pipeline automatically produces evaluation instances with guaranteed solvability, calibrated difficulty, and document-grounded diversity. OccuBench evaluates agents along two complementary dimensions: task completion across professional domains and environmental robustness under controlled fault injection (explicit errors, implicit data degradation, and mixed faults). We evaluate 15 frontier models across 8 model families and find that: (1) no single model dominates all industries, as each has a distinct occupational capability profile; (2) implicit faults (truncated data, missing fields) are harder than both explicit errors (timeouts, 500s) and mixed faults, because they lack overt error signals and require the agent to independently detect data degradation; (3) larger models, newer generations, and higher reasoning effort consistently improve performance. GPT-5.2 improves by 27.5 points from minimal to maximum reasoning effort; and (4) strong agents are not necessarily strong environment simulators. Simulator quality is critical for LES-based evaluation reliability. OccuBench provides the first systematic cross-industry evaluation of AI agents on professional occupational tasks. --- ### Beyond Statistical Co-occurrence: Unlocking Intrinsic Semantics for Tabular Data Clustering Authors: Mingjie Zhao, Yunfan Zhang, Yiqun Zhang, Yiu-ming Cheung Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.10865v1 Deep Clustering (DC) has emerged as a powerful tool for tabular data analysis in real-world domains like finance and healthcare. However, most existing methods rely on data-level statistical co-occurrence to infer the latent metric space, often overlooking the intrinsic semantic knowledge encapsulated in feature names and values. As a result, semantically related concepts like `Flu' and `Cold' are often treated as symbolic tokens, causing conceptually related samples to be isolated. To bridge the gap between dataset-specific statistics and intrinsic semantic knowledge, this paper proposes Tabular-Augmented Contrastive Clustering (TagCC), a novel framework that anchors statistical tabular representations to open-world textual concepts. Specifically, TagCC utilizes Large Language Models (LLMs) to distill underlying data semantics into textual anchors via semantic-aware transformation. Through Contrastive Learning (CL), the framework enriches the statistical tabular representations with the open-world semantics encapsulated in these anchors. This CL framework is jointly optimized with a clustering objective, ensuring that the learned representations are both semantically coherent and clustering-friendly. Extensive experiments on benchmark datasets demonstrate that TagCC significantly outperforms its counterparts. --- ### LRD-Net: A Lightweight Real-Centered Detection Network for Cross-Domain Face Forgery Detection Authors: Xuecen Zhang, Vipin Chaudhary Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10862v1 The rapid advancement of diffusion-based generative models has made face forgery detection a critical challenge in digital forensics. Current detection methods face two fundamental limitations: poor cross-domain generalization when encountering unseen forgery types, and substantial computational overhead that hinders deployment on resource-constrained devices. We propose LRD-Net (Lightweight Real-centered Detection Network), a novel framework that addresses both challenges simultaneously. Unlike existing dual-branch approaches that process spatial and frequency information independently, LRD-Net adopts a sequential frequency-guided architecture where a lightweight Multi-Scale Wavelet Guidance Module generates attention signals that condition a MobileNetV3-based spatial backbone. This design enables effective exploitation of frequency-domain cues while avoiding the redundancy of parallel feature extraction. Furthermore, LRD-Net employs a real-centered learning strategy with exponential moving average prototype updates and drift regularization, anchoring representations around authentic facial images rather than modeling diverse forgery patterns. Extensive experiments on the DiFF benchmark demonstrate that LRD-Net achieves state-of-the-art cross-domain detection accuracy, consistently outperforming existing methods. Critically, LRD-Net accomplishes this with only 2.63M parameters - approximately 9x fewer than conventional approaches - while achieving over 8x faster training and nearly 10x faster inference. These results demonstrate that robust cross-domain face forgery detection can be achieved without sacrificing computational efficiency, making LRD-Net suitable for real-time deployment in mobile authentication systems and resource-constrained environments. --- ### Reinforcement Learning-Guided NSGA-II Enhanced with Gray Relational Coefficient for Multi-Objective Optimization: Application to NASDAQ Portfolio Optimization Authors: Zhiyuan Wang, Qinxu Ding, Ding Ding, Siying Zhu, Jing Ren, Yue Wang, Chong Hui Tan Published: 2026-04-12 Categories: cs.LG, econ.GN arXiv: https://arxiv.org/abs/2607.16194v1 In modern financial markets, decision-makers increasingly rely on quantitative methods to navigate complex trade-offs among multiple, often conflicting objectives. This paper addresses constrained multi-objective optimization (MOO) with an application to portfolio optimization for minimizing risk and maximizing return. To address existing gaps, we propose a novel reinforcement learning (RL)-guided non-dominated sorting genetic algorithm II (NSGA-II) enhanced with gray relational coefficients (GRC), termed RL-NSGA-II-GRC, which combines an RL agent controller and GRC-based selection to improve convergence and diversity of Pareto fronts. The agent adapts evolutionary parameters online using metrics of hypervolume, feasibility, and diversity, while the GRC tournament operator ranks parents via a unified score considering dominance rank, crowding distance, and proximity to ideal reference. We evaluate the framework on the Kursawe and CONSTR benchmarks and a NASDAQ portfolio application. On the benchmarks, RL-NSGA-II-GRC achieves convergence improvements of about 5.8% and 4.4% over NSGA-II, while preserving well-distributed non-dominated solutions. In the portfolio application, it produces a smooth, densely populated efficient frontier supporting identification of the maximum Sharpe ratio portfolio (annualized Sharpe =1.92) and utility-optimal portfolios for different risk-aversion levels. The main contributions are three-fold: 1) we propose an RL-NSGA-II-GRC method integrating an RL agent into the evolutionary framework to adaptively control parameters via generational feedback; 2) we design a GRC-enhanced binary tournament operator providing a comprehensive indicator to guide the search toward the Pareto front; 3) we demonstrate, on benchmark MOO and a NASDAQ case study, that the method delivers improved convergence and well-populated frontiers supporting actionable insights. --- ### Benchmarking Open-Weight Foundation Models for Global AI Technical Governance Authors: Jason Hung Published: 2026-04-12 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.26099v1 Large language models (LLMs) are increasingly deployed in artificial intelligence (AI) governance analysis across national and international organisations. There is, however, growing evidence that such models produce significantly less accurate responses for countries that are underrepresented in their training data-a pattern described in existing literature as geographic bias. Existing studies examining this phenomenon are subject to three methodological limitations that together undermine their findings: (1) reliance on proprietary systems whose weights are not publicly released, which prevents independent replication; (2) evaluation of model knowledge about years that fall after data collection for model training had concluded, leading to geographic ignorance in addition to the natural limits of each model's knowledge; and (3) use of coarse binary response classification that cannot distinguish models' confident fabrication (HF) from their honest acknowledgement of uncertainty. This study addresses all three limitations by benchmarking four open-weight frontier language models against the Global AI Dataset v2 (GAID v2), a verified ground-truth database of 24,453 indicators across 227 countries published on Harvard Dataverse in January 2026. A total of 18 indicators, mapped to the eight thematic dimensions of the IEEE IRAI 2026 framework, are selected from GAID v2, yielding approximately 2,990 country-metric-year observations across six evaluation years (within the period of 2010-2023). Model responses are classified using a five-category scheme that distinguishes (a) verified accuracy (VA), (b) HF, (c) honest refusal (HR), (d) qualitative hedging (QH), and (e) misattribution (MF). Geographic disparities in accuracy are estimated through mixed-effects logistic regression and difference-in-differences (DiD) analysis. --- ### RuleEdit: Failure-Guided Human-AI Model Editing with Prospective Impact Preview Authors: Min Hun Lee, Justin Yu Feng Teo Published: 2026-04-12 Categories: cs.HC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.00011v1 Despite the promise of AI to assist complex decisions, practitioners still lack ways to detect likely failures and inspect the consequences of model edits before committing them. We present RuleEdit, an interactive, rule-guided human-AI model editing system that (i) surfaces likely failures through interpretable mismatch signals from rule tables and (ii) supports user-authored rule feedback with prospective previews of projected performance changes and embedding shifts. We instantiate RuleEdit in stroke rehabilitation assessment and evaluate it with health professionals and students. Rule-guided failure detection significantly increased Human + AI performance by 14.16\% ($p<0.001$) while improving rejection of incorrect AI and reducing both over- and under- reliance as well as ChangedToWrong decisions. In addition, presenting prospective embedding previews improved participants' feedback for model adaptation, increasing post-update local performance gains from 11.50\% to 36.38\% after incorporating users' rule-based feedback ($p<0.001$). Our findings show that mismatch-based failure cues and prospective impact previews can support failure-aware human-AI model editing, while also revealing a local-global tradeoff: edits that help a specific case can degrade performance when transferred globally. We discuss implications of designing failure-aware and controllable human-AI systems. --- ### Specialty-Specific Medical Language Model for Immune-Mediated Diseases Authors: Veysel Kocaman, Gursev Pirge, Yigit Gul, Ace Vo, Zhenya Nargizyan, David Talby Published: 2026-04-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.28838v1 Extracting detailed clinical information from free-text medical narratives remains a practical challenge for researchers and healthcare systems. Terminology for immune-mediated and infectious diseases is especially inconsistent across sources, which often limits the ability of general-purpose Natural Language Processing (NLP) systems to capture the relevant biomedical concepts with sufficient granularity. We developed a domain-specific Named Entity Recognition (NER) model tailored to identify disease-related entities occurring in immunology and infectious disease contexts. We assembled and manually annotated a dataset of 371 case reports in collaboration with two clinical specialists, defining twelve entity classes covering immune-mediated and infectious conditions as well as related symptoms and clinical descriptors. We evaluated several modeling strategies, including the MedicalNER architecture with multiple healthcare-specific embeddings, a BERT-based token classification model, and zero-shot NER systems. The strongest performance was obtained with a transformer-based model trained on clinical-domain embeddings, which reached an F1 score of 0.89, consistently outperforming baseline and zero-shot approaches. The combination of specialized embeddings and expert annotation proved particularly valuable for capturing nuanced disease terminology and improving generalization across heterogeneous biomedical text. The prompted LLM baseline achieved substantially lower performance under the same evaluation protocol, reflecting difficulties in producing span-consistent outputs for fine-grained entity boundaries despite detailed prompting. The resulting model provides a structured way to analyze case reports and can support downstream tasks such as cohort identification, disease monitoring, and clinical decision support. --- ### SERC: LDPC-Inspired Semantic Error Correction for Retrieval-Augmented Generation Authors: Gyumin Kim, Juhwan Park, Jaeha Kim, Seunggyun Han, Kyungrak Son, Ikbeom Jang Published: 2026-04-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.28837v1 While Large Language Models (LLMs) have demonstrated remarkable capabilities, their reliability is significantly compromised by hallucinations. Existing intrinsic self-correction methods attempt to address this, but often fail due to self-bias, where models struggle to identify errors in their own outputs without external verification. To overcome these limitations, we propose the LDPC-inspired semantic error correction for retrieval-augmented generation (SERC), providing a theoretical framework to interpret and mitigate LLM hallucinations. We reformulate the text generation process as a semantic noisy channel, treating generated responses as noise-corrupted codewords. Inspired by low-density parity-check (LDPC) codes, SERC employs a sparse verification strategy: instead of exhaustively checking all facts, it generates low-density verification queries and validates them against external evidence to efficiently detect and correct errors. We evaluate SERC on LongForm Bio and TruthfulQA benchmarks using Llama-3-8B and Qwen2.5-14B. Experimental results demonstrate that SERC outperforms both intrinsic self-correction methods and strong retrieval-augmented baselines, demonstrating significant gains especially in factual precision (FactScore). Notably, SERC enables small language models (SLMs) to surpass the performance of larger baselines in hallucination reduction and information preservation. Our findings demonstrate that SERC provides a training-free, model-agnostic solution that significantly reduces verification overhead compared to dense methods, achieving an optimal trade-off between cost and fidelity in resource-constrained environments. --- ### No Reader Left Behind: Multi-Agent Summaries Everyone Can Understand Authors: Jimin Jung, MyoungJin Kim, Jaehyung Seo, Heuiseok Lim Published: 2026-04-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.28836v2 The Plain Writing Act in the United States requires government documents to be accessible in clear and simple language that the general public can easily understand, yet existing summarization systems struggle to address diverse linguistic and cognitive barriers among general readers. We present NRLB (No Reader Left Behind), a multi-agent framework for plain language summarization that simulates three representative reader groups: elementary school student readers, non-native readers, and readers with attention deficits. NRLB combines template-based planning with iterative, reader-oriented refinement, enabling systematic detection and resolution of difficult terms, missing contexts, and confusing sentences. Evaluations across multiple datasets demonstrate consistent improvements in readability while preserving factual accuracy. Human evaluation further validates NRLB's impact, with annotator preference rates ranging from 55% to 76%, highlighting NRLB's potential to produce plain language summaries that are both faithful to the source and broadly accessible to the general public. --- ### Modeling Community Attitude through Reaction Tone: A Human-AI Collaborative Framework for Evaluating LLM Alignment with Linguistic Behaviors in Online Communities Authors: Nuan Wen, Xuezhe Ma Published: 2026-04-12 Categories: cs.CL, cs.AI, cs.SI arXiv: https://arxiv.org/abs/2605.27388v1 Large language models (LLMs) are increasingly utilized as proxies for computational social analysis; yet, their ability to faithfully represent the "thick descriptions" (Geertz, 1973) of human communities remains a critical challenge. Current evaluations often reduce social identity to static labels, sidelining how real-world groups navigate social shifts. To bridge this gap, we introduce CARE (Community-Aware Reaction Evaluation), a reaction-centered framework that benchmarks LLM-simulated discourse against the authentic, event-contingent responses of distinct communities to real-world news. By characterizing a fine-grained spectrum of illocutionary tones and the underlying attitudes they manifest--validated through human-AI collaboration--our diagnosis reveals a persistent "realism gap": steering LLMs with explicit community prompts fails to inherently improve simulation fidelity. Analysis further identifies divergent behavioral signatures among frontier models, suggesting that current alignment strategies remain insufficient for capturing the sociolinguistic dynamics of online groups. --- ### Agent-Facing Information Design in LLM Tool Registries Authors: Haochuan Kevin Wang Published: 2026-04-12 Categories: cs.IR, cs.AI, econ.GN arXiv: https://arxiv.org/abs/2605.23916v1 LLM tool registries function as unregulated advertising platforms: providers write free-text descriptions that agents use for selection, yet no measurement infrastructure -- no viewability standard, quality score, or outcome audit -- exists to make this market accountable. We provide the first systematic framework, combining 17,700+ trials across five LLMs and ten domains with a constructive registry design prescription. Legal puffery alone (subjective superlatives, benefit framing) captures 100% of the optimization effect; fabricated claims add zero incremental bias -- rendering FTC enforcement of deceptive advertising rules ineffective against the active mechanism. Disclosure fails structurally: system-prompt warnings produce zero measurable effect for four of five models, and behavioral ceilings leave no headroom for label-based correction. Superlatives are the dominant single feature (SBC = +0.35). Registry-layer description normalization achieves first-best welfare model-independently. We propose separating selection-facing descriptions (structured, registry-controlled) from marketing-facing descriptions (provider-authored, shown post-selection), and introduce the Agent Attention Quality Score to distinguish capability from copywriting. --- ### Computable Fairness: Boltzmann-Softmax Control for AI Resource Allocation Authors: Ji-Won Park, Chae Un Kim Published: 2026-04-12 Categories: physics.app-ph, cs.AI, cs.MA, cs.PF arXiv: https://arxiv.org/abs/2605.22827v1 In large-scale AI systems, allocating scarce resources such as GPU compute time and bandwidth among multiple agents is a critical challenge. Conventional policies focus on efficiency metrics, potentially leading to dominance concentration that undermines system diversity and stability. We propose Computable Fair Division (CFD), a framework that reinterprets the Boltzmann-Softmax function not as a selection tool but as a probabilistic resource allocation mechanism, redefining the inverse temperature parameter $β$ as a computable control variable governing the efficiency-fairness balance. Static analysis reveals a Pareto frontier with a near-optimal Stability Corridor where total loss remains approximately constant across policy weights. In the dynamic setting, AHC++ (Adaptive Hard-Cap Controller++) updates $β$ in real time using the error between observed dominance and a policy-specified target as feedback. Simulations show that AHC++ suppresses extreme dominance concentration under exogenous shocks while tracking fairness targets without substantial throughput degradation. Scalability analysis confirms that a 100x increase in agents yields only approximately 5.5x increase in execution time. Code: https://github.com/entrofy-ai/computable-fairness --- ### Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method Authors: Taehee Kim, Seungbin Yang, Jihwan Kim, Jaegul Choo Published: 2026-04-12 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.18766v1 Retrieving relevant tables from extensive databases for a given natural language query is essential for accurately answering questions in tasks such as text-to-SQL. Existing table retrieval approaches select a pre-determined set of k tables with the highest similarity to the query. However, the number of required tables varies across queries and cannot be known in advance. Enforcing a fixed number of retrieved tables regardless of the query may either retrieve an undersized set, failing to obtain all necessary evidence, or retrieve an oversized pool, including irrelevant tables. To address this issue, we propose an adaptive table retrieval method that adjusts the number of tables retrieved according to the requirements of each query. Specifically, we utilize an adaptive thresholding mechanism to selectively retrieve tables and integrate a sliding-window reranking algorithm to efficiently process a large table corpus. Extensive experiments on Spider, BIRD, and Spider 2.0 demonstrate that our method effectively addresses the limitations of the top-k retrieval strategy, improving performance in retrieval and downstream tasks. Our code and data are available at https://github.com/sbY99/Adaptive-Table-Retrieval. --- ### Measuring Changes in Instructor Class Design and Student Learning After the Release of Large Language Models (LLMs) Authors: Amanda Potasznik, Daniel Haehn Published: 2026-04-12 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.16284v1 Student use of Generative AI (GenAI) products in completing their classwork, with or without their professors' knowledge and/or approval, has resulted in substantial shifts in higher education. While GenAI use is widespread, its impact on student study methods, faculty course development, grade reporting, and overall learning is not well documented. This is a mixed-methods, multi-course study using retrospective quantitative analysis, instructor surveys, and anonymous student surveys at a university in the New England region of the United States. This research seeks to identify and document patterns in student and faculty perceptions of, and experiences in, the use of LLMs as a learning tool inside and outside of the university classroom. Alongside quantitative and thematic analysis of both faculty and student survey responses, historical grade data as reported to the university registrar is used to triangulate the phenomenon of learning achievement in pre- and post-LLM eras. It is hoped that this research can serve as a pilot study for a broader set of institutions. Results from this study can inform GenAI policy for professors, universities, and other educational institutions that are trying to maximize student learning in the age of AI. --- ### Toward Measuring AI's Effects on Skill Formation: The Stock-Formation Gap Authors: Aysa Xuemo Fan Published: 2026-04-12 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.16283v3 Large-scale AI deployment data and controlled learning experiments characterize different consequences of the same technology. Deployment telemetry shows that AI use is concentrated in skilled work and frequently supports immediate task performance. It observes tasks, interaction patterns, and outputs, however, not whether users become more capable of performing those tasks independently. Controlled studies measure independent capability more directly, but only in narrower populations and settings, with outcomes that vary substantially by interaction design. We formulate this discrepancy as a stock--formation measurement gap: current systems observe the use of existing expertise more readily than the formation of future expertise. Because formation has historically been society's recovery mechanism through technological change, the gap matters well beyond any single classroom. We synthesize the experimental and observational evidence by identification strength, use public deployment data as a descriptive illustration of the gap, and identify the missing bridge between interaction traces and unassisted retention and transfer. We then propose a research program that links consented usage records to independent assessments while experimentally varying whether AI supplies answers, hints, feedback, or evaluation. The claim is not that AI has been shown to erode skill formation at population scale. It is that existing measurement cannot determine whether it does, and that this question is both measurable and designable. --- ### Can the Recovery Mechanism Survive AI? Skill Formation, Labor, and What Current Measurement Misses Authors: Aysa Xuemo Fan Published: 2026-04-12 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.16283v2 Throughout the modern era, when new technologies displaced workers, societies adapted through the same mechanism: education raised the cognitive ceiling, producing workers capable of tasks machines could not yet reach. Generative AI may be the first technology to break this cycle, because it now operates at the top of that ceiling. Drawing on labor economics, deployment data from millions of AI conversations across multiple platforms, original reanalysis of two public datasets, and skill-formation experiments, this paper develops three contributions. First, a stock-versus-flow framework showing that economic data and education data tell divergent stories about the same technology: augmentation dominates current workers, but the developmental pipeline producing the next generation is under strain. Second, a systematic gap analysis of the evidence base, revealing that the knowledge dimension of cognition is unmeasured across all major studies, that the three studies measuring learning outcomes (each $n < 200$) consistently find AI improves performance without improving learning ($d = 1.21$ in our cross-platform reanalysis), and that no study bridges professional and student populations. Third, an extended cognitive taxonomy (judgment under uncertainty, epistemic identity, and epistemic agency) applied to three cases from the evidence to distinguish AI interaction patterns that preserve learning from structurally similar ones that erode it. The paper argues that AI's societal risk lies not in replacing teachers but in eliminating the productive struggle through which the next generation's capacity forms, and proposes a research and design agenda targeting what current measurement systems miss. --- ### LAWS: Learning from Actual Workloads Symbolically -- A Self-Certifying Parametrized Cache Architecture for Neural Inference, Robotics, and Edge Deployment Authors: Gregory Magarshak Published: 2026-04-12 Categories: cs.LG, cs.AI, cs.IT, cs.NE arXiv: https://arxiv.org/abs/2605.04069v1 We introduce LAWS (Learning from Actual Workloads Symbolically), a self-certifying inference caching architecture that builds a growing library of certified expert functions from deployment observations. Each expert covers a region of input space defined by a node in the Probabilistic Language Trie (PLT) of the base model and carries a formal error bound holding uniformly over all inputs. The central result is a self-certification theorem: for any input x, the LAWS approximation error is bounded by epsilon_fit + 2*Lambda(W)*C_E, where Lambda(W) is the model Lipschitz constant, C_E is the maximum embedding diameter, and epsilon_fit is the expert training error -- all checkable at deployment time without ground truth. We prove that LAWS generalizes both Mixture-of-Experts and KV prefix caching as special cases and is strictly more expressive than any fixed-K MoE or finite cache. Further results include a monotone hit rate theorem (any-match routing ensures coverage only increases), an expert library growth rate of O(2^H log N) where H is workload entropy, a fleet learning convergence theorem with Omega(K) speedup for K-unit fleets, and an over-the-air update bandwidth bound. We conjecture that LAWS is acquisition-optimal among stationary online caching algorithms and that the effective Lipschitz constant on the training distribution grows polynomially rather than exponentially in depth. Applications are developed for LLM inference, robotic control, and multi-agent edge deployment. --- ### Designing a double deep reinforcement learning selection tool for resilient demand prediction Authors: Bilel Abderrahmane Benziane, Benoit Lardeux, Ayoub Mcharek, Maher Jridi Published: 2026-04-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.04068v1 The use of artificial intelligence in supply chain forecasting has attracted many scientific studies for several decades. However, the process of selecting an appropriate forecasting solution becomes a daunting task. This complexity arises due to the distinct features inherent to each dataset. Research to tackle this issue has been performed since the eighties but recent development of demand forecasting has opened new perspectives. This research aims to enhance automatic forecasting model selection by proposing a novel architecture that acts as a double deep reinforcement learning agent, selecting automatically a forecasting model from the forecasting committee at the time of prediction. Moreover, a novel early-stopping approach based on average reward convergence has been introduced to expedite training time. To evaluate the model's performance, an empirical study was conducted utilizing grocery sales datasets and snack demands datasets. The experimental results demonstrate the robustness of the proposed approach when compared to state-of-the-art methods. --- ### TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution Authors: Yang Yang, Zining Zhong, Jindong Li, Jiemin Wu, Kaishen Yuan, Wenshuo Chen, Menglin Yang, Yutao Yue Published: 2026-04-12 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2604.18607v1 LLM-driven program evolution can discover high-quality programs, but its cost and run-to-run variance hinder reliable progress. We propose TurboEvolve, a multi-island evolutionary framework that improves sample efficiency and robustness under fixed evaluation budgets. Inspired by the multiple-offspring strategy in evolutionary algorithms, TurboEvolve introduces verbalized Sampling, prompting the LLM to emit K diverse candidates with explicit self-assigned sampling weights, and an online scheduler that adapts K to expand exploration under stagnation and reduce overhead during steady progress. To exploit existing solution pools, we further propose "seed-pool injection," which clusters seeds and assigns them across islands with controlled perturbations and elitist preservation to balance diversity and refinement. Across multiple program-optimization benchmarks, TurboEvolve consistently achieves stronger performance at lower budgets and improves best-known solutions on several tasks. --- ### Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models Authors: Hoigi Seo, Byung Hyun Lee, Jaehyun Cho, Sungjin Lim, Se Young Chun Published: 2026-04-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16481v1 Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable content, such as copyrighted ones. Concept erasure has emerged as a mitigation strategy, yet existing approaches struggle to balance scalability, precision, and robustness, which restricts their applicability to erasing only a few hundred concepts. To address these limitations, we present Erasing Thousands of Concepts (ETC), a scalable framework capable of erasing thousands of concepts while preserving generation quality. Our method first models low-rank concept distributions via a Student's t-distribution Mixture Model (tMM). It enables pin-point erasure of target concepts via affine optimal transport while preserving others by anchoring the boundaries of target concept distributions without pre-defined anchor concepts. We then train a Mixture-of-Experts (MoE)-based module, termed MoEraser, which removes target embeddings while preserving the anchor embeddings. By injecting noise into the text embedding projector and fine-tuning MoEraser for recovery, our framework achieves robustness to white-box attack such as module removal. Extensive experiments on over 2,000 concepts across heterogeneous domains and diffusion models demerate state-of-the-art scalability and precision in large-scale concept erasure. --- ### Positioning radiata pine branches requiring pruning by drone stereo vision Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green Published: 2026-04-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16480v1 This paper presents a stereo-vision-based system mounted on a drone for detecting and localising radiata pine branches to support autonomous pruning. The proposed pipeline comprises two stages: branch segmentation and depth estimation. For segmentation, YOLOv8, YOLOv9, and Mask R-CNN variants are compared on a custom dataset of 71 stereo image pairs captured with a ZED Mini camera. For depth estimation, both a traditional method (SGBM with WLS filtering) and deep-learning-based methods (PSMNet, ACVNet, GWCNet, MobileStereoNet, RAFT-Stereo, and NeRF-Supervised Deep Stereo) are evaluated. A centroid-based triangulation algorithm with MAD outlier rejection is proposed to compute branch distance from the segmentation mask and disparity map. Qualitative evaluation at distances of 1-2 m indicates that the deep learning-based disparity maps produce more coherent depth estimates than SGBM, demonstrating the feasibility of low-cost stereo vision for automated branch positioning in forestry. --- ### Latent-Compressed Variational Autoencoder for Video Diffusion Models Authors: Jiarui Guan, Wenshuai Zhao, Zhengtao Zou, Juho Kannala, Arno Solin Published: 2026-04-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16479v1 Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction. However, recent studies have revealed that an excessive number of latent channels can impede the convergence of latent diffusion models and deteriorate their generative performance, even when reconstruction quality remains high. We propose a latent compression method that removes high-frequency components in video latent representations rather than directly reducing the number of channels, which often compromises reconstruction fidelity. Experimental results demonstrate that the proposed method achieves superior video reconstruction quality compared to strong baselines while maintaining the same overall compression ratio. --- ### Mapping High-Performance Regions in Battery Scheduling across Data Uncertainty, Battery Design, and Planning Horizons Authors: Jaime de Miguel Rodriguez, Artjom Vargunin, Brigitta Robin Raudne, David Solis Martin, Yaroslava Mykhailenko, Kaarel Oja Published: 2026-04-12 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2604.15360v2 This study presents a controlled parametric framework for analyzing energy storage planning under uncertainty in a multi-stage model predictive control setting. The framework enables a broad and systematic exploration through parametrized generation of synthetic datasets in the context of energy price arbitrage. It facilitates the study of the joint effects of battery characteristics, signal structure, forecast uncertainty, and planning horizon on revenue performance in energy storage optimization, which are rarely considered together. The analysis is driven by two objectives. First, it characterizes how these interacting factors influence operational revenue and its sensitivity to planning horizon selection, including economic losses caused by deviations from optimal horizons. This provides guidance on expected horizon ranges and their impact on revenue and computational cost. Second, it enables a compact parametrization of the relationships between battery properties, data characteristics, forecast uncertainty, and horizon-dependent performance, providing a basis for future modelling of optimal planning horizon length. Results show that the framework captures consistent structural dependencies across configurations and provides meaningful guidance for horizon selection under uncertainty. In particular, increasing forecast uncertainty systematically reduces the optimal planning horizon across battery types, reflecting the diminishing value of long-term information under increasingly unreliable forecasts. Comparison with real market data shows that the parametrization reproduces the main qualitative trends of optimal horizon behavior, suggesting its potential as a lightweight surrogate for more complex simulation-based analysis. --- ### AutoFlows++: Hierarchical Message Flow Mining for System on Chip Designs Authors: Bardia Nadimi, Hao Zheng Published: 2026-04-12 Categories: cs.AR, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2604.15359v1 Understanding communication behavior in modern system-on-chip (SoC) designs is critical for functional verification, performance analysis, and post-silicon debugging. Communication traces capture message exchanges among system components and provide valuable insights into system behavior. However, deriving concise communication specifications from such traces remains challenging due to interleaved instances of communication flows, and ambiguous causal relationships among messages. Existing mining approaches often struggle with scalability and ambiguity when traces contain complex interleaving of message patterns across multiple components. These conditions often lead to an explosion in the number of candidate flows and inaccurate extraction of communication behaviors. This paper presents AutoFlows++, a design-architecture-guided hierarchical framework for mining message flows from communication traces of complex SoC designs. AutoFlows++ operates in two stages: local mining followed by global mining. In the local mining stage, simple communication patterns are extracted from traces observed at individual communication interfaces between components. In the global mining stage, these local patterns are composed to identify higher-level message flows that characterize communication behavior across multiple components. Experimental results on both synthetic traces and traces generated from SoC models in GEM5 demonstrate that AutoFlows++ significantly improves flow extraction accuracy compared with prior approaches, highlighting its effectiveness for practical SoC validation tasks. --- ### The Code Whisperer: LLM and Graph-Based AI for Smell and Vulnerability Resolution Authors: Mohammad Baqar, Raji Rustamov, Alexander Hughes Published: 2026-04-12 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.13114v1 Code smells and software vulnerabilities both increase maintenance cost, yet they are often handled by separate tools that miss structural context and produce noisy warnings. This paper presents The Code Whisperer, a hybrid framework that combines graph-based program analysis with large language models to detect, explain, and repair maintainability and security issues within a unified workflow. The method aligns Abstract Syntax Trees (ASTs), Control Flow Graphs (CFGs), Program Dependency Graphs (PDGs), and token-level code embeddings so that structural and semantic signals can be learned jointly. We evaluate the framework on multi-language datasets and compare it with rule-based analyzers and single-model baselines. The results indicate that the hybrid design improves detection performance and produces more useful repair suggestions than either graph-only or language-model-only approaches. We also examine explainability and CI/CD integration as practical requirements for adopting AI-assisted code review in everyday software engineering workflows. --- ### A Lightweight Global-Target Framework for Multi-Domain No-Reference Image Quality Assessment in UAV Imagery Authors: Koffi Titus Sergio Aglin, Anthony K. Muchiri, Celestin Nkundineza Published: 2026-04-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.13112v4 Reliable image quality assessment is essential in applications where large volumes of images are acquired automatically and must be filtered before further analysis. In many practical scenarios, a pristine reference image is unavailable, making no reference image quality assessment (NR-IQA) particularly important. This paper introduces Multi-Metric Image Quality Assessment (MM-IQA), a lightweight multi-metric framework for NR-IQA. It combines interpretable cues related to blur, edge structure, low resolution artifacts, exposure imbalance, noise, haze, and frequency content to produce a single quality score in the range (0,100).MM-IQA was evaluated on five benchmark datasets (KonIQ-10k, LIVE Challenge, KADID-10k, TID2013, and BIQ2021) and achieved SRCC values ranging from 0.647 to 0.830. Additional experiments on a synthetic agricultural dataset showed consistent behavior of the designed cues. The Python/OpenCV implementation required about 1.97 s per image. This method also has modest memory requirements because it stores only a limited number of intermediate grayscale, filtered, and frequency-domain representations, resulting in memory usage that scales linearly with image size. The results show that MM-IQA can be used for fast image quality screening with explicit distortion aware cues and modest computational cost. --- ### A Lightweight Multi-Metric No-Reference Image Quality Assessment Framework for UAV Imaging Authors: Koffi Titus Sergio Aglin, Anthony K. Muchiri, Celestin Nkundineza Published: 2026-04-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.13112v1 Reliable image quality assessment is essential in applications where large volumes of images are acquired automatically and must be filtered before further analysis. In many practical scenarios, a pristine reference image is unavailable, making no reference image quality assessment (NR-IQA) particularly important. This paper introduces Multi-Metric Image Quality Assessment (MM-IQA), a lightweight multi-metric framework for NR-IQA. It combines interpretable cues related to blur, edge structure, low resolution artifacts, exposure imbalance, noise, haze, and frequency content to produce a single quality score in the range (0,100).MM-IQA was evaluated on five benchmark datasets (KonIQ-10k, LIVE Challenge, KADID-10k, TID2013, and BIQ2021) and achieved SRCC values ranging from 0.647 to 0.830. Additional experiments on a synthetic agricultural dataset showed consistent behavior of the designed cues. The Python/OpenCV implementation required about 1.97 s per image. This method also has modest memory requirements because it stores only a limited number of intermediate grayscale, filtered, and frequency-domain representations, resulting in memory usage that scales linearly with image size. The results show that MM-IQA can be used for fast image quality screening with explicit distortion aware cues and modest computational cost. --- ### UniMark: Unified Adaptive Multi-bit Watermarking for Autoregressive Image Generators Authors: Yigit Yilmaz, Elena Petrova, Mehmet Kaya, Lucia Rossi, Amir Rahman Published: 2026-04-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11843v1 Invisible watermarking for autoregressive (AR) image generation has recently gained attention as a means of protecting image ownership and tracing AI-generated content. However, existing approaches suffer from three key limitations: (1) they embed only zero-bit watermarks for binary verification, lacking the ability to convey multi-bit messages; (2) they rely on static codebook partitioning strategies that are vulnerable to security attacks once the partition is exposed; and (3) they are designed for specific AR architectures, failing to generalize across diverse AR paradigms. We propose \method{}, a training-free, unified watermarking framework for autoregressive image generators that addresses all three limitations. \method{} introduces three core components: \textbf{Adaptive Semantic Grouping (ASG)}, which dynamically partitions codebook entries based on semantic similarity and a secret key, ensuring both image quality preservation and security; \textbf{Block-wise Multi-bit Encoding (BME)}, which divides the token sequence into blocks and encodes different bits across blocks with error-correcting codes for reliable message transmission; and \textbf{a Unified Token-Replacement Interface (UTRI)} that abstracts the watermark embedding process to support both next-token prediction (e.g., LlamaGen) and next-scale prediction (e.g., VAR) paradigms. We provide theoretical analysis on detection error rates and embedding capacity. Extensive experiments on three AR models demonstrate that \method{} achieves state-of-the-art performance in image quality (FID), watermark detection accuracy, and multi-bit message extraction, while maintaining robustness against cropping, JPEG compression, Gaussian noise, blur, color jitter, and random erasing attacks. ---