# Research Papers — 2026-08 · bundle page 80 of 240 > Full-text markdown of papers #3951–4000 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/80 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/79.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/81.md) ### SENTRY: Deterministic, Intelligent Risk Assessment for IT Change Management Authors: Daniel Arulpragasam, Christer Henrysson, Ella Ly, Deepika Anbalagan, Leo Feng Published: 2026-08-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.21203v1 Technology change management in large financial institutions depends on risk assessments that are accurate, consistent, and auditable. In practice, many institutions still rely on self-reported questionnaires. Those questionnaires are subjective, easy to game, and poor at separating routine changes from the ones that later trigger major incidents. This paper presents SENTRY, a risk assessment platform that replaces questionnaire-based scoring with a deterministic machine learning pipeline built from gradient-boosted decision trees (XGBoost) and hybrid retrieval-augmented generation (RAG). The system combines structured operational metadata, application dependency graphs, and historical incident records with a hybrid semantic and lexical search over historical change requests. The retrieval step captures the risk signal in unstructured change request text, then compresses that signal into a single scalar feature before model inference. That design keeps the model deterministic and preserves per-prediction explainability via SHAP values. Evaluated on enterprise-scale change data, SENTRY achieves a ROC AUC of 0.87 and 85% overall accuracy, and it detects high-risk changes at roughly 3.25 times the rate of the existing process. We close by examining the architectural trade-offs behind this design and what they imply for the use of machine learning in regulated change management. --- ### Tydra: An Efficient Hybrid Model for Tabular Data Authors: Mieszko Komisarczyk, Saurabh Mathur, Maurice Kraus, Sriraam Natarajan, Kristian Kersting Published: 2026-08-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.21199v1 Transformer-based tabular foundation models such as TabPFN achieve strong predictive performance but incur quadratic computational cost with context length. On the other hand, subquadratic SSM-based alternatives such as Hydra trade away accuracy for efficiency. To balance both, we introduce Tydra, a hybrid Transformer-State Space Model (SSM) architecture for tabular in-context learning that interleaves attention and SSM layers. Across 30 OpenML datasets, Tydra reduces inference time by 30% relative to TabPFN while retaining much of its predictive performance. Tydra also outperforms an approximately ten-times-larger Hydra model while providing faster inference. The results indicate that hybrid architectures are a promising direction for tabular foundation models. --- ### ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation Authors: Can Jin, Ying Li, Jingchen Sun, Hongwu Peng, Jiahui Zhao, Yang Zhou, Lei Li, Dimitris N. Metaxas Published: 2026-08-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.21194v1 Visual prompting (VP) has emerged as a parameter-efficient method for adapting pre-trained models to downstream tasks. However, existing approaches encounter a trade-off between flexibility and efficiency. Some methods apply a fixed prompt to all images, ignoring individual image characteristics, while others introduce auxiliary networks to generate diverse prompts. Although the latter can improve performance, it also significantly increases parameter usage and the potential for overfitting to specific datasets. Furthermore, the auxiliary networks, combined with inherent biases in pre-trained models, limit scalability and generalization. In this paper, we propose Energy-Shaped Visual Prompting (ES-VP), a novel approach that generates image-specific prompts using low-rank initialization and energy-guided dynamic adaptation, achieving superior performance with fewer parameters compared to single-prompt methods. ES-VP directly utilizes the pre-trained model for adaptive prompt generation, ensuring both parameter efficiency and improved generalization. Extensive experiments conducted on five architectures across fifteen datasets demonstrate that ES-VP consistently outperforms current state-of-the-art (SOTA) single and diverse VP methods. For instance, using the CLIP architecture across four datasets, ES-VP outperforms the SOTA method DAM-VP by an average of 2.6\% in accuracy while utilizing 590$\times$ fewer VP parameters, thereby establishing a new benchmark for efficient and generalizable model adaptation. --- ### Towards Investigating Residual Hearing Loss: Quantification of Fibrosis in a Novel Cochlear OCT Dataset Authors: Julia Dietlmeier, Benjamin Greenberg, Wenxuan He, Teresa Wilson, Rubing Xing, Jordan Hill, Adrienne Fettig, Madeline Otto, Teyhana Rounsavill, Lina A. J. Reiss, Jingang Yi, Noel E. O'Connor et al. Published: 2026-08-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.21189v1 Objective: Cochlear implants (CIs) are bionic prostheses that restores hearing via electrical stimulation of the auditory nerve. Hybrid CIs, which use electroacoustic stimulation (EAS), combine residual low-frequency acoustic hearing with CI electrical stimulation. Intracochlear fibrosis, which forms in response to the presence of the implant, may impede residual hearing function and gradually reduce the efficacy of EAS. It is therefore a translational objective to study the formation of cochlear fibrosis in rodents, with the goal of reducing fibrotic burden and improving outcomes for CI patients. Methods: We generate and annotate a novel dataset of optical coherence tomography (OCT) images from chronically implanted guinea pigs as part of an ongoing study focused on implant induced fibrosis. Objectively assessing fibrotic burden in this model, with high resolution and repeatability, presents an obvious use case for computer vision methods. Results: We present the results of several state-of-the-art semantic segmentation models and compare their efficacy for identifying cochlear fibrosis and other relevant annotations, using a new library of manually segmented OCT images. Conclusions: We find that the best performance is achieved by using a modified version of the well-known UNET architecture (which we term 2D-OCT-UNET) that operates on the upscaled OCT input resolution. Significance: For the first time, we have successfully applied computer vision techniques to an OCT dataset of implanted cochleae with fibrosis. Using this deep learning model, the cochlear fibrotic burden calculation can be reliably carried out as we verify in our experimental section. The dataset and the project code are available at: https://github.com/juliadietlmeier/CF-OCT-segmentation --- ### Anchored Regularized Direct Least Squares (ARDLS): Integrating Established Prioritization Operators for Priority Elicitation in the Analytic Hierarchy Process Authors: Kevin Kam Fung Yuen Published: 2026-08-21 Categories: math.OC, cs.AI, math.NA arXiv: https://arxiv.org/abs/2608.21187v2 Pairwise reciprocal matrices are fundamental to the Analytic Hierarchy Process (AHP),a decision-making model. While the Direct Least Squares (DLS) method provides an intuitive mechanism for deriving priority vectors without complex transformations, it is susceptible to solution non-uniqueness. Under high levels of inconsistency, such as severe cyclic contradictions, the DLS optimization landscape becomes non-convex, yielding multiple distinct global minima. Consequently, priority rankings become unstable and critically dependent on initial algorithmic guesses. Furthermore, established prioritization operators (POs), including normalization techniques, the Eigenvector method, Singular Value Decomposition, Cosine Maximization, and the Pseudo-Inverse Gram Matrix (the closed-form solution of Weighted Least Squares), frequently generate disparate outcomes. To overcome these structural deficiencies, this paper introduces the Anchored Regularized Direct Least Squares (ARDLS) optimization model as a harmonizing framework. ARDLS integrates uniquely determined established POs as theoretical anchors within a regularization penalty. This integration systematically breaks mathematical symmetries and tilts the optimization landscape to guarantee convergence upon a single, unique global minimum. By minimizing the root mean square variance (RMSV) of the initial baseline vectors, ARDLS effectively unifies these divergent solutions. Comprehensive numerical experiments validate that the framework successfully fine-tune the solution of established POs by reducing RMSV while ensuring strict mathematical uniqueness. The practical utility of the method is further demonstrated through a numerical case study resolving an innovation fund dilemma in FinTech project selection. The proposed ARDLS approach offers a robust alternative to classical AHP across a wide range of decision-making domains. --- ### Anchored Regularized Direct Least Squares (ARDLS): Integrating Established Prioritization Operators for Priority Elicitation in the Analytic Hierarchy Process Authors: Kevin Kam Fung Yuen Published: 2026-08-21 Categories: math.OC, cs.AI, math.NA arXiv: https://arxiv.org/abs/2608.21187v1 Pairwise reciprocal matrices are fundamental to the Analytic Hierarchy Process (AHP), a decision-making model. While the Direct Least Squares (DLS) method provides an intuitive mechanism for deriving priority vectors without complex transformations, the DLS provides multiple solutions. Under high levels of inconsistency, such as cyclic contradictions, this non-convexity yields multiple distinct global minima, resulting in unstable priority rankings that critically depend on initial algorithmic guesses. To overcome this structural deficiency, this paper introduces the Anchored Regularized Direct Least Squares (ARDLS) optimization model. ARDLS integrates uniquely determined established prioritization operators, such as normalization techniques, the Eigenvector method, Singular Value Decomposition, Cosine Maximization, and the Pseudo-Inverse Gram Matrix (the closed-form solution of Weighted Least Squares), as theoretical anchors within a regularization penalty. This integration systematically breaks mathematical symmetries, tilting the optimization landscape to guarantee convergence upon a single, unique global minimum. Comprehensive numerical experiments and simulations validate that the ARDLS framework successfully reduces root mean square error among established priority operators, while guaranteeing strict mathematical uniqueness. The proposed ARDLS may be the ideal alternative for the AHP applied to many application domains. --- ### A Neurosymbolic Approach for Constructing Planning Domain Models from Clinical Narratives Authors: Ranveer Singh, Saurabh Mathur, Michael Skinner, Prasad Tadepalli, Kristian Kersting, Sriraam Natarajan Published: 2026-08-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.21186v1 Surgical procedures such as laparoscopic appendectomy are complex, high-stakes processes, yet formalizing their workflows for decision support remains a significant challenge. Inducing probabilistic planning domain models in this setting is particularly difficult due to the lack of structured event data and the prevalence of implicit actions in clinical narratives, which neither empirical symbolic methods nor Large Language Models (LLMs) can adequately address on their own. We introduce NSPIN, a neurosymbolic framework for inducing probabilistic planning domain models from unstructured clinical narratives. Our method extracts and imputes structured event sequences from raw text using a pretrained LLM, then induces a PPDDL model and refines its preconditions with LLM-proposed revisions, guided by empirical validation. We evaluate the approach on 2,660 laparoscopic appendectomy notes written by 9 surgeons. NSPIN yields models that generalize to unseen notes, and expert clinical review indicates its induced knowledge is largely consistent with surgical practice. --- ### Toward Vision Language Model-based Assessment of Clinical Quality and Usability of LGE-MR Images for Cardiac Ablation Planning Authors: Bipasha Kundu, Abhishek Chaturvedi, Axel W. E. Wismueller, Richard Simon, Cristian A. Linte Published: 2026-08-21 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.21180v1 LGE cardiac MRI is widely used for left atrial fibrosis assessment and ablation planning in atrial fibrillation patients as knowledge of fibrotic tissue regions identified from LGE-MRI is critical for catheter ablation. Often, poor quality images used during ablation planning can cause mis-localization of ablation targets, directly impacting procedure safety and outcome. The decision of whether a scan meets the minimum quality threshold for ablation planning is currently made informally by the reviewing radiologist and is not captured by any automated system, yet it is arguably the most safety-critical output of the image quality assessment (IQA) process. However, variations in image quality caused by noise, motion artifacts, and poor boundary definition significantly compromise the reliability of downstream segmentation and clinical decision-making tasks. Manual quality assessment by expert radiologists is subjective and difficult to scale, while existing automated methods produce scalar scores without interpretable clinical reasoning. In this work, we propose a two-stage vision language model (VLM) framework for clinically grounded image quality assessment of left atrial LGE-MRI. In the first stage, a fine-tuned VLM generates structured radiology-style quality reports predicting five radiologist-defined criteria: Noise, Motion Artifact, LA Boundary Accuracy, PV Region Accuracy, and Under-segmentation Severity. In the second stage, a GPT-based reasoning module maps the predicted quality and reports to a structured quality scores and binary clinical usability decision for ablation planning. We curate a dataset of 60 annotated image slice-text pairs from 20 patients and benchmark four state-of-the-art VLM architectures. InternVL2 achieves the highest criterion-level accuracy (Avg ACC=0.65, PLCC=0.79), while DeepSeek achieves perfect clinical usability agreement (Acc=1.00, kappa=1.00). --- ### DAMOS: Learning Distortion-Aware Speech Quality Assessment through Explicit Distortion Localization Authors: Naiyuan Li, Li Dong, Diqun Yan Published: 2026-08-21 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2608.21176v1 Automatic speech quality assessment aims to predict Mean Opinion Scores (MOS) consistent with human subjective perception and is essential for evaluating speech generation, enhancement, and communication systems. For speech signals, especially synthetic speech, distortions often occur locally, and overall perceptual quality is usually dominated by a small number of perceptually salient distortion regions. However, most existing methods are primarily optimized with utterance-level MOS, which provides only coarse-grained supervision and offer no explicit indication of where perceptually important distortions occur. To address this limitation, we introduce explicit distortion localization as auxiliary knowledge for speech quality assessment. We construct the first partially distorted speech dataset with frame-level distortion annotations and train a localization model to generate distortion cues. Building on these cues, we propose DAMOS, a distortion-aware speech quality assessment framework that integrates localization information into the MOS prediction pipeline. Experiments on multiple public benchmarks demonstrate that DAMOS consistently outperforms existing methods and exhibits strong cross-dataset generalization, validating the effectiveness of explicit distortion localization for speech quality assessment. --- ### SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control Authors: Ruihua Han, Rui Gao, Zhe Liu, Xinyi Wang, Chang Chen, Shuai Wang, Qi Hao, Jia Pan, Hengshuang Zhao Published: 2026-08-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.21175v1 Safe and efficient shape-aware navigation in heterogeneous crowds and robot fleets remains challenging. Traditional approaches often assume homogeneous robots, sparse workspaces, simplified geometry, offline computation, or handcrafted parameters to make the problem tractable, which limits their deployment in dense crowd scenarios. Toward this end, we propose Shape-Aware Reinforcement Learned Model Predictive Control (SRL-MPC), a method for safe, efficient, and adaptive navigation in crowds with heterogeneous shapes without geometry simplification. To encode shape-aware safety, we formulate high-order control barrier function (HOCBF) constraints from geometric separation features (GSFs) based on support function transformation. A reinforcement learning (RL) framework then learns a neural policy that reads GSFs and outputs real-time MPC parameter updates, enabling the MPC solver to adapt to neighboring crowd geometries. The key advantage of SRL-MPC is that it preserves the safety structure and generalizability of MPC while integrating the adaptability and intelligence of RL. Experiments in randomized crowd scenarios with arbitrary shaped robot fleets demonstrate the effectiveness, scalability, and robustness of SRL-MPC. The results show that SRL-MPC substantially outperforms representative baselines in safety and adaptability. Project website: https://hanruihua.github.io/srl_mpc_project/ --- ### From Attention Masks to Inert Zero-Vector Tokens: OAttention and O-Closure for Token Dynamics Authors: Heyang Gong Published: 2026-08-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.21174v1 Attention masks are relation-level controls: they specify which query--source pairs may interact. They do not provide a representation-carried token state that is non-participating at the attention boundary. We assign each token hidden carrier \(h_i\) an active-presence coefficient \(p_i=\lVert h_i\rVert^2/(τ+\lVert h_i\rVert^2)\). The same coefficient has two roles: it gates information emitted by token \(i\), and it determines the mass with which token \(i\) enters computations shared with other tokens. OAttention is the support-coupled attention realization of this rule. It gates the receiver output by \(p_i\) and weights source \(j\) by \(p_j\) in both the attention numerator and partition, while retaining the standard score, visibility relation, exponential competition, and value aggregation. This makes the zero-vector token a zero element and yields exact null-receiver, null-source insertion, self-attention insertion, and empty-support properties. The same token-level presence gives local O-components (OFFN, ONorm, and OInject), presence-weighted OStandardize, the O-Closure law \(M(H\oplus0)=M(H)\oplus0\), and an OTransformer by residual and compositional closure. The canonical operator is checked by contract tests and a GPU evaluation. In a zero-fine-tuning retrofit of a cloned pretrained TabPFN v3 regressor, calibrated hidden-carrier OAttention and Full-O variants change mean RMSE by $+0.088\%$ and $+0.177\%$, respectively, over 18 matched dataset--seed cases. A two-block ablation shows that OAttention alone does not preserve a NULL state through ordinary host components, whereas the OTransformer path does. These are scoped tests of exactness, active-path compatibility, and compositional necessity; they do not establish universal no-loss, arbitrary-host closure, learned attraction to the origin, or a general semantics for missing values. --- ### Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AI Authors: Shiva Shrestha, Kazi Shaharair Sharif, Zongxing Xie, Jiajing Huang, Anhao Xiang, Honghui Xu Published: 2026-08-21 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2608.21172v1 Federated fine-tuning enables large language models to adapt on edge devices without centralizing private data, but practical deployments must address hardware instability and adversarial update corruption together. Thermally constrained clients may throttle, slow local training, or delay synchronous aggregation, while Byzantine clients and communication-layer adversaries can corrupt the updates used to form the global model. To address these challenges, we present Thermo-FL, a thermal-aware federated LoRA fine-tuning framework that uses device temperature as an active control signal for local adapter training and sparse update transmission. On the client side, Thermo-FL adjusts the active LoRA-layer fraction and transmitted update density as devices heat or cool, reducing workload under thermal stress. On the server side, Thermo-FL introduces TERRA, a robust aggregation pipeline for dynamically sparse LoRA updates that combines norm filtering, mask-aware directional validation, adaptive active-coordinate clipping, and mask-aware aggregation. We evaluate Thermo-FL using both a large-scale emulator and a Jetson-based physical testbed. In the emulator, Thermo-FL improves robustness under adversarial sparse aggregation and achieves the strongest BoolQ accuracy across clean and attack settings while remaining competitive on GSM8K. In the physical prototype, Thermo-FL stabilizes device temperature, reduces compressed upload size through bitmap sparse encoding, and preserves GSM8K utility under sign-flip/scale and MITM perturbations. These results show that secure edge LLM adaptation should jointly consider hardware behavior, workload regulation, sparse communication, and aggregation robustness. --- ### Is Visual Prompting All You Need? Studying VLM Spatial Reasoning under Progressive Visual Scaffolds Authors: Lars Benedikt Kaesberg, Tianyu Yang, Florian Valentin Wunderlich, Terry Ruas, Daniel Kurzawe, Jan Philip Wahle, Bela Gipp Published: 2026-08-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.21170v2 Vision-language models (VLMs) have advanced rapidly in multimodal reasoning, yet recent work shows that their failures often reflect an interaction between visual grounding and downstream reasoning. What remains less clear is how the visual presentation of a task shapes model performance and failure modes when the underlying reasoning problem is unchanged. We study this question in SPaRC, a benchmark for grid-based visual spatial planning, by introducing lightweight input-side scaffolds that preserve the visual modality while making spatial structure more accessible. Across multiple VLMs, these scaffolds improve task accuracy over the original visual setting by up to 34.0 percentage points and further complement GRPO-based training, yielding up to 4.6 additional accuracy points compared with near-zero gains on the original visual input. Analyses on both end-to-end task solving and object detection show that these gains are closely tied to reductions in grounding-related errors, while rule reasoning remains comparatively challenging. We find that visual presentation is a central factor that determines whether VLM benchmarks measure grounded perception, downstream reasoning, or a mixture of both. --- ### Is Visual Prompting All You Need? Studying VLM Spatial Reasoning under Progressive Visual Scaffolds Authors: Lars Benedikt Kaesberg, Tianyu Yang, Florian Valentin Wunderlich, Terry Ruas, Jan Philip Wahle, Daniel Kurzawe, Bela Gipp Published: 2026-08-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.21170v1 Vision-language models (VLMs) have advanced rapidly in multimodal reasoning, yet recent work shows that their failures often reflect an interaction between visual grounding and downstream reasoning. What remains less clear is how the visual presentation of a task shapes model performance and failure modes when the underlying reasoning problem is unchanged. We study this question in SPaRC, a benchmark for grid-based visual spatial planning, by introducing lightweight input-side scaffolds that preserve the visual modality while making spatial structure more accessible. Across multiple VLMs, these scaffolds improve task accuracy over the original visual setting by up to 34.0 percentage points and further complement GRPO-based training, yielding up to 4.6 additional accuracy points compared with near-zero gains on the original visual input. Analyses on both end-to-end task solving and object detection show that these gains are closely tied to reductions in grounding-related errors, while rule reasoning remains comparatively challenging. We find that visual presentation is a central factor that determines whether VLM benchmarks measure grounded perception, downstream reasoning, or a mixture of both. --- ### Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates Authors: Hui Wei, Licai Sun, Guoying Zhao Published: 2026-08-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.21160v1 Machines that understand humans should perceive the present and anticipate the future. Existing human-centric vision model are pretrained on human images, set the state of the art in static dense perception, so motion and anticipation are out of reach. Here we present Human-JEPA, a human-centric vision model trained on video by anchored forecasting: dense targets are pinned to a frozen copy of the initialization, preventing a silent collapse of dense perception, and block masks are replaced by a pure past-to-future split, avoiding a five-point action tax and a seventeen-point re-identification collapse. Under frozen probes, Human-JEPA leads the pixel-anchored specialists on pose and person re-identification at 2.7 times fewer parameters, conceding high-resolution dense parsing, and its released predictor head is the first that does not degrade anticipation. A single safely adapted model thus serves both halves of understanding humans. --- ### AID-Guard: Stateful Authorization for Delegated Agent Effects Authors: Yingzhe Tong, Leyu Dai, Songhui Guo Published: 2026-08-21 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.21159v1 Tool-using AI agents turn delegated tasks into provider effects, yet authorization often ends at admission while provider state, delivery, retry, and recovery evolve. A request may change before commit, or response loss may cause a replacement to create a second effect from one approval. We present AID-Guard, a stateful authorization-to-effect closure protocol. It revalidates the approved request and provider state at commit, retains one reservation under ambiguity, and permits release or one successor only after a terminal result or certified no effect with a delivery fence. For supported provider contracts, one reservation yields at most one effect across retry and recovery. To our knowledge, it is the first evaluated agent-authorization protocol to unify these controls in one lifecycle. We implement a Python/SQLite prototype. In a declared loopback MCP domain, 13 live mutations caused no unauthorized provider effects, three concurrent histories were linearizable, and evidence bundles supported public verification and replay. All 210 Stripe provider-contract trials matched predeclared outcomes. Across Stripe and Resend, 40 terminalize-successor schedules, 30 overlapping races, and 10 crash-recovery schedules completed without duplicate effects. Under complete proposer compromise, AID-Guard blocked 44/44 attacks and admitted 44/44 matched legitimate proposals. Its strict exact-manifest profile reduced benign utility by 35.4 to 43.8 percentage points; a typed frontier recovered 9-10 completions without observed unsafe effects. A composition study blocked 20/20 post-admission lifecycle attacks and preserved 8/8 valid or exact-retry executions. The results support authorization-to-effect binding under the evaluated effect-path inventory, provider contracts, and failure schedules. --- ### HIERA: Workload-Aware Planning Across Implementation Spaces for GPU Kernel Optimization Authors: Jinghao Wang, Qiqi Gu, Chenpeng Wu, Jianguo Yao, Haibing Guan, Xijun Li Published: 2026-08-21 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2608.21157v1 High-performance GPU kernels underpin modern deep learning and scientific computing. As workloads become increasingly diverse and GPU hardware evolves rapidly, developing efficient methods for automated GPU kernel generation and optimization has become increasingly important. Existing LLM-based methods typically optimize within a fixed implementation space, limiting either optimization flexibility or search efficiency. We propose \textsc{HIERA}, a hierarchical search-space planning framework for GPU kernel optimization. \textsc{HIERA} constructs contract-augmented task specifications, selects an appropriate implementation space across PyTorch operators, CUDA libraries, and custom CUDA kernels, and uses profiling feedback and expert knowledge to guide structured iterative refinement. Experiments on KernelBench across multiple various workload levels and base LLMs show that \textsc{HIERA} delivers stronger overall implementation validity, sample efficiency, and optimization performance than existing training-free methods, while remaining competitive with the training-based CUDA-L1 without additional model training. A case study on a specialized stencil operator from scientific computing further achieves a \(1.53\times\) speedup over cuDNN, demonstrating the potentiality of the general framework beyond standard machine-learning workloads. --- ### Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence Authors: Yuyuan Feng, Zhishang Xiang, Chaobin Yang, Qichao Ma, Zerui Chen, Yujing Zhang, Ke Huang, Chuanjie Wu, Zhaoxu Liu, Yili Wang, Xin He, Jiapu Wang et al. Published: 2026-08-21 Categories: cs.IR, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2608.21156v2 LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks. This evolution has produced paradigms including Prompt Engineering to elicit model capabilities, Context Engineering to manage information access, Harness Engineering to organize external tools and resources, and Loop Engineering to support continual reflection and self-improvement. Yet as tasks grow more complex, individual intelligence faces a fundamental limit: many tasks require heterogeneous expertise, interdependent subtasks, parallel execution, independent verification, and persistent state, exceeding any single agent's organizational capacity. Augmenting one agent's capabilities or context cannot resolve this architectural mismatch; intelligence must instead be distributed across specialized agents and organized at the system level. We call this System Intelligence: an agent system's ability to organize and coordinate multiple intelligent components into a coherent, adaptive whole pursuing a shared objective. Achieving it requires more than adding agents; it demands explicit structures to organize work, coordinate heterogeneous agents, and maintain evolving execution states. We introduce Graph Engineering, an emerging paradigm for next-generation agent systems. Unlike prior paradigms that mainly optimize individual interactions or agent-level behavior, Graph Engineering constructs explicit, dynamic, evolving graph structures representing tasks, agents, and system states. These abstractions provide a unified foundation for organizing complex objectives, orchestrating heterogeneous agents, modeling system dynamics, and enabling scalable agent evolution. We systematically review the principles, methodologies, and applications of Graph Engineering for LLM agents. Related papers, open-source data, and projects are collected at https://github.com/DEEP-JLU/Awesome-Graph-Engineering. --- ### Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence Authors: Yuyuan Feng, Zhishang Xiang, Chaobin Yang, Qichao Ma, Zerui Chen, Yujing Zhang, Ke Huang, Chuanjie Wu, Zhaoxu Liu, Yili Wang, Xin He, Jiapu Wang et al. Published: 2026-08-21 Categories: cs.IR, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2608.21156v1 LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks. This evolution has produced paradigms including Prompt Engineering to elicit model capabilities, Context Engineering to manage information access, Harness Engineering to organize external tools and resources, and Loop Engineering to support continual reflection and self-improvement. Yet as tasks grow more complex, individual intelligence faces a fundamental limit: many tasks require heterogeneous expertise, interdependent subtasks, parallel execution, independent verification, and persistent state, exceeding any single agent's organizational capacity. Augmenting one agent's capabilities or context cannot resolve this architectural mismatch; intelligence must instead be distributed across specialized agents and organized at the system level. We call this System Intelligence: an agent system's ability to organize and coordinate multiple intelligent components into a coherent, adaptive whole pursuing a shared objective. Achieving it requires more than adding agents; it demands explicit structures to organize work, coordinate heterogeneous agents, and maintain evolving execution states. We introduce Graph Engineering, an emerging paradigm for next-generation agent systems. Unlike prior paradigms that mainly optimize individual interactions or agent-level behavior, Graph Engineering constructs explicit, dynamic, evolving graph structures representing tasks, agents, and system states. These abstractions provide a unified foundation for organizing complex objectives, orchestrating heterogeneous agents, modeling system dynamics, and enabling scalable agent evolution. We systematically review the principles, methodologies, and applications of Graph Engineering for LLM agents. Related papers, open-source data, and projects are collected at https://github.com/DEEP-JLU/Awesome-Graph-Engineering. --- ### Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learning Authors: Blaise Delaney, Dominic Dootson, Juan Jose Juan Castella, Salil Patel, Andrew Pfaff, Yuji Xing, Jonny Hancox, Karin Sevegnani Published: 2026-08-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.21147v1 The cyclic structure of physiological processes offers a natural prior for self-supervised representation learning, and the cardiac cycle provides a particularly well-defined setting in which to exploit it. We derive a phase-equivariant self-supervised objective and introduce Winder, a joint-embedding architecture that organises representations into phase-invariant coordinates and phase-rotating harmonic subspaces. Its transport operator is fixed and closed-form, derived from the cycle's geometry rather than learned, and adds no parameters. Evaluated on PTB-XL under a frozen linear-probe protocol, Winder attains diagnostic accuracy within the range reported by state-of-the-art self-supervised methods at a ~1 M parameter footprint, while exhibiting phase-equivariant latent geometry. These findings demonstrate that explicitly encoding cardiac-phase symmetry can preserve diagnostically useful information while yielding a latent geometry that is legible, parameter-efficient, and directly tied to a measurable physiological quantity. --- ### COEC: Calibrated Orthogonal-Equivalence Compensation for Structured Pruning of Large Language Models Authors: Peiqi Yu, Nam Ling, Wei Wang, Wei Jiang Published: 2026-08-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.21142v1 Structured pruning reduces the size and inference cost of large language models (LLMs) by removing weight columns, but the resulting output error can degrade accuracy. Existing training-free compensation methods use an additive bias or a single orthogonal rotation on the output side of the retained weight. These corrections leave its input singular frame unchanged and therefore limit how the retained weight can adapt after column removal. We propose COEC (Calibrated Orthogonal-Equivalence Compensation), a training-free compensation framework that applies alternating left and right orthogonal rotations to the retained weight. The right rotation is optimized on a reduced Stiefel manifold, while singular values are rescaled using generalized cross-validation to select the regularization strength for each layer. COEC further tempers the calibration Gram matrix to reduce the dominance of high-energy activation directions and introduces an alignment penalty that preserves the geometric relation between adjacent attention projections.All components use second-order statistics from a small calibration set and require neither backpropagation through the LLM nor retraining of the model parameters. COEC is independent of the column pruning criterion and can be applied to multiple structured pruning methods. Experiments on the Llama-3, Llama-3.1, and Qwen2.5 model families across multiple structured sparsity levels show that COEC improves perplexity on every model and zero-shot accuracy in most settings over existing compensation methods, with larger gains at higher sparsity. These results show that post-pruning compensation can recover part of the performance lost to column removal. --- ### A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans Authors: Simon Vincent Abel, Heiko Hillenhagen, Michael Götz, Timo Ropinski, Ayhan Can Erdur, Daniel Santak Wolf Published: 2026-08-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.21140v1 Reliable spatial understanding is an important prerequisite for future medical vision-language systems that aim to support radiological report generation and structured image understanding. While modern vision-language models (VLMs) show promising performance on many medical imaging tasks, recent evidence suggests they remain weak in controlled spatial reasoning and often fail to reliably ground spatial relations in image evidence. Given that radiological reasoning hinges on understanding the relative positions of anatomical structures and findings, this spatial weakness poses risks to diagnostic accuracy. We present a modular medical imaging agent for binary spatial relation verification in axial CT slices. Instead of directly predicting spatial answers end-to-end, the system decomposes the task into explicit stages: language parsing, anatomical localization, and deterministic geometric verification. Natural-language queries are converted into structured relation tuples, queried organs are localized with a YOLO-based detector, and the final spatial decision is computed from object centers using deterministic geometric rules. We evaluate the approach on the held-out MIRP spatial QA benchmark and compare it against representative end-to-end VLM baselines. The best-performing hybrid configuration reaches 94.1% accuracy and 94.2% F1, outperforming direct Qwen2-VL prompting by 42.5 percentage points in accuracy, while preserving interpretable intermediate representations and auditable reasoning stages. The results suggest that explicit modular spatial verification can serve as a promising building block for future report-oriented medical imaging agents. --- ### BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning Authors: Mouhamed Amine Bouchiha, Gregory Blanc, Yufei Han Published: 2026-08-21 Categories: cs.LG, cs.CR, cs.DC arXiv: https://arxiv.org/abs/2608.21137v2 Decentralized Federated Learning (DFL) promises trust-free collaborative learning by replacing the centralized parameter server with peer-to-peer model exchange. However, this architectural shift fundamentally reshapes the threat landscape. Without globally coordinated aggregation, DFL becomes particularly susceptible to backdoor attacks, in which malicious participants implant persistent hidden behaviors while maintaining high clean-task performance. In this paper, we argue that the robustness of DFL has been significantly overestimated. Existing studies rely on simplified threat models, non-adaptive adversaries, fragmented evaluation protocols, inconsistent communication topologies, and ad hoc training configurations, leading to an incomplete understanding of DFL security. To address these limitations, we present BackDFL, a unified benchmark for systematically evaluating DFL under realistic and adaptive backdoor attacks. Through extensive experiments, BackDFL exposes critical failure modes of decentralized learning. Our results demonstrate that both state-of-the-art Byzantine-robust DFL methods and adapted FL backdoor defenses fail under modest malicious participation rates (as low as 15%), especially in heterogeneous settings, while their robustness varies substantially across communication graph topologies. --- ### BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning Authors: Mouhamed Amine Bouchiha, Gregory Blanc, Yufei Han Published: 2026-08-21 Categories: cs.LG, cs.CR, cs.DC arXiv: https://arxiv.org/abs/2608.21137v1 Decentralized Federated Learning (DFL) promises trust-free collaborative learning by replacing the centralized parameter server with peer-to-peer model exchange. However, this architectural shift fundamentally reshapes the threat landscape. Without globally coordinated aggregation, DFL becomes particularly susceptible to backdoor attacks, in which malicious participants implant persistent hidden behaviors while maintaining high clean-task performance. In this paper, we argue that the robustness of DFL has been significantly overestimated. Existing studies rely on simplified threat models, non-adaptive adversaries, fragmented evaluation protocols, inconsistent communication topologies, and ad hoc training configurations, leading to an incomplete understanding of DFL security. To address these limitations, we present BackDFL, a unified benchmark for systematically evaluating DFL under realistic and adaptive backdoor attacks. Through extensive experiments, BackDFL exposes critical failure modes of decentralized learning. Our results demonstrate that both state-of-the-art Byzantine-robust DFL methods and adapted FL backdoor defenses fail under modest malicious participation rates (as low as 15%), especially in heterogeneous settings, while their robustness varies substantially across communication graph topologies. --- ### Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding Authors: Jie Xu, Na Zhao Published: 2026-08-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.21136v1 Recently, open-vocabulary zero-shot 3D scene understanding using vision foundation models has emerged as a promising alternative to data-intensive supervised methods. However, deploying these models in real-world scenarios is severely hindered by their inability to efficiently handle streaming RGB-D inputs and their inherent vulnerability to noise 2D segmentation masks. To address these critical limitations, we propose Stream3Dv2, a novel training-free framework designed for robust streaming 3D perception. Stream3Dv2 processes sequential data through an original nested local-to-historical architecture, capturing multi-view consistency while circumventing the high computational overhead so as to support timely responses. At its core, we introduce a comprehensive geometric-semantic fusion mechanism that resolves geometric noise and semantic ambiguity by explicitly utilizing semantic guidance and formulating 3D segmentation as solving point-and-set merging and partitioning problems. Furthermore, we present an innovative manifold-distance-based point cloud refinement strategy. This approach leverages local manifold graphs for point-to-manifold optimization that mitigates the boundary delineation failures caused by Euclidean-distance metrics, and employs geometric bounding boxes to dynamically activate and update historical instances for achieving rapid manifold-to-manifold refinement. Extensive experiments on public datasets demonstrate that Stream3Dv2 consistently outperforms existing baselines in foundational open-vocabulary streaming 3D segmentation and detection. Finally, we show that integrating our framework with an LLM-based agent enables advanced language-driven 3D scene understanding, underscoring its potential for open-world embodied intelligence. Code will be updated at https://github.com/SubmissionsIn/Stream3D. --- ### Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs Authors: Luka Ribar, Jeevan Bhoot, Douglas Orr Published: 2026-08-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.21134v1 Deploying vision-language models (VLMs) on mobile devices is challenging due to their significant memory and compute requirements. We present a framework for quantizing VLMs for efficient inference on resource-constrained hardware. Our approach combines a quantization pipeline that uses the model itself to generate training data and does not require access to the training setup, with a novel 2.7-bit-per-parameter format supporting efficient execution on Arm CPUs. We validate our approach by compressing the Llama 3.2 11B Vision Instruct model to 3.7 GB with 8-bit activations, preserving strong performance on a set of standard visual question answering tasks. --- ### Masking Is Not Enough: Generative Restoration for Multimodal De-Identification in Medical AI Authors: Shiva Shrestha, Zongxing Xie, Chen Zhao, Liran Ma, Zhipeng Cai, Honghui Xu Published: 2026-08-21 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2608.21133v1 Medical image-text data can expose protected health information (PHI) through both visible image content as well as accompanying text, creating a barrier to privacy-preserving medical AI systems. This risk is especially prominent in multimodal systems, where images, questions, reports, and clinical context may enter training, evaluation, or inference pipelines. Existing medical vision-language benchmarks primarily emphasize task utility, while de-identification methods are often evaluated separately from downstream reasoning. We introduce ClinX, an end-to-end multimodal PHI sanitization framework for medical image-text data. ClinX detects visible identifiers with optical character recognition (OCR), constructs binary PHI masks, and applies ClinX-PRISM, a no-skip generative restoration module with privacy-oriented post-processing for burned-in identifier suppression. In parallel, text-side PHI is reduced through progressive de-identification levels: regex masking, context-aware masking, and rewrite-based sanitization. We evaluate ClinX in medical visual question answering (MedVQA), jointly measuring PHI leakage and downstream utility across image-side, text-side, and combined de-identification settings. Results show that OCR-only masking is not sufficient as a standalone solution, and restoration-based sanitization better preserves clinically relevant visual context while sharply reducing recoverable PHI. --- ### Root cause analysis via difference graph discovery from linear time-series data Authors: Anouk Ruer, Timothée Loranchet, Daria Bystrova, Charles K. Assaad Published: 2026-08-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.21117v1 Root cause analysis aims to identify the mechanisms responsible for anomalies in complex dynamical systems. In this paper, we study root cause analysis in linear time-series through the lens of difference graph discovery. We focus on effect-defying root causes, corresponding to variables whose causal coefficients change between a normal and an anomalous regime. We formalize this problem using linear discrete-time dynamic structural causal models and adapt several methods originally introduced for discovering difference graphs between two populations to the time-series setting, where the two populations are replaced by a normal and an anomalous regime. We first evaluate the proposed approaches on simulated data, and then demonstrate their practical relevance on real-world datasets from IT monitoring and intensive care monitoring. Our results show how difference graph discovery can help localize causal mechanisms responsible for anomalous behavior. --- ### CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agents Authors: Jiancheng Wang, Mingli Zhu, Tong Zhang, Jiaqi Ruan, Wei Wang, Siyuan Liang, Dacheng Tao Published: 2026-08-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.21114v3 Visual world-model agents such as DreamerV3 act through a recurrent latent state rather than a single observation, which weakens frame-wise observation attacks and makes their perturbations vary sharply over time under a strict per-frame perturbation constraint. We study white-box, causal, online attacks on such agents and propose Critic-Induced Value-Subspace Attacks (\textbf{CIVA}). Our key observation is that, along a rollout, critic-guided perturbations concentrate in a low-dimensional subspace induced by the victim's own critic. Based on this observation, CIVA first probes the frozen victim offline with critic-guided PGD and extracts a low-rank value-subspace by SVD. At test time, it optimizes only the subspace coefficients, smooths them with an exponential moving average (EMA), and maps them back to pixels. This design attacks value-sensitive recurrent dynamics while keeping the online optimization cheap and temporally coherent. Extensive experiments on DMC walker walk, Atari Pong, and Crafter show that CIVA consistently outperforms five recent methods; on DMC walker walk, it achieves the largest reward drop of 26.07\% while keeping temporal variation low, with TempAbs of 0.646. --- ### CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agents Authors: Jiancheng Wang, Mingli Zhu, Tong Zhang, Jiaqi Ruan, Wei Wang, Siyuan Liang, Dacheng Tao Published: 2026-08-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.21114v1 Visual world-model agents such as DreamerV3 act through a recurrent latent state rather than a single observation, which weakens frame-wise observation attacks and makes their perturbations vary sharply over time under a strict per-frame perturbation constraint. We study white-box, causal, online attacks on such agents and propose Critic-Induced Value-Subspace Attacks (\textbf{CIVA}). Our key observation is that, along a rollout, critic-guided perturbations concentrate in a low-dimensional subspace induced by the victim's own critic. Based on this observation, CIVA first probes the frozen victim offline with critic-guided PGD and extracts a low-rank value-subspace by SVD. At test time, it optimizes only the subspace coefficients, smooths them with an exponential moving average (EMA), and maps them back to pixels. This design attacks value-sensitive recurrent dynamics while keeping the online optimization cheap and temporally coherent. Extensive experiments on DMC walker walk, Atari Pong, and Crafter show that CIVA consistently outperforms five recent methods; on DMC walker walk, it achieves the largest reward drop of 26.07\% while keeping temporal variation low, with TempAbs of 0.646. --- ### Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda Authors: Wei Lin, Tao Zhou, Zhaofei Xie, Changgui Hong Published: 2026-08-21 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.21107v1 Large Language Models (LLMs) are moving from code completion toward repository-scale agents that retrieve context, edit files, execute tools, and participate in security-sensitive workflows. The evidence for these systems, however, remains divided between software engineering evaluations centered on functional task completion and software security evaluations centered on vulnerability detection, secure generation, or exploit-oriented validation. This evidence-centered structured survey synthesizes representative work available through May 31, 2026 across software engineering tasks, software security tasks, adaptation mechanisms, artifact granularity, and evaluation design. In addition to a task taxonomy, we introduce an assurance framework that separates functional correctness, security, operational reliability, evidence provenance, and agent authority. The review shows that execution feedback and repository access can substantially improve engineering task completion, but do not by themselves establish security; conversely, static-analysis labels or vulnerability-classification scores rarely establish deployable correctness. We identify recurring validity threats--weak test oracles, duplicated and temporally leaked data, changing agent harnesses, proxy-only security checks, and under-reported budgets and human intervention--and derive a minimum reporting protocol for cross-study comparison. The resulting research agenda prioritizes jointly secure-and-functional benchmarks, repository-scale threat models, calibrated human oversight, longitudinal maintainability evidence, and reproducible agent evaluation. The central conclusion is that model capability should be judged as an assurance case supported by task-appropriate evidence, rather than by a single benchmark score. --- ### Atom Learning Model (ALM): how a real classroom got tokenised Authors: Philipp Bogdan Published: 2026-08-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.21106v3 The Atom Learning Model (ALM) tokenises a school curriculum. 757 pages of GCSE and Further Mathematics material were read by machine into 1,934 atoms, each one thing a learner can do in a single step, ordered by 4,616 machine-written prerequisite links. Both sides of a lesson are then expressed in that one structure: a question is a set of atoms plus everything beneath them, a child's ability is a score between 0 and 1 on every atom of the same graph, and whether a question suits a child is arithmetic over one index, with no difficulty parameter fitted for either side. Nobody wrote an atom, a link or a question. Reading the 757 pages cost £55, building the whole structure cost between £615 and £1,230, and against it the system composed 6,648 questions for 373 children in two English secondary schools over seven weeks, at 26p per composed question. Four measurements went against expectation. The cost is in the links, not the pages. The composer's own difficulty label has a rank correlation of -0.0123 with measured facility, so a language model shown a question cannot say how hard it is. Children stop working when a mark takes seven seconds instead of three. And the deployment never served a question deeper than two prerequisite steps, which is exactly where the central premise becomes testable, leaving it unfalsified rather than confirmed. --- ### Atom Learning Model (ALM): how a real classroom got tokenised Authors: Philipp Bogdan Published: 2026-08-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.21106v1 The Atom Learning Model (ALM) tokenises a school curriculum. Two secondary mathematics textbooks were read by machine into 1,934 atoms, each one thing a learner can do in a single step, ordered by 4,616 machine-written prerequisite links. Both sides of a lesson are then expressed in that one structure: a question is a set of atoms plus everything beneath them, a child's ability is a score between 0 and 1 on every atom of the same graph, and whether a question suits a child is arithmetic over one index, with no difficulty parameter fitted for either side. Nobody wrote an atom, a link or a question. Reading the 757 pages cost £55, building the whole structure cost between £615 and £1,230, and against it the system composed 6,648 questions for 373 children in two English secondary schools over seven weeks, at 26p per composed question. Four measurements went against expectation. The cost is in the links, not the pages. The composer's own difficulty label has a rank correlation of -0.0123 with measured facility, so a language model shown a question cannot say how hard it is. Children stop working when a mark takes seven seconds instead of three. And the deployment never served a question deeper than two prerequisite steps, which is exactly where the central premise becomes testable, leaving it unfalsified rather than confirmed. --- ### ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents Authors: Kai Wang, Zeming Wei, BiaoJie Zeng, Chang Jin, An Wang, Xiaokun Luan, Zhixiao Lin, Jingjing Qu, Xia Hu, Xingcheng Xu Published: 2026-08-21 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.21101v1 As large language model (LLM) agents move from conversation to executing code, reading local files, and orchestrating external tools, a single agent hijacked by a malicious third-party skill can cause data exfiltration, privilege escalation, or cascading compromise. We argue that agentic risk is progressive: it can enter at four loci of the agent control loop--skill admission, invocation-time intent, execution-time effect, and post-action consequence--while a denied dangerous objective can reappear across surface forms, tools, or turns; existing safeguards are typically local to one lifecycle boundary or one call. Guided by this threat model, we present ClawSentry, an open-source, framework-agnostic security supervision gateway for agent runtimes. Before a skill package is ever executed, First-use Skill Package Review (FSPR) audits it under a deterministic evidence floor, escalating unresolved cases to bounded read-only agentic review (locus A). At runtime, a three-tier progressive decision engine--a deterministic L1 layer, a rule-anchored L2 semantic reviewer, and a read-only L3 evidence-seeking agent--spends contextual review only on the residual ambiguity, while a session-level anti-bypass mechanism recognizes tool-switching and rephrased retries (loci B--C); a post-action path feeds high-severity evidence non-retroactively into later review (locus D). An Agent Harness Protocol (AHP) abstraction applies one policy across Codex, Claude Code, Kimi CLI, and Gemini CLI without modifying agent internals. On SkillInject with Codex/GPT-5.4, contextual ASR falls from 39.55% to 2.61% while contextual TSR moves only from 83.78% to 83.05%. Across five Work Agents on the full SkillsSafety benchmark, ClawSentry confines ASR to 9.09--15.03% from 33.5--49.7% unprotected, and aggregate TSR on clean skills remains 98.7%. --- ### ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models Authors: Wenzheng Jiang, Xuankun Rong, Yuanzhao Zhai, Dawei Feng, Huaimin Wang Published: 2026-08-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.21100v1 While multimodal large language models (MLLMs) extend model capabilities beyond text, they also make safety alignment increasingly challenging. Multimodal safety alignment methods must address cross-modal jailbreaks, safety-awareness failures, and over-sensitive refusals. However, existing methods often rely on retraining or internal-state inspection, limiting their applicability to deployed closed-source MLLMs and motivating test-time safety alignment. We analyze this setting and identify two key obstacles, utility dominance and reasoning inertia, which cause models to overlook latent risks or follow malicious reasoning trajectories. Guided by these insights, we propose ReFrame, a training-free multimodal input reframing framework where two agents share a lightweight locally deployed MLLM: the evidence-generation agent constructs complementary risk and utility evidence, and the rewrite-and-routing agent converts it into a safe proxy prompt and image-routing decision before calling the downstream MLLM, without modifying it or accessing its internal information. Experiments across multiple MLLMs and benchmarks show that ReFrame improves jailbreak defense, safety awareness, and oversensitivity reduction while preserving multimodal utility. --- ### A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration Authors: Jiekang Feng, Zhihe Fan, Yunqi Zhu, Xinjie Yao, Yueying Zhang, Yike Gao, Ranxin Li, Guanzuo Chen, Pengfei Zhu Published: 2026-08-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.21099v2 Multi-modal object detection is essential for robust scene understanding in challenging conditions, including low-light and adverse environments. Recent vision foundation models (e.g., DINOv3) have exhibited strong representation capabilities, yet adapting them to multi-modal scenarios remains challenging. Existing dense cross-modal fusion strategies often force heterogeneous modalities to interact indiscriminately, which may introduce redundant information and disrupt the valuable pre-trained representations. To address this issue, we revisit multi-modal fusion from the perspective of socialized learning and propose adapter to DINOv3 (A2DINOv3), a multi-expert collaboration framework with a Socialized Collaboration Protocol (SCP). Specifically, RGB and infrared branches are modeled as heterogeneous experts that independently preserve their specialized knowledge while exchanging complementary information through selective and constrained interactions. This design mitigates harmful cross-modal interference and prevents degradation of pre-trained priors during adaptation. Furthermore, a zero-initialization strategy is introduced to gradually activate cross-modal collaboration, enabling a smooth transition from modality-specific learning to cooperative representation learning. Extensive experiments on four multi-modal benchmarks, including aerial detection (GAIIC), autonomous driving (FLIR), low-light surveillance (LLVIP), and diverse real-world scenarios (M3FD), demonstrate that A2DINOv3 consistently achieves state-of-the-art performance in multi-modal object detection. --- ### A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration Authors: Jiekang Feng, Zhihe Fan, Yunqi Zhu, Xinjie Yao, Yueying Zhang, Yike Gao, Ranxin Li, Guanzuo Chen Published: 2026-08-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.21099v1 Multi-modal object detection is essential for robust scene understanding in challenging conditions, including low-light and adverse environments. Recent vision foundation models (e.g., DINOv3) have exhibited strong representation capabilities, yet adapting them to multi-modal scenarios remains challenging. Existing dense cross-modal fusion strategies often force heterogeneous modalities to interact indiscriminately, which may introduce redundant information and disrupt the valuable pre-trained representations. To address this issue, we revisit multi-modal fusion from the perspective of socialized learning and propose adapter to DINOv3 (A2DINOv3), a multi-expert collaboration framework with a Socialized Collaboration Protocol (SCP). Specifically, RGB and infrared branches are modeled as heterogeneous experts that independently preserve their specialized knowledge while exchanging complementary information through selective and constrained interactions. This design mitigates harmful cross-modal interference and prevents degradation of pre-trained priors during adaptation. Furthermore, a zero-initialization strategy is introduced to gradually activate cross-modal collaboration, enabling a smooth transition from modality-specific learning to cooperative representation learning. Extensive experiments on four multi-modal benchmarks, including aerial detection (GAIIC), autonomous driving (FLIR), low-light surveillance (LLVIP), and diverse real-world scenarios (M3FD), demonstrate that A2DINOv3 consistently achieves state-of-the-art performance in multi-modal object detection. --- ### When does fusing hand-crafted knowledge with learned representations pay? A cost-normalized benchmark of stacking, substitution, and interference Authors: Ahmad AlMughrabi, Albert Clop, Benjamin Busam, Ricardo Marques, Petia Radeva Published: 2026-08-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.21098v1 Fusing prior knowledge with data-driven learning is attractive where data is scarce, yet no controlled account says when it helps, is redundant, or harms. We benchmark one fixed hand-crafted knowledge source, a pinned bank of Gabor targets injected only during training at $\sim$2\% overhead, against data-driven alternatives (SimCLR, SimSiam, DINO, ImageNet transfer, augmentation, learned teachers) under one frozen recipe with fixed subsets: 13 datasets, 9 backbones, 150 to 1.28M images, 32--224\,px, 2.5M--86M parameters ($\computeCells$ classification configurations over $\computeRuns$ runs, plus segmentation and detection transplants). Across the training-time combinations we measure, three outcomes recur (decision-level fusion differs). Different-\emph{currency} sources can stack: the prior composes with DeiT augmentation on attention backbones and is worth $+26$ points to ViT-B/16 at $224$\,px, $+6.7$ at twice that budget. Same-currency sources substitute: against effective self-supervised pretraining, the combination never usefully exceeds the better single source. Fusing at full strength into an already-informed initialization interferes in proportion to what it carries: ImageNet transfer, $-15$ to $-17$ points, removed by a weaker auxiliary weight. Frozen-feature diagnostics measured on each source alone separate these outcomes retrospectively but do not predict them: a rule built on them calls one of nine unseen pairs. At a practitioner's own label budget, the frozen-feature gain predicts the end-to-end gain to within $0.17$ points across 30 cells and seven datasets; the underlying decomposition, $Δ= G + \readout(\mathrm{base})$, holds in sign on $\auditRate\%$ of testable cells and is called an unseen backbone family's feature gain in advance. The project page is https://amughrabi.github.io/MomentAux. --- ### When Trust Meets Truth: Trust-Truth Separability in LLM-as-Judge Authors: Xin Sun, Di Wu, Yuchen Guo, Jiahuan Pei, Isao Echizen, Abdallah El Ali, Saku Sugawara Published: 2026-08-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.21097v1 LLM-as-Judge systems can produce multi-dimensional evaluations, such as trustworthiness, reliability, and factuality, and these outputs are often interpreted as independent evidence. We test this assumption for a common pair of judgments: trust scoring and binary truth classification. On correctness-controlled QA, LLM judges align trust scores with truth verdicts more tightly than human behavioral reference, suggesting weaker separations between trust and truth judgment. We then apply stress tests by changing only source cues of identical QA between Human and AI. Source attribution shifts not only trust scores but also truth verdicts and logit-derived correct-side probabilities. Results show that current LLM-as-Judge protocols should not treat trust scores as independent evidence for truth judgments. --- ### FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space Authors: Jiahong Liu, Ram Samarth B B, Xinyu Fu, Menglin Yang, Weixi Zhang, Rex Ying, Irwin King Published: 2026-08-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.21096v1 Federated learning enables privacy-preserving collaborative training, but highly heterogeneous client data remain challenging, especially in graph federated learning where clients possess structurally diverse graphs. Existing personalized federated learning (PFL) methods ignore the intrinsic geometric properties of diverse graph structures. We propose FlatLand, a novel personalized federated learning method that embeds different clients' data in tailored Lorentz space of hyperbolic geometry. Our key insight is that hyperbolic geometry naturally accommodates the intrinsic negative curvature prevalent in real-world graphs, while the time-like dimension in Lorentz space provides a principled way to encode client-specific heterogeneity. We develop a parameter decoupling strategy that separates heterogeneous information (captured in time-like parameters) from common knowledge (preserved in space-like parameters), enabling direct aggregation without requiring client similarity estimation and extra calculation modules. Empirical results on diverse federated graph learning tasks demonstrate that FlatLand achieves superior performance, particularly in low-dimensional settings. --- ### Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems Authors: Balkrishna Giri, Md Toufique Hasan, Jussi Rasku, Muhammad Waseem, Pekka Abrahamsson Published: 2026-08-21 Categories: cs.SE, cs.AI, cs.CL, cs.CR, cs.IR arXiv: https://arxiv.org/abs/2608.21095v1 Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) outputs in external knowledge, but RAG systems usually trust whatever they retrieve, creating a Security-Reliability Gap: high semantic relevance does not guarantee factual truth. Adversaries exploit this through knowledge poisoning, inserting malicious documents to cause targeted misinformation. We propose an Evaluation Agent, middleware that combines Natural Language Inference (NLI) factual verification, a five-signal poison detector with relevance-weighted aggregation, and a Trust Index T = 0.4 F + 0.35 C + 0.25 (1 - P ) with a non-linear dampener for high-contamination contexts. On TruthfulQA with Llama 3.3 70B, the agent reaches 91% accuracy and 100% precision, with 100% recall on instruction injection, while in-place edits, such as entity swaps, remain hard to detect. Across three LLMs the Trust Index stays discriminative, with a Receiver Operating Characteristic Area Under the Curve (ROC-AUC) of 0.73 to 0.81; generation style matters more than model size, and per-LLM threshold calibration restores baseline competitive accuracy, whereas a weaker FEVER result shows that cross-dataset generalization requires domain-specific calibration. In a software-engineering use case, a secure-coding assistant over guidance from the Open Worldwide Application Security Project (OWASP) Top 10 and the Common Weakness Enumeration (CWE), the agent reliably blocks instruction injection of unsafe advice (F1 92%), while contradiction and subtle semantic weakening remain hard. Throughout, the agent measures detection of poisoned context before generation, not whether the LLM adopts the injected misinformation. We release the proposed approach, attack generator, and experimental artifacts at the link: https://github.com/GPT-Laboratory/TrustworthyRAG. --- ### Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion Prediction Authors: Yue Ma, Frederick W. B. Li, Xiaohui Liang Published: 2026-08-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.21093v1 Stochastic human motion prediction aims to forecast future motion distributions. Although recent studies have achieved strong performance in terms of accuracy and diversity, they often overlook plausibility (e.g., resulting in physically unrealistic predictions) and uncertainty quantification, both of which are essential for real-world applications and downstream tasks. To address these issues, we propose a latent flow-based model equipped with a data-driven Gaussian mixture prior that more effectively disentangles diverse human behaviors than conventional single-modal priors. This prior is derived from patterns in the training data without requiring additional annotations. Furthermore, the fully invertible nature of our model enables natural uncertainty quantification through tractable likelihood computation. Experiments on the Human3.6M and AMASS datasets demonstrate that our approach achieves state-of-the-art performance in both accuracy and plausibility. --- ### Can Legal AI Know When It Is Wrong? And Do Students Know When It Is? Authors: Angel Mary John, Vipin Kumar Singh, Jerrin Thomas Panachakel Published: 2026-08-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.21089v1 Integrating Large Language Models (LLMs) into the Indian judiciary promises access to justice but introduces severe risks. We identify the 'inertia of confidence'--an overconfidence phenomenon analogous to the Dunning-Kruger effect where LLMs provide incorrect legal verdicts with near-maximum confidence, driven by a hypothesized 'precedent overfitting' bias. Phase I of our socio-technical audit tested ChatGPT (GPT-5.2), Meta AI, and Perplexity AI on a 60-case battery regarding the Indian Contract Act, 1872, and the shift toward statutory enforcement of specific performance. We introduce the High-Confidence Error Rate (HCER) to quantify incorrect verdicts delivered with dangerous certainty (>= 9 on a 1-10 scale). All models struggled with statutory updates. Meta AI proved most vulnerable (31.7% HCER), frequently misapplying pre-amendment rules with a 9.1/10 mean confidence, followed by Perplexity (15.0%) and ChatGPT (6.7%). Phase II investigated human vulnerability to this overconfidence via a survey of Indian law students (N=380). Verification often functions as a reactive adaptation to machine hallucinations: students encountering fabricated citations reported higher verification scores (4.2/5) than those with no such encounters (2.8/5). Furthermore, while 81.6% knew submitting hallucinated cases can lead to contempt-of-court, 71.1% received no formal training on ethical AI use. We propose shifting toward adversarial legal research pedagogy and implementing source-grounded verification architectures to prevent systemic professional negligence. --- ### When the Feature Pool Goes Algorithmic: Extending Mufwene's Ecology of Language Evolution to LLM-Mediated Exposure Authors: Kunmei Han Published: 2026-08-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.21088v1 Mufwene's ecological model locates language evolution in competition among variants contributed by individual idiolects and in speakers' selection from linguistic material made available through interaction. Large language models (LLMs) complicate this architecture without requiring the locus of selection to move away from human speakers. This article argues that LLMs are best treated as distributional mediators: they aggregate language produced across human populations, transform its distribution through training and post-training, and redistribute model-specific outputs at scale. I call the resulting ecological process algorithmic reweighting of the speaker-accessible distribution: model mediation can alter the relative frequencies with which competing variants reach human selectors. Emerging evidence on model-specific linguistic profiles and lexical uptake is consistent with parts of this pathway, but does not establish inevitable convergence. Human social evaluation remains decisive: model-associated forms may diffuse and become conventionalized, become socially recognizable as 'AI-like' and subsequently avoided, or fail to diffuse in the first place. The proposal extends Mufwene's feature-pool ecology one step upstream of speaker selection and yields testable predictions about uptake, model-version effects, convergence, and social reversal. --- ### Jokes Aside: Measuring the Semantic Distance of Double Meanings Authors: Fabio De Ponte Published: 2026-08-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.21087v1 Large language models have significantly enriched the toolkit for computational humor research, particularly in the automated generation of jokes and puns. A key innovation, contextual embedding vectors, offers new opportunities to revisit and refine earlier hypotheses. Notably, Petrovic and Matthews (2013) proposed a joke generation model based on the scheme "I like my X like I like my Y, Z" (e.g. "I like my ice like I like my dreams, crushed"). They suggested that joke hilarity increases with: a) frequent association of Z with X and Y, b) rarity of Z, c) ambiguity of Z, and d) meaning distance between X and Y. Building on this, Winters et al. (2019) proposed a set of metrics, based on Google Ngrams and Word2Vector. In this work, three out of their five metrics are revisited with word embeddings: obviousness, compatibility, and comparison. Another measure, symmetry, defined as closeness of Z to both X and Y, is introduced here for the first time. Two models were used to collect the embedding vectors (OpenAI text-embedding-3-small and MiniLM all-MiniLM-L6-v2) on three datasets: JokeJudger, Expunations, and rJokes. The last two datasets, Expunations, and rJokes, were expanded by adding paired sentences that captured the ambiguous expression at the core of each joke in its two different meanings. Results revealed that models trained on the proposed metrics performed poorly in predicting humor ratings: on JokeJudger, the best model achieved 57.1% accuracy, below the 61.5% baseline, while performance on Expunations and rJokes was even lower. Nevertheless, the symmetry metric seems consistently associated with higher-rated jokes, suggesting it may capture a necessary -though not sufficient- property of humor. --- ### Causal Modeling of Adverse Pregnancy Outcomes via Adaptive LLM Proposals Authors: Kavimayil P. Komarasamy, Saurabh Mathur, Ameet Soni, David M. Haas, Kristian Kersting, Sriraam Natarajan Published: 2026-08-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.21079v1 Adverse Pregnancy Outcomes (APOs) such as preterm birth and gestational diabetes can have long-term consequences for both the mother and child, yet an understanding of their causes remains elusive. Causal discovery in this domain is especially challenging due to a paucity of data and incomplete domain knowledge. As a result, pure data-driven methods fail, and Large Language Model (LLM) outputs remain inconsistent or contradictory. We introduce a neurosymbolic framework for generating plausible causal hypotheses that iteratively combines the broad prior knowledge of LLMs with empirical scoring on data. Our method treats the LLM as an adaptive proposal distribution, generating hypotheses that are scored against empirical data; the resulting high-scoring graphs are then used to update the LLM's context, steering subsequent generations toward more promising regions of the hypothesis space. We evaluate our approach on a real-world clinical dataset for modeling APOs and their risk factors, comparing our results against an expert-constructed causal graph. Our method recovers all expert-validated edges and identifies additional plausible causal relations not previously listed by experts, potentially providing new insights for targeted interventions. --- ### AudioWorldSim: Realistic Binaural Audio Datasets For World Models Authors: Luis Vitor Zerkowski, Luiz Velho Published: 2026-08-21 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2608.21075v1 This technical report presents AudioWorldSim, an open-source platform designed to generate realistic binaural audio datasets and advance research in audio-based machine learning, particularly world models. Built as a custom extension of Meta's SoundSpaces 2.0 platform, AudioWorldSim leverages their comprehensive acoustics framework, but focuses on the automatic rollout of random agent navigations, as well as implements crucial fixes to how continuous sound is composed. AudioWorldSim is made publicly available to the research community at https://github.com/Luizerko/AudioWorldSim to facilitate reproducibility. --- ### PromptResponse: Optimizing Prompts for LLM Coding Tasks Authors: Erik Thureck, Robert Kühnen, Tim Jacobowitz Published: 2026-08-21 Categories: cs.CL, cs.AI, cs.HC, cs.SE arXiv: https://arxiv.org/abs/2608.21074v1 Large language models (LLMs) are increasingly used in research workflows and software development pipelines, yet their output remains sensitive to input prompt variations. This paper presents $\unicode{x00AB}$PromptResponse$\unicode{x00BB}$, a controlled study examining how formatting and LLM-based tuning of coding task prompts affect the resulting code's performance, efficiency, and stability. Using five semantically identical yet syntactically distinct variants of the HumanEval dataset$\unicode{x2014}$baseline, JSON, Markdown, YAML, and an LLM-tuned version$\unicode{x2014}$we had GPT-4o solve its coding problems over 8200$\unicode{x00A0}$executions. Our results show that consistent formatting$\unicode{x2014}$especially JSON$\unicode{x2014}$improves generation efficiency and syntactic stability, with minor gains in task performance. Conversely, the LLM-tuned prompts resulted in significantly degraded task performance without significant improvements in any other dimension. These findings suggest that low-effort reformatting alone can yield measurable improvements, while tuning must account for model alignment. We conclude our work with providing a set of practical recommendations informed by our results as well as releasing our dataset variants and evaluation pipeline for future work. --- ### TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics Authors: Yuhao Sun, Zekun Wu, Zixun Huang, Peijie Zhou Published: 2026-08-21 Categories: cs.LG, cs.AI, q-bio.GN arXiv: https://arxiv.org/abs/2608.21070v1 Inferring continuous system evolution from sparse temporal snapshots is a key challenge in generative modeling and single-cell omics. While Optimal Transport (OT) is popular, existing frameworks are largely restricted to first-order dynamics, assuming memoryless velocity fields. This limits expressiveness, as first-order systems fail to account for regulatory momentum and time-delayed responses inherent in processes like cell differentiation. Here, we introduce TracingFlow, a simulation-free Flow Matching framework generalizing to second-order dynamics. By using neural networks to regress the acceleration field, TracingFlow provides an exact, efficient solution to the Dynamical Optimal Acceleration Transport (DOAT) problem. Unlike first-order methods yielding over-smoothed trajectories, our second-order formulation captures high-curvature transitions and nonlinear evolutions by learning the underlying force fields. Evaluated on complex synthetic and large-scale scRNA-seq datasets, TracingFlow achieves superior accuracy in distributional reconstruction and trajectory faithfulness. Moreover, by integrating lineage tracing priors, it recovers dynamical structures that are both mathematically optimal and biologically plausible. --- ### AT-ViT: Area-Targeted Multi-View Vision Transformer with Cross-Attention and Multi-Scale Patching for Plant Trait Recognition in Herbarium Images Authors: Amani Sedrat, Takieddine Chehhat, Youcef Sklab, Hanane Ariouat, Abderrazak Sebaa, Eric Chenin, Jean-Daniel Zucker, Edi Prifti Published: 2026-08-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.21067v2 Automated plant traits recognition from herbarium images is essential for plant sciences, yet remains challenging because background elements (e.g., textual labels, mounting artifacts, and color charts) can introduce shortcut learning, leading models to rely on spurious non-plant cues rather than plant morphology. This bias degrades both generalization and interpretability. In this paper, we introduce AT-ViT, a dual-branch Vision Transformer that jointly encodes raw herbarium scans and their segmented-derived counterparts via a multi-scale, multi-view cross-attention fusion scheme. AT-ViT further incorporates a mask-guided patch weighting mechanism that amplifies plant-relevant regions and attenuates background-driven features. By learning from the original scans while being guided by segmentation masks through the mask-guided patch reweighting mechanism, the model is encouraged to focus on plant organs and learn plant-centric representations more effectively. Across multiple trait classification tasks (e.g., leaf base shape, thorns), AT-ViT delivers consistent accuracy gains, improves attention localization on plant regions, and exhibits increased robustness under synthetic background perturbations. Specifically, AT-ViT substantially improves spatial attention grounding, boosting plant-region alignment (Avg IoU_p: +15.66 to +18.03 pp) while reducing background overlap (Avg IoU_b: -27.92 to -31.02 pp) relative to CrossViT, and remains markedly more robust to background perturbations, outperforming ResNet101 by up to +32.32 accuracy points and CrossViT by up to +5.07 points under background-noise conditions. ---