# Research Papers — 2026-07 · bundle page 107 of 222 > Full-text markdown of papers #5301–5350 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/107 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/106.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/108.md) ### WREN: Low Light Image Enhancement Using Retinex theory-based Double U-Net-like Structures Authors: Reina Kaneko, Junya Hara, Hiroshi Higashi, Yuichi Tanaka Published: 2026-07-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15604v1 This paper proposes a neural network for low light image enhancement (LLIE) based on retinex theory to make LLIE robust for various dynamic range scenes. The retinex theory is an image formulation model inspired by a human color perception hypothesis, where a low light image is decomposed into intrinsic color context (i.e., reflectance map) and scene-dependent illumination (i.e., illumination map). Due to non-uniqueness of its decomposition, existing retinex-based LLIE methods often fail to achieve stable decomposition, which lead to over-enhancement. Typically, they are sensitive to the dynamic ranges that vary in different lighting conditions. To tackle this issue, we propose WREN: An LLIE neural network with double U-Net-like structures. WREN consists of two U-Net-like sub-networks. The first network has one encoder and two decoders that decompose an input image into the reflectance and illumination maps. The second network with a customized Transformer block between an encoder and a decoder only enhances the illumination map obtained from the first network: This completely follows the assumption of the retinex theory. Finally, the enhanced illumination map is recombined with the reflectance map. The network is trained end-to-end with a scale-invariant loss function, which gives robustness against the illumination scaling. Numerical results show that our method achieves the state-of-the-art performance across multiple datasets. Our code is available online. --- ### Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth Authors: Jung-Hee Kim, Xiaoming Liu Published: 2026-07-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15600v2 Monocular depth foundation models have demonstrated remarkable generalization capabilities across diverse environments. However, they continue to struggle with metric depth estimation in diverse environments. This limitation stems from the inherent scale ambiguity of single-view inference, leading to misaligned scale predictions even when the relative geometry is accurate. Conversely, recent multi-view foundation models leverage cross-view cues to learn robust scene-level geometry and consistent scale. Yet, these benefits typically vanish during single-image inference, as the absence of explicit geometric constraints causes performance to degrade. To bridge this gap, we propose a novel framework that transfers the scale-aware geometric priors of multi-view models into monocular depth foundation models. Specifically, we introduce an Epipolar Distillation (EpiDistill), an approach utilizing Rectified Stereo Tokens, which enables the single-view prediction model to retain epipolar attention patterns and maintain geometric consistency without requiring multi-view inputs at inference. Experimental results demonstrate that our method significantly improves zero-shot metric depth estimation, particularly on challenging datasets like ETH3D and DIODE where scale alignment is critical. Furthermore, our approach is model-agnostic, consistently boosting the performance of state-of-the-art ViT-based models, including UniDepthV2 and DepthPro. --- ### Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth Authors: Jung-Hee Kim, Xiaoming Liu Published: 2026-07-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15600v1 Monocular depth foundation models have demonstrated remarkable generalization capabilities across diverse environments. However, they continue to struggle with metric depth estimation in diverse environments. This limitation stems from the inherent scale ambiguity of single-view inference, leading to misaligned scale predictions even when the relative geometry is accurate. Conversely, recent multi-view foundation models leverage cross-view cues to learn robust scene-level geometry and consistent scale. Yet, these benefits typically vanish during single-image inference, as the absence of explicit geometric constraints causes performance to degrade. To bridge this gap, we propose a novel framework that transfers the scale-aware geometric priors of multi-view models into monocular depth foundation models. Specifically, we introduce an Epipolar Distillation (EpiDistill), an approach utilizing Rectified Stereo Tokens, which enables the single-view prediction model to retain epipolar attention patterns and maintain geometric consistency without requiring multi-view inputs at inference. Experimental results demonstrate that our method significantly improves zero-shot metric depth estimation, particularly on challenging datasets like ETH3D and DIODE where scale alignment is critical. Furthermore, our approach is model-agnostic, consistently boosting the performance of state-of-the-art ViT-based models, including UniDepthV2 and DepthPro. --- ### Scalable LLM Agent Tool Access in the Cloud Authors: Mingxin Li, Enge Song, Yueshang Zuo, Xiaodong Liu, Rong Wen, Qiang Fu, Gianni Antichi, Jian He, Jing Tie, Zhou Shao, Xiaobo Xue, Xiong Xiao et al. Published: 2026-07-17 Categories: cs.DC, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2607.15593v1 LLM agents increasingly rely on tool calling to act on external systems, and the Model Context Protocol (MCP) has quickly become its de facto interface. Operating MCP at cloud scale, however, becomes difficult. On the tool provider side, legacy services are not directly callable through MCP; the rapid protocol development also creates ongoing compatibility cost. On the agent side, the number of accessible tool is limited by the LLM context window and inference overhead; mounting a large tool set increases token usage and inference latency and can reduce task success rate. Moreover, for stateful MCP backends with multiple replicas, preserving session affinity increases client-side complexity. We present a cloud-scale gateway system for MCP service. It breaks the direct-connect model on the data plane and offloads legacy service integration, consolidating incompatible MCP variants, access control, tool recommendation, and session-aware routing to the gateway. Hybrid retrieval sustains 98% Top-15 recall; it scales agent tool access to 3,000+ with high tool selection accuracy, and reduces tool selection time by $8.9\times$ and token usage by $23.8\times$, with low per-call overhead, stable under scale-out. Finally, we share the lessons learned from deploying the gateway system in production. --- ### MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion Authors: Xu Hou, Meiyu Liang, Wei Huang, Yawen Li, Zhe Xue, Wu Liu, Guanhua Ye, Lei Shi, Kangkang Lu Published: 2026-07-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.15592v1 Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues. Existing diffusion-based MKGC methods usually denoise directly on raw multimodal features. Such a design forces the denoiser to simultaneously perform relation-dependent cue selection, cross-modal semantic alignment, and structure-aware entity generation, which introduces noisy and semantically inconsistent conditions for diffusion and consequently leads to suboptimal completion performance. To address this limitation, we propose MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts (MGDT), a novel MKGC framework built on an align-then-diffuse paradigm. MGDT first employs a Relation-Adaptive Semantic Routing Mixture-of-Experts (RASR-MoE) module to select relation-relevant multimodal semantic transformation paths and suppress irrelevant modality interference. MGDT then uses a frozen Multimodal Large Language Model (MLLM) as a semantic anchor to align the routed multimodal representations into a unified latent space and reduce cross-modal semantic heterogeneity. Finally, a Knowledge Graph Diffusion Transformer (KGDT) performs graph-conditioned denoising generation in the aligned space to produce the missing entity representation. Experiments on three benchmark datasets show that MGDT consistently outperforms strong baselines. --- ### Field-Aware RankMixer with Dual-Stream Bilinear Fusion for the Tencent UNI-REC Challenge Authors: Yufeng Zhang, Zhengqi Xu, Jiajun Cui Published: 2026-07-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.15590v1 This paper presents our solution to the KDD Cup 2026 Tencent UNIREC Challenge. The task requires joint modeling of multi-domain user behavior sequences and non-sequential multi-field features for target-ad pCVR prediction. We develop a Field-Aware RankMixer (FA-RankMixer) with dual-stream bilinear fusion. The model first applies target-aware DIN modules to extract user interests from multiple behavior domains. It also models recent and earlier interests separately for the longest behavior sequence. The model then forms semantic tokens based on feature fields and behavior domains and uses RankMixer blocks for cross-token interaction. A shallow MLP stream complements the deep RankMixer stream, and a group-wise bilinear module fuses their representations. Our final solution ranks ninth on the official leaderboard. Our code is available at https://github.com/PixelCookie-zyf/TAAC-2026-SeRankMixer. --- ### MemoGuard: An Adaptive Runtime for Guarding Against Memory Traps in Communication-Limited Robot Navigation Authors: Rajat Bhattacharjya, Hyeonjong Ju, Sing-Yao Wu, Eli Bozorgzadeh, Nikil Dutt Published: 2026-07-17 Categories: cs.RO, cs.AI, cs.NI, eess.SY arXiv: https://arxiv.org/abs/2607.15589v1 Communication-limited robots in mission-critical scenarios such as disaster inspection and search-and-rescue must make reliable onboard decisions without access to remote operators or high-capacity reasoning services. Episodic memory reuse is an attractive low-cost fallback, but retrieval similarity does not guarantee execution validity, i.e., a retrieved action may match the current context yet be unsafe due to changed topology, insufficient battery margin, or unreliable prior outcomes. We call such high-similarity but execution-invalid episodes memory traps. This creates a safety-efficiency design space where similarity only reuse minimizes fallback cost but can be unsafe, while always invoking local reasoning improves safety at high computational and energy cost. This paper presents MemoGuard, a lightweight adaptive runtime that validates episodic memories against topology, resource, and outcome contracts before reuse, invoking fallback only when validation fails. In a graph-based corridor-inspection simulator, MemoGuard reduces battery safety violations by 76.6% over similarity-only top-1 reuse while reducing fallback calls by 21.4% over always reasoning. On an NVIDIA Jetson AGX Xavier with local llama3.2:3b fallback reasoning, this corresponds to 3.67 s and 36.97 J of avoided fallback-reasoning overhead per trial. We open-source MemoGuard at https://github.com/hetheiin/memoguard. --- ### Rethinking Transfer in Continual Learning: A Replay-Based Realisation Authors: Yang Meng, Zhenya Liu, Zhuokai Zhao, Yuxin Chen Published: 2026-07-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.15587v1 Continual learning studies how deployed language models can continually acquire new tasks without expensive retraining from scratch. Existing methods, whether rehearsal-based (replaying stored past data) or rehearsal-free (regularising or isolating parameters), overwhelmingly target one objective: preventing catastrophic forgetting. Forward transfer, the past helping the future, has meanwhile been pursued almost exclusively through parameter reuse, with no explicit account of when transfer should be expected at all. We begin one step earlier: before designing a transfer mechanism, we ask when transfer should exist at all. We answer with a framework of three measurable conditions: the target task must leave room for improvement beyond its own limited supervision, transferable information must survive continued optimisation, and replay must come from compatible previous tasks. We instantiate this view as Transfer-Selective Replay (TSR), which selects replay data predicted to benefit the incoming task rather than replaying past examples indiscriminately. Selection is guided by a zero-training task signature, while distillation preserves stability on previous tasks. Under the standard continual learning protocol in the low-budget regime, TSR consistently improves forward transfer while maintaining stability, outperforming existing replay baselines across heterogeneous and homogeneous task streams. More broadly, the results argue for treating transfer as a first-class objective of continual learning, to be understood before it is engineered. --- ### Information-Directed Sampling for Causal Bandits Authors: Muhammad Qasim Elahi, Murat Kocaoglu, Mahsa Ghasemi Published: 2026-07-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.15577v2 Causal bandits exploit structural relationships among variables to share information across interventions and accelerate the identification of high-reward decisions. In many applications, however, some variables cannot be directly manipulated, even though they influence the reward and provide useful information about the underlying causal system. We study contextual causal bandits with non-manipulable variables, where context variables are observed before action selection and additional variables are observed after each intervention. Assuming a known causal graph without latent confounding, we adopt a Bayesian formulation in which the conditional probability tables of the observational distribution constitute the unknown parameter. This representation allows observations collected under one intervention to update reward estimates for other interventions through their shared causal mechanisms. We develop causal variants of Thompson Sampling and Information-Directed Sampling (IDS) for this setting. For Thompson Sampling, we establish an entropy-dependent sublinear Bayesian regret bound. For IDS, we derive an entropy-dependent regret bound that explicitly quantifies the additional error introduced by Monte Carlo approximation of the expected regret and information gain; when these quantities are available exactly, the bound recovers the standard sublinear IDS rate. The dependence of these guarantees on the action-set size is worst-case: our model contains the standard multi-armed bandit as a special case. We further provide high-probability confidence bounds for the Monte Carlo estimates. Experiments on synthetic causal bandit tasks show that the proposed methods outperform causal and non-causal baselines by effectively exploiting information shared across interventions. --- ### Information-Directed Sampling for Causal Bandits Authors: Muhammad Qasim Elahi, Murat Kocaoglu, Mahsa Ghasemi Published: 2026-07-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.15577v1 Causal bandits exploit structural relationships among variables to share information across interventions and accelerate the identification of high-reward decisions. In many applications, however, some variables cannot be directly manipulated, even though they influence the reward and provide useful information about the underlying causal system. We study contextual causal bandits with non-manipulable variables, where context variables are observed before action selection and additional variables are observed after each intervention. Assuming a known causal graph without latent confounding, we adopt a Bayesian formulation in which the conditional probability tables of the observational distribution constitute the unknown parameter. This representation allows observations collected under one intervention to update reward estimates for other interventions through their shared causal mechanisms. We develop causal variants of Thompson Sampling and Information-Directed Sampling (IDS) for this setting. For Thompson Sampling, we establish an entropy-dependent sublinear Bayesian regret bound. For IDS, we derive an entropy-dependent regret bound that explicitly quantifies the additional error introduced by Monte Carlo approximation of the expected regret and information gain; when these quantities are available exactly, the bound recovers the standard sublinear IDS rate. We further provide high-probability confidence bounds for the Monte Carlo estimates used by the algorithm. Experiments on several synthetic causal bandit tasks show that the proposed methods outperform causal and non-causal baselines by more effectively exploiting information shared across interventions. --- ### Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models Authors: Rakshanda Hassan Abhinandan, John Galeotti, Deva Ramanan, Gautam Rajendrakumar Gare Published: 2026-07-17 Categories: cs.CV, cs.AI, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2607.15565v2 Where should the question go in a vision-language model (VLM) prompt: before the image or after it? Intuition says before: knowing what is asked should tell the model where to look. Yet across visual question answering benchmarks, question-first prompting consistently underperforms the image-first ordering recommended for frontier VLMs, a phenomenon we term the question-first paradox. We trace this paradox to a conflict between two stages of VLM computation. Logit-lens and attention probes show that question-first prompting steers perception, shifting image patch representations toward question-relevant concepts. But downstream, stranded behind hundreds of image tokens, the question is barely attended by the answer token, which instead commits to image-driven, often wrong answers. Causal attention knockout confirms that the answer reads the question only when it follows the image. This diagnosis yields a training-free fix: question echoing, restating the question on both sides of the image so one copy steers perception while the other is available at answer time. A similar division of labor appears in a fifty-year-old finding on human 'adjunct questions', where repeating a question before and after a passage improves comprehension. Echoing the image as well brings further gains by restoring the whole-image view otherwise lost by a causal decoder. The paradox holds across five open VLMs, costing up to 17.5 group-accuracy points. Echoed prompts recover most of the gap and, on NaturalBench and Winoground, surpass the best single-pass ordering by up to 19 group-accuracy points on Winoground, with no training, fine-tuning, or architecture change. The paradox reveals a tension between steering what a model sees and preserving access to what it was asked; echoing resolves this through prompt design. Project Page: https://rakshanda-cmu.github.io/ask-twice-look-twice/ --- ### Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models Authors: Rakshanda Hassan Abhinandan, John Galeotti, Deva Ramanan, Gautam Rajendrakumar Gare Published: 2026-07-17 Categories: cs.CV, cs.AI, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2607.15565v1 Where should the question go in a vision-language model (VLM) prompt: before the image or after it? Intuition says before: knowing what is asked should tell the model where to look. Yet across visual question answering benchmarks, question-first prompting consistently underperforms the image-first ordering recommended for frontier VLMs, a phenomenon we term the question-first paradox. We trace the paradox to a conflict between two stages of VLM computation. Logit-lens and attention probes show the intuition is half right: a question placed before the image genuinely steers perception, moving image patch representations toward question-relevant concepts. The failure lies downstream. Stranded behind hundreds of image tokens, the question is barely attended by the answer token, which instead commits to image-driven (often wrong) answers; a causal attention knockout confirms that the answer reads the question only when the question follows the image. The diagnosis yields a training-free fix: question echoing, restating the question on both sides of the image so that one copy steers perception while the other is read out at answer time. The same division of labor appears in a fifty-year-old finding on human ``adjunct questions'', where repeating a question before and after a passage aids comprehension more than either position alone. Echoing the image as well brings further gains, restoring the whole-image view a causal decoder otherwise loses. The paradox holds across five open VLMs, costing up to 17.5 group-accuracy points. Echoed prompts close it and surpass the best single-pass ordering on NaturalBench, POPE, Winoground, and open-ended VQAv2, by up to 19 Winoground group-accuracy points, with no training, fine-tuning, or architecture change. The paradox reveals a trade-off between steering perception and preserving question access; echoing resolves it through prompt design alone. --- ### Are All Tokens Necessary for Visual Place Recognition? An Empirical Study of Token Reduction for Efficient Inference Authors: Tong Jin, Yunpeng Liu, Shuyu Hu, Qinghua Zhang, Ruize Han, Song Wang, Feng Lu Published: 2026-07-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15563v1 Recent visual place recognition (VPR) methods based on vision transformers, particularly foundation models, have achieved remarkable recognition performance. However, these models process all visual tokens throughout the entire network, resulting in substantial computational overhead, which hinders their deployment in real-time and resource-constrained scenarios. A natural question thus arises: are all visual tokens necessary for VPR? To answer this question, we present the first systematic benchmark of token reduction for efficient visual place recognition. Our benchmark comprehensively evaluates representative token pruning, token merging, and hybrid pruning-merging methods across multiple state-of-the-art VPR models and diverse benchmark datasets covering urban, suburban, and natural environments. We further investigate token reduction from multiple perspectives, including recognition performance under different reduction configurations, computational complexity, inference speed, qualitative visualization, and deployment efficiency on edge devices. Through extensive experiments and in-depth analysis, our benchmark reveals multiple important characteristics of token reduction in VPR and provides several practical insights into the trade-offs between accuracy and inference efficiency. For example, token reduction can reduce computational cost by up to 29\% and improve throughput by up to 44\%, while incurring less than 1\% degradation in recognition accuracy. Overall, this work establishes a comprehensive foundation for future research on token-efficient VPR and efficient visual retrieval systems. Our codes and models will be available at https://github.com/Tong-Jin01/TokenReduction4VPR --- ### Hard Rules, Soft Preferences: Bridging Reasoning, Learning, and Optimization for Personalized Packing Checklist Generation Authors: Himel Dev, Madhusudan Basak, Tanmoy Sen, Paromita Shome, Bashima Islam Published: 2026-07-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.15562v1 Packing for air travel is recurring and error-prone: the checklist must be personal and context-aware, yet feasible under safety rules, item dependencies, and luggage limits. Existing packing assistants are template-driven and generic, or recommendation-driven but unconstrained, leaving users to manually patch regulatory and capacity violations. We propose a reasoning-guided learning framework with three stages: (1) a symbolic engine that generates a regulation-aware seed checklist with explicit dependency structure, (2) a two-stage preference learner that estimates inclusion and priority utilities from user add and remove actions while mitigating survivorship bias, and (3) a CP-SAT optimizer that selects a compact, compliant subset. The architecture instantiates a general pattern for constrained personalization, applicable wherever hard feasibility coexists with sparse preference signals. On 604 labeled trip scenarios, comprising 29K inclusion labels and 343K pairwise comparisons, the symbolic engine attains 99.7% recall and 0.96 rubric validity, compared with 0.78 to 0.81 for frontier LLMs. Gradient-boosted trees and LambdaMART reach an AUC-ROC of 0.943 and an NDCG@5 of 0.923. CP-SAT attains 100% constraint satisfaction, compared with 28% for greedy selection and 10% for random selection. Deployment in FlyEnJoy, a production iOS travel app, doubled checklist completions and reduced editing and completion time. --- ### Evolutionary Algorithm-Guided LLMs for Physics-Informed Neural Network Design Authors: Xu Yang, Mingyang Yu, Jing Xu, Keqian Li Published: 2026-07-17 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2607.15560v1 Physics-informed neural networks (PINNs) are unusually sensitive to interacting choices of architecture, activation, loss weighting, collocation, optimization, and constraint enforcement. Large language models (LLMs) can propose these choices, but independent recommendations do not accumulate experience from previously trained PINNs. We propose a closed-loop evolutionary algorithm that guides an LLM to generate complete, executable PINN configurations across generations, using measured training outcomes to determine subsequent search decisions. The algorithm maintains an evaluated population and lineage, applies parent-conditioned mutation and crossover, preserves elite and diverse solutions, rejects effective duplicates, and converts parent-relative successes and failures into the next-generation context supplied to the LLM. Every proposed configuration is executed directly under an exact optimizer-step budget. On a one-dimensional multiscale wave equation, two independent ten-generation runs trained 60 PINNs for 600,000 optimizer steps. In both runs, the best configuration appeared in the final generation, with best mean-squared error reduced by 2.97\% and 95.38\% relative to the initial population. The stronger run validated residual connections and increased depth on separate branches, combined them in a later generation, and then refined width and collocation density. It also revealed that low solution error can coexist with a high PDE residual. These results demonstrate the feasibility of evolutionary-algorithm-guided LLMs for PINN design on a controlled PDE while motivating broader, physics-aware evaluation. --- ### SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents Authors: Yanze Wang, Pengfei Yao, Tianyi Sun, Chuanrui Hu, Yan Xiao, Xiaotian Luo, Yunyun Han, Yifan Chen, Jun Sun, Yafeng Deng Published: 2026-07-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.15557v6 Agent skills, SKILL files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Public repositories now host them in large and growing numbers, yet these artifacts are fragmented, redundant, and uneven in quality, and their value in practice is unclear. A core question remains open, namely how to consolidate this open-source SKILL ecosystem into a single usable corpus, and what bounds its benefit on real-world agent tasks. We present SkillCorpus, a framework that aggregates, curates, matches, and evaluates the open skill ecosystem at scale. It filters ~821,000 crawled skills through a multi-stage pipeline into 96,401 skills organised by a 16-class taxonomy and three quality facets (utility, robustness, safety), and pairs them with a fine-tuned retrieval-and-selection stack that matches task-relevant skills. We evaluate end-to-end across three benchmarks (SkillsBench, GDPVal, QwenClawBench), two harnesses, and two open backbones with a frontier robustness check. Integrating SkillCorpus yields consistent gains across all three benchmarks, largest on SkillsBench (+7.5 pp). An operational analysis traces the gains to a coverage boundary and a harness boundary. SkillCorpus is, to our knowledge, the first end-to-end account of when a curated, retrieval-served community corpus improves real agent tasks, and where it does not. The dataset, models, and code are available at https://github.com/EverMind-AI/SkillCorpus. --- ### SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents Authors: Yanze Wang, Pengfei Yao, Tianyi Sun, Chuanrui Hu, Yan Xiao, Xiaotian Luo, Yunyun Han, Yifan Chen, Jun Sun, Yafeng Deng Published: 2026-07-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.15557v5 Agent skills, SKILL files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Public repositories now host them in large and growing numbers, yet these artifacts are fragmented, redundant, and uneven in quality, and their value in practice is unclear. A core question remains open, namely how to consolidate this open-source SKILL ecosystem into a single usable corpus, and what bounds its benefit on real-world agent tasks. We present SkillCorpus, a framework that aggregates, curates, matches, and evaluates the open skill ecosystem at scale. It filters ~821,000 crawled skills through a multi-stage pipeline into 96,401 skills organised by a 16-class taxonomy and three quality facets (utility, robustness, safety), and pairs them with a fine-tuned retrieval-and-selection stack that matches task-relevant skills. We evaluate end-to-end across three benchmarks (SkillsBench, GDPVal, QwenClawBench), two harnesses, and two open backbones with a frontier robustness check. Integrating SkillCorpus yields consistent gains across all three benchmarks, largest on SkillsBench (+7.5 pp). An operational analysis traces the gains to a coverage boundary and a harness boundary. SkillCorpus is, to our knowledge, the first end-to-end account of when a curated, retrieval-served community corpus improves real agent tasks, and where it does not. The dataset, models, and code will be released upon acceptance. --- ### When Can Test-Time Adaptation Help Zero-Shot CT Vision-Language Models? Authors: Ailar Mahdizadeh, Puria Azadi Moghadam, Xiangteng He, Leonid Sigal Published: 2026-07-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15556v1 3D CT vision-language models (VLMs) classify abnormalities from text prompts in a zero-shot manner, enabling cross-institution deployment where labels are scarce and clinical tasks shift faster than supervised models can be retrained. A real CT scan, however, typically contains several co-occurring abnormalities, and the reliability of zero-shot multi-label prediction under distribution shift remains poorly understood. Test-time adaptation (TTA) updates a model on unlabeled target scans without source data or target annotations, yet existing TTA methods target multi-class softmax prediction on natural images or 2D medical segmentation, and none addresses unsupervised multi-label adaptation for zero-shot 3D CT VLMs. We study when TTA helps zero-shot 3D CT VLMs. A controlled diagnostic analysis shows that TTA is conditional: the volumetric input must preserve the encoder's depth structure, and the base representation must transfer to the target cohort, with depth reduction alone lowering internal AUROC by more than 0.12. We then focus on the regime where the base model already separates present from absent abnormalities. We introduce CARVE (Cardinality-Aware Retained-View Entropy), the first TTA method for this setting. CARVE estimates a sample-specific positive-label cardinality $\hat{k}$, optimizes a top-$\hat{k}$ objective to preserve co-occurring abnormalities, and performs memory-efficient multi-view adaptation by scoring weak 3D views without gradients before updating on a retained subset. Across contrastive CT-CLIP and anatomy-aware fVLM, CARVE provides the most consistent improvements across multi-label, three-class, and binary CT tasks when the base model is already discriminative. These results establish multi-label TTA for zero-shot 3D CT VLMs as a distinct problem and CARVE as a cardinality-aware solution. --- ### From Feasibility to Desirability: Plan, Learn, Adapt (PLA) Framework for Personalized On-Device Itinerary Generation Authors: Himel Dev, Tanmoy Sen, Madhusudan Basak, Bashima Islam Published: 2026-07-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.15552v1 Generating personalized trip itineraries is a complex planning task and involves a tension between hard combinatorial feasibility and soft latent desirability. Classical optimization enforces constraints but fails to capture subjective traveler preferences. While learning-based approaches model preferences, they cannot guarantee feasibility. Mobile deployment imposes additional resource constraints on both. To address this, we propose Plan, Learn, Adapt (PLA), a three-stage framework for personalized on-device itinerary generation. The Plan stage builds a heterogeneous ensemble of lightweight planners that produces structurally diverse feasible candidates. From pairwise itinerary comparisons, Learn fits a compact Bradley-Terry reward model that captures emergent schedule properties such as pacing, geographic coherence, and day balance, which per-POI signals miss. Finally, Adapt applies feasibility-preserving local refinement within a device-aware compute budget; every intermediate state is feasible by construction. On 2,519 pairwise human comparisons across more than 100 U.S. cities, the reward-guided ensemble achieves a 67.8% win rate, 11.2 percentage points above the best single planner, with 100% feasibility. Three frontier LLMs, GPT-5, Claude Opus 4.5, and Gemini 3 Pro, achieve 0% feasibility under the same constraints. The reward model generalizes across held-out cities, with a 67.6% mean leave-one-city-out accuracy. In production deployment within FlyEnJoy, PLA increased itinerary completion rates by 91%, with 109.9 ms average on-device latency. --- ### SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction Authors: Xue Yu, Bo Yuan, Kailin Zhao, Pengshuai Yang, Hong Hu, Junlan Feng Published: 2026-07-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.15550v3 Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks because a single erroneous action can lead to irreversible consequences. Existing safety mechanisms are primarily reactive, lacking the ability to assess risks before execution. In this paper, we introduce SeerGuard, a consequence-aware safety framework designed to mitigate these risks through pre-execution instruction-level screening and action-level risk assessment. Specifically, the action-level assessment analyzes agent-proposed actions within current GUI states, anticipating likely outcomes to identify risks before they are executed. To enable these capabilities, we construct a unified safety-augmented world model (SAWM) via multi-task learning, integrating semantic next-state prediction with safety risk assessment. Extensive experiments demonstrate that SeerGuard generalizes effectively across diverse mobile GUI agents. On Qwen3-VL-8B-Instruct, it increases the safety-utility score from $0.191$ to $0.596$ at $ω=0.8$ and reduces the risk-cost score from $0.347$ to $0.135$ at $α=0.8$. Further analyses on our SAWM validate the effectiveness of the instruction-level screening, alongside the capability of action risk assessment and next-state prediction. --- ### SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction Authors: Xue Yu, Bo Yuan, Pengshuai Yang, Kailin Zhao, Hong Hu, Junlan Feng Published: 2026-07-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.15550v1 Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks where a single erroneous action can lead to irreversible consequences. Existing safety mechanisms are primarily reactive, lacking the ability to assess risks before execution. In this paper, we introduce SeerGuard, a consequence-aware safety framework designed to mitigate these risks through pre-execution instruction-level screening and action-level risk assessment. Specifically, the action-level assessment analyzes agent-proposed actions within current GUI states, anticipating likely outcomes to identify risks before they are executed. To enable these capabilities, we construct a unified safety-augmented world model (SAWM) via multi-task learning, integrating semantic next-state prediction with safety risk assessment. Extensive experiments demonstrate that SeerGuard generalizes effectively across diverse mobile GUI agents. On Qwen3-VL-8B-Instruct, it increases the safety-utility score from $0.191$ to $0.596$ at $ω=0.8$ and reduces the risk-cost score from $0.347$ to $0.130$ at $α=0.8$. Further analyses on our SAWM validate the effectiveness of the instruction-level screening, alongside the capability of action risk assessment and next-state prediction. --- ### CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration Authors: Jiayao Gu, Kexin Chu, Peidong Liu, Yue Yang, Lynn Ai, Qi Zhang, Ling Yang, Tianyu Shi Published: 2026-07-17 Categories: cs.MA, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.15545v1 LLM-based agents excel at writing articles, coding and information retrieval. However, they fail to form strong collaborations within the scientific community due to the bidirectional, dynamic nature of the problem and a high demand of decision interpretability. We proposed COWEAVER, a bidirectional, learnable and explainable algorithm to match scientists and form strong collaborations within a human-agent network. COWEAVER matches candidates and requesters through filling capability gaps and filters candidates through a two-stage ranking step. Finally, the model explores newcomers by maintaining uncertainty-aware capability estimates and updating them through requester's feedback. We show that the selection mechanism of combining both exploration (UCB) and greedy of COWEAVER exceeds the greedy-only mechanism - the analytical best solution - on 6 out of the 20 tasks and performed on par with the greedy-only mechanism in terms of selecting the best candidate. We compared COWEAVER baselines in terms of matching quality and efficiency. COWEAVER outperforms baselines on all metrics. --- ### EpiNarrate: Agentic Generation of Grounded Narratives from Epidemiological Scenario Projections Authors: Rituparna Datta, Srini Venkatramanan, Bryan L. Lewis, Yiqi Su, Harry Hochheiser, Lucie Contamin, Parantapa Bhattacharya, Naren Ramakrishnan, Anil Vullikanti Published: 2026-07-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.15544v1 Generation of clear and accessible public health narratives is critical for communicating complex epidemiological projections to policymakers and the general public at large. Such narratives require more than simply reporting numbers: projections must be contextualized and quantitatively grounded across multiple dimensions. Further, projections are often derived from large ensemble datasets which combine intervention assumptions, geographic and demographic strata, outcomes, time horizons, and uncertainty quantiles. However, directly using large language models (LLMs) to summarize and contextualize such data often leads to inconsistencies, omissions, and fragile behavior. We introduce an agentic framework (EpiNarrate) for public health report generation that separates structured numerical reasoning from natural-language generation. The framework first extracts scenario axes and organizes them into a partial-order schema, enabling systematic traversal of the underlying multidimensional space. It then constructs an augmented dataset and derives valid quantitative statements through a comparison grammar that enforces semantic and arithmetic consistency. To balance coverage and non-redundancy, we introduce an interestingness-driven selection mechanism based on maximum-entropy principles. Experiments on the COVID-19 Scenario Modeling Hub demonstrate that our model produces narratives with improved factual grounding and broader coverage of salient epidemiological patterns, while preserving the style of expert-written reports. --- ### ImprovedVBGS: Real-time Continual Variational Bayes Gaussian Splatting Authors: Damani Mguni-Coker Published: 2026-07-17 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.15542v2 On-the-fly reconstruction is a key requirement for many applications in robotics and autonomous navigation. Variational Bayes Gaussian Splatting (VBGS) enables continual learning without replay buffers using Coordinate Ascent Variational Inference (CAVI), but its per-frame iterations over all observed points make it too slow for real-time use with strict memory and latency requirements. We present ImprovedVBGS, an accelerated framework for on-the-fly continual reconstruction. This is achieved primarily through (i) spatially truncated variational inference, and (ii) improved reassignment that uses forwarding, truncation and eliminates wasteful dynamic recompilation. On the NeRF synthetic dataset, we reduce mean per-frame latency from ~84.0 s to ~0.050 s on an RTX 3070 Ti, a 1680x speed-up while maintaining reconstruction quality. We also improve novel-view synthesis quality using an exact renderer with no added training costs. --- ### ImprovedVBGS: Real-time Continual Variational Bayes Gaussian Splatting Authors: Damani Mguni-Coker Published: 2026-07-17 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.15542v1 On-the-fly reconstruction is a key requirement for many applications in robotics and autonomous navigation. Variational Bayes Gaussian Splatting (VBGS) enables continual learning without replay buffers using Coordinate Ascent Variational Inference (CAVI), but its per-frame iterations over all observed points make it too slow for real-time use with strict memory and latency requirements. We present ImprovedVBGS, an accelerated framework for on-the-fly continual reconstruction. This is achieved primarily through (i) spatially truncated variational inference, and (ii) improved reassignment that uses forwarding, truncation and eliminates wasteful dynamic recompilation. On the NeRF synthetic dataset, we reduce mean per-frame latency from ~84.0 s to ~0.050 s on an RTX 3070 Ti, a 1680x speed-up while maintaining reconstruction quality. --- ### E3DGS: Unified Geometric-Photometric Equivariance for 3D Gaussian Splatting via Color-as-Geometry Embedding Authors: Chankyo Kim, Maani Ghaffari Published: 2026-07-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.15536v1 3D Gaussian Splatting (3DGS) captures scenes by coupling explicit geometry (position, covariance) with view-dependent photometry (Spherical Harmonics). However, building $\mathrm{SE}(3)$-equivariant architectures on these primitives presents a fundamental representation bottleneck. Color has been treated as a signal rather than a geometric entity, making it nontrivial to unify symmetry across geometry and appearance as the camera frame changes. While translations are handled by relative coordinates, rotations act heterogeneously across attributes: $μ\mapsto Rμ$, $Σ\mapsto RΣR^\top$, and $f_\ell\mapsto D^\ell(R)f_\ell$. This mismatch complicates strict equivariance, leading existing methods to either discard or flatten SH coefficients, thereby breaking symmetry. We propose a unified solution rooted in representation theory: for SH degrees $\ell\le2$, photometry is algebraically isomorphic to a rank-2 geometric tensor. We prove that the Wigner-$D$ action on these SH coefficients can be exactly reformulated as the conjugation action on $3\times3$ matrices. Leveraging this, we introduce the Unified Matrix Embedding, a lifting that maps all Gaussian attributes into a unified carrier space, $\mathfrak{gl}(3)$. Building on the "Color-as-Geometry" formulation, we present E3DGS, a rigid-body ($\mathrm{SE}(3)$) equivariant architecture that processes 3D Gaussians without Clebsch-Gordan tensor products. Evaluations on object vision and action-conditioned Gaussian world modeling demonstrate that our unified approach yields strong robustness under camera-frame changes and improved data efficiency. --- ### Logic, Optimization, and Artificial Intelligence Authors: J. N. Hooker Published: 2026-07-17 Categories: cs.AI, math.OC arXiv: https://arxiv.org/abs/2607.15532v1 Logic and optimization can, in combination, make valuable contributions to rule-based AI. Logic is the obvious medium for encoding a rule base and drawing inferences from it, while optimization provides a powerful technology for computing inferences. Their combination has taken on new relevance amid a growing concern for transparency in AI. which is important for reproducibility, explainability, trustworthiness, and fairness. Rule-based AI provides a natural solution to transparency that is becoming increasingly practical due to today's highly advanced optimization methods. This article surveys several areas of logic-optimization partnership, including probabilistic logic, Bayesian logic, belief logics and Dempster-Shafer theory, nonmonotonic (default) logic, many-valued logics, and inference of logical formulas from noisy data based on Boolean regression. It shows how to compute projections, the fundamental problem of both logic and optimization, using decision diagrams and logic-based Benders decomposition. It describes the use of postoptimality analysis to explain how conclusions are reached, further enhancing transparency, as well as the role of optimization in answer set programming modulo theories. The paper concludes by suggesting possible future research directions. --- ### On the Role of Normalization in Binary Iterative Hard Thresholding for 1-bit Compressed Sensing Authors: Arya Mazumdar, Prateeti Mukherjee Published: 2026-07-17 Categories: cs.IT, cs.DS, math.ST, stat.ML arXiv: https://arxiv.org/abs/2607.15530v2 Binary Iterative Hard Thresholding (BIHT) is a simple, yet effective, greedy method for recovering a sparse vector from one-bit sign measurements. In its original form, BIHT performs a ``gradient-descent'' step, followed by hard thresholding. A convergence analysis of this algorithm was left open in the introductory work of (Jac+11) and has remained unresolved for over a decade, with subsequent sharp analyses studying a normalized variant instead, that additionally projects every iterate onto the unit sphere. This paper resolves that gap and characterizes when per-iteration normalization is algorithmically necessary. In the noiseless setting, we prove a universal, sample-optimal convergence theorem for the original BIHT algorithm. Specifically, with $\widetilde O(s/ε)$ measurements, a deterministic finite-time iterate has directional error at most $ε$, simultaneously for every $s$-sparse unit vector. This matches the optimal sample dependence achieved by normalized BIHT in prior work. Thus, in the noiseless regime, per-iterate normalization is unnecessary for optimal recovery. Under sign corruptions, we prove a sharp separation. If at most a $τ$ fraction of signs are flipped adversarially, then BIHT, without per-iterate normalization, still reaches the robust error floor at an early iterate with a matching $\widetilde O(s/ε)$ sample complexity rate as its normalized variant. This recovery, however, is not stable. We prove a scalar lower bound showing that any nontrivial corruption pattern, even one that involves only one flipped sign together with one clean sign, forces the iterates to oscillate indefinitely. Consequently, no general last-iterate convergence theorem can hold for BIHT under sign corruptions, while its normalized surrogate provably escapes this instance. --- ### Publicly-Verifiable Certificates for Statistical Algorithms Authors: Michael Ngo, Michael P. Kim Published: 2026-07-17 Categories: cs.LG, cs.CR, cs.DS arXiv: https://arxiv.org/abs/2607.15528v1 Following Goldwasser, Rothblum, Shafer, and Yehudayoff, who defined a framework for interactive proofs of learning (ITCS'21), we initiate the study of non-interactive proofs of learning. We define and study a new notion: Publicly-Verifiable Certificates of Statistical Validity (pvCSVs), which allow for public, distributionally-robust certification that the result of a learning algorithm is valid. In a pvCSV, a learner publishes a hypothesis $h$ and corresponding certificate $π$; then, any user, who holds a user-specific distribution, can read the pair $(h,π)$ and determine efficiently whether the hypothesis is valid according to the user-specific distribution. We construct pvCSVs in the context of Adaptive Statistical Query (SQ) Algorithms. To certify SQ algorithms that makes $k$ adaptive queries, we construct pvCSVs where the sample complexity scales with $O(\log k)$, whereas the sample complexity of the best learning algorithms scale with $\tilde{O}(\sqrt{k})$. More generally, we study proof systems for learning in the SQ model, demonstrating the model's strengths as well as its limitations. --- ### Physics-aware Masked Diffusion-based Flood Simulation for Urban Fisheye Disaster Detection Authors: Sodtavilan Odonchimed, Tsogt Enkhbayar, Oyunzul Munkhtamga, Munkhjargal Gochoo Published: 2026-07-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15527v1 Physical simulations that predict the behavior of urban disasters, such as climate-related flooding, play a crucial role in disaster prevention and the development of anomaly detection models. However, the severe shortage of flood data in real-world environments, combined with the inherent distortions of fisheye lens images, which are used for urban surveillance, has made high-precision simulations challenging. To address this, we propose a new physical simulation system PhysFlood that leverages Diffusion Models to synthesize realistic floods from just a single image captured by a fisheye lens. Our system not only enables simulation from a single image, but also features the ability to freely control and generate diverse flood scenarios by manipulating physically meaningful variables, such as water levels. In our evaluation experiments, we conducted a qualitative human study and demonstrated that the simulation images generated by PhysFlood exhibit both acceptable realism and robustness. --- ### Kolmogorov--Arnold Networks for Small Language Models Authors: Felippe Alves, Renato Vicente Published: 2026-07-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.15525v1 Kolmogorov--Arnold Networks (KANs) replace fixed node activations with learned one-dimensional edge functions, offering an explicit interface for interpretation and a possible alternative to transformer feed-forward networks. We test these claims separately. In a six-layer, 10M-parameter B-spline KAN, we reconstruct all 884,736 feed-forward edges: 87.8\% exceed (NLS>0.1) and 0.4\% are inactive. Pruning the lowest-activity 20--25\% causes negligible loss increase, although structured MLP neuron pruning tolerates comparable sparsity. The audit replicates on BabyLM, but grid-size sweeps show that near-total fPCA compression and high closed-form-fit coverage are properties of the low-capacity grid-2 basis, not universal KAN behavior. For replacement, we evaluate MLP, SwiGLU, grouped Chebyshev, and rational GR-KAN networks on BabyLM. The KAN-family and gated variants improve validation loss over the GELU MLP, but this ordering does not transfer to standardized benchmarks: across ten seeds and 59,875 BLiMP pairs, accuracies span 62.4--63.1\%, EWoK remains at chance, and a (+0.7)-point GR-KAN effect on BLiMP reverses on the supplement. Larger tests are also cautionary: parameter-matched MLPEdge underperforms the MLP on Wikitext-103, and 286M-parameter GR-KAN remains below a SwiGLU ClimbMix baseline after stabilization. Thus, small-basis KANs provide a practical, corpus-transferable interface for auditing learned scalar transformations, but the tested replacements show no consistent benchmark, quality, or latency advantage over strong MLP baselines. --- ### Recursive Harness Self-Improvement Authors: Hyunin Lee, Jinglue Xu, Jeffrey Seely, Donghyun Lee, Matei Zaharia, Yujin Tang Published: 2026-07-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.15524v1 Under model--harness co-evolution, harnesses are not merely inference-time scaffolds but data-generating components whose execution traces can shape future foundation models. This motivates harness-in-the-loop learning: optimizing harnesses for both immediate agent performance and the quality of traces used for future model training. However, continually updating provider-built scaffolds is costly and labor-intensive. We therefore investigate whether optimizing user-constructed harnesses in a task-specific manner can improve execution-trace quality while remaining computationally lightweight and requiring only a few update iterations. To this end, we introduce Recursive Harness Self-Improvement (RHI), which represents the harness as a prompt-level specification of the agent loop and iteratively refines it using pairwise feedback over its own revision history. Across 30 synthetic machine-learning research tasks spanning quantitative finance, robotics, and pharmacy, a few RHI iterations suffice to substantially raise the performance ceiling of low-reasoning-effort agents, exceeding the corresponding maximum-reasoning-effort setting while reducing inference cost by up to 60%. We show that these gains arise primarily from improved task-specific context management through more effective inter-agent information flow rather than longer reasoning traces. Finally, we formalize this behavior as an information-theoretic hypothesis for RHI's implicit optimization objective, suggesting RHI as a practical algorithm for continual learning within the paradigm of model--harness co-evolution. --- ### SLAPBench: Benchmarking Multimodal Large Language Models for Four-Finger SLAP Fingerprint Verification Authors: Bibesh Pyakurel, M. G. Sarwar Murshed Published: 2026-07-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.15517v1 Four-finger SLAP fingerprints are flat live-scan impressions of the index, middle, ring, and little fingers of one hand, used for identity verification in border control and law enforcement. No benchmark has evaluated whether multimodal large language models (MLLMs) can verify identity from SLAP images. We introduce SLAPBench, the first benchmark for MLLM-based four-finger SLAP fingerprint verification, built from NIST SD302b with 7,832 pairs (176 mated, 7,656 non-mated). We evaluate four open-source MLLMs (InternVL3-8B, Qwen2.5-VL-7B, Qwen3-VL-8B, Gemma-3-12B) and the proprietary Claude Opus 4.8 under zero-shot, task-description, and similarity-scoring prompts. Prompting governs verification behavior. Task-description prompting collapses all four open-source models to near-100% False Accept Rate (FAR), and Gemma-3-12B collapses under zero-shot as well; Claude Opus 4.8 alone resists collapse under both binary prompts, giving the best binary result (FAR = 20.2%). Similarity scoring removes collapse across the open-source models and exposes wide capability gaps: Claude reaches AUC = 0.953 and Gemma-3-12B 0.837, while InternVL3-8B is inverted (AUC = 0.590) and Qwen2.5-VL-7B near random (0.567). Qwen3-VL-8B attains perfect separation (AUC = 1.000), which we treat as a diagnostic rather than as capability: SD302b holds one SLAP capture per finger position, so mated pairs are cross-resolution. A matched-resolution control leaves the perfect score intact, ruling out the resolution shortcut; what cannot be excluded within SD302b is near-duplicate detection, since a mated pair is one capture rendered twice. A fairness probe over gender, race, and age suggests disparity grows as discrimination weakens. SLAPBench establishes the first SLAP-specific MLLM baseline and shows that prompting governs collapse while model capability governs discrimination. --- ### Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Authors: Yan Song Published: 2026-07-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.15516v1 Production LLM deployments combine two cost-reduction primitives: prompt caching (a discounted rate for re-used token prefixes) and prompt compression (fewer tokens sent). The compression literature has standardized on query-aware methods that produce a different compressed prefix per query, mechanically invalidating the prefix-strict cache on every call. We characterize this cost empirically on Anthropic's Sonnet 4.6 API and find caching is far from the rho=1.0 ideal the literature assumes: Sonnet's cache has a two-tier architecture with a sharp threshold near 3,500 tokens, below which the hit rate plateaus at rho~0.83 across 30-call sessions. Our cost model predicts, and experiments confirm, that under realistic rho, query-aware compression beats naive caching at high compression ratios (r>=6). We propose Cache-Aware Prompt Compression (CAPC), pairing query-agnostic compression with explicit cache_control plus a tier-preserving ratio bound that prevents over-compression from pushing the cached prefix into the hot tier. CAPC is the cheapest strategy in 16/16 configurations on LongBench-v2, with mean savings of 49% over cache-only, 64% over query-aware compression, and 90% over vanilla, at quality within 0.05 of the uncompressed baseline. We validate CAPC on three production workloads: an enterprise tool-using assistant with a 94k-token schema prefix (51.7% cost reduction at r=3); a graphify knowledge-graph RAG pipeline across two codebases (9.3x vs cache-all on FastAPI, 2.4x on httpx); and the public tau-bench retail benchmark (50 tasks), where CAPC is the cheapest of four strategies with reward exactly equal to vanilla (both 36/50, p=1.00) while query-aware compression is the most expensive at +40.1% over vanilla -- the first production confirmation of the crossover model's negative-ROI prediction on a public benchmark. --- ### LaSeD: Label-Semantic Self-Distillation for Visual-Only Surgical Phase Recognition Authors: Ye Tao, Claudia Scherl, Sara Monji-Azad Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.18971v1 Surgical phase recognition maps each video frame to a clinically meaningful workflow phase, supporting context-aware assistance, documentation, and postoperative analysis. Most methods treat phase annotations only as class IDs, whereas recent surgical vision-language models often require additional video--text data, captions, or instruction tuning. We propose \emph{LaSeD}, a label-semantic self-distillation framework that uses phase names as privileged training-time context while retaining visual-only deployment without a ground-truth phase-name hint. LaSeD initializes a frozen teacher and a student from the same pretrained VLM checkpoint. The teacher receives the frame, a fixed task prompt, and the ground-truth phase-name hint; the student receives the same frame and prompt without the hint, and only its visual encoder is optimized. Training combines hard phase-token supervision with feature-level distillation from cached teacher representations. At inference, the teacher and hint are removed, and the student predicts one of the seven Cholec80 phases through constrained digit-token logits without an additional classifier head. On the Cholec80 evaluation split, LaSeD achieves 86.20\% accuracy, 77.75\% macro recall, 78.13\% macro precision, and 64.15\% macro Jaccard. Under the identical protocol, it improves a visual-only Qwen3-VL-4B baseline by 9.45, 9.42, 11.93, and 12.22 percentage points, respectively. Visual-only means that the image is the only sample-specific inference input, while all frames share the same fixed task prompt. These results suggest that phase names provide a useful low-cost signal for adapting VLMs to surgical workflow analysis. (The code will be published soon.) --- ### The Automaton Underneath: The Additive Input Pathway Is a Parasitic Attractor for State Tracking in Householder Linear RNN Authors: Gunner Levi Howe Published: 2026-07-16 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2609.18966v1 Linear RNNs with input-dependent Householder-product transitions (DeltaNet/DeltaProduct-class) can provably represent hard state-tracking automata, yet trained models fail to length-generalize -- a gap recent work attributes to optimization, without a causal account. We give one, in a pre-registered, within-architecture causal ablation: the same model with one term deleted -- the additive input injection $b_t = W_b e_t$. With $b_t$, models fit length 32 and collapse out-of-distribution on parity, $S_4$, $A_5$, and non-solvable $S_5$ word problems (0.20 at position 512 on $S_5$). Without it -- input acting only through the orthogonal transitions -- the same architecture learns the exact automaton: median accuracy 1.00 at 16x the training length, at every width admitted by a representation law we state and test: the minimal number of Householder factors per token equals the maximal reflection length of the task's generators in the format-pinned representation (parity 1, $S_4$ 3, $A_5$ and $S_5$ 4); below it, nothing fits. The contrast with DeltaProduct's $S_4$/$A_5$ at $n_h{=}2$ (group-element classification, $SO(3)$ realization) shows the law is representation-relative: task format is a hidden variable in state-tracking benchmarks. Two pre-registered arms locate the mechanism. (i) Initialized at a verified-exact solution with $W_b{=}0$, Adam grows the additive path and pulls the model off the exact solution; $-b$ controls stay at 1.00. (ii) Our registered prediction that the fit routes through $b_t$ fired its kill criterion: all 49 fitting seeds retain in-domain fit under $W_b{:=}0$ -- and at law-minimal width, zeroing $W_b$ at inference restores exact generalization (parity 5/5, $S_5$ 5/5, $S_4$ 4/5, $A_5$ 4/5). The additive pathway is parasitic: it destabilizes, then conceals, a correctly learned automaton. All 202 runs pre-registered; all numbers regenerate from artifacts. --- ### BadQubits: An LLM-Based Framework for Static Pre-Execution Detection of Structurally Harmful Quantum Circuits Authors: Justin Woodring, Lamine Noureddine, Aisha Ali-Gombe Published: 2026-07-16 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.18965v1 This paper presents BadQubits, an LLM-based framework for static pre-execution detection of structurally harmful OpenQASM 2.0 circuits. The framework targets physical-execution-layer threats by analyzing submitted circuits prior to runtime, where dynamic inspection is constrained by measurement irreversibility and the exponential cost of classical quantum-state simulation. We evaluate four code-understanding LLM architectures on a dataset of 1,500 circuits consisting of 1,000 benign programs from MQTBench(33) and 500 synthetic attack circuits derived from three documented physical-layer threat primitives. Our fine-tuned Qwen Coder 2.5 7B model achieves 92.67% classification accuracy and 96.1% harmful-circuit recall. Two of the four evaluated base models fail to generalize under constrained LoRA fine-tuning, indicating that architecture-aware model selection is a necessary design consideration rather than a minor tuning choice. To characterize what the detector has learned, we compare it against a bag-of-gates CNN under progressive confound removal and adversarial syntactic perturbation. The CNN's harmful-circuit recall drops from 100% to 17%, while the fine-tuned LLM decreases only from 96.1% to 91.2%. We attribute this gap to the sequential structure retained in token-level LLM inputs but discarded by histogram-based baselines. A correlation analysis further shows that model decisions track threat-defining features, specifically SWAP density and measurement timing, rather than generator-specific artifacts such as register naming. --- ### MechSparse: Mechanism-Guided Sparse PEFT Selection Is Task-Shaped Authors: Son Ha Xuan, Phat T. Tran-Truong, Xuan-Bach Le Published: 2026-07-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.18961v1 Mechanistic interpretability identifies sparse subsets of heads and MLP blocks that carry specific behaviors. We ask whether such causal signals can guide where to place a small PEFT budget more effectively than the cheap heuristics practitioners already use. \method{} scores attention heads and MLP blocks by normalized activation-patching recovery on clean/corrupted probes and trains LoRA/QLoRA only on the selected sites; \methodc{} adds bounded credit for small within-layer joint subsets. We compare against random, magnitude, activation-norm, and gradient/Fisher on Ministral-8B/NF4 in three cells: Swahili span-JSON information extraction (IE) at $b{=}0.25\%$ and $1.0\%$, and English$\to$Swahili machine translation (MT) at $b{=}1.0\%$. The causal selectors never win the primary metric. On the headline IE cell (3 seeds, paired-bootstrap CIs over $600$ predictions), \methodc{} beats random by $+0.079$ span+type F1 and gradient/Fisher by $+0.174$, but trails activation-norm by $0.028$, with the smallest cross-seed std ($\pm 0.003$). On MT all four selectors lie within $0.30$ BLEU and every paired CI includes zero. A schema-versus-span decomposition explains the IE gap: activation-norm captures the rigid JSON routine, while causal scores track content-sensitive sites. We distill a preliminary diagnostic -- prefer activation-norm when output structure dominates, treat causal selectors as a hypothesis for content-dominated tasks -- and release masks, scores, predictions, and evaluation files for direct replay. --- ### Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks Authors: Arth Singh Published: 2026-07-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.17552v1 Moral-reward RL can make language-model agents more cooperative, but whether that alignment survives adversarial persona pressure is unknown. Such attacks are realistic: retrieved context, tool outputs, or multi-turn framing can all inject role instructions that compete with the agent's moral objective. We red-team morally trained Gemma-2-27B/9B and Llama-3.1-8B agents with five persona attacks, then probe causality with noise-reward controls, adversarial PPO, representation analysis, steering, and head ablations. At 27B, moral RL cuts mean adversarial degradation by 5.2x but costs ~11pp ETHICS accuracy; across 205 scenarios and 5 seeds, reasoning-level moral reward yields 5.8x robustness while a matched random reward yields none. The training also reshapes representation geometry (mean CKA 0.82/0.83 vs. 0.98 for noise), moves peak attack processing 8 layers earlier, and exposes a rank-1 L21 direction that recovers 83% of full PPO's average robustness. One failure mode survives all of this. Against Fiction role-play, L21 steering recovers only 29% of the gap, and head ablation finds 38 compliance heads competing with 25 alignment heads. Moral RL thus builds robustness that is partly linear and partly circuit-distributed, transferable through activation steering, yet still beaten by named-character role-play. --- ### No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback Authors: Saad Aamir, Muhammad Awais Bin Adil Published: 2026-07-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.17550v1 Language models frequently abandon correct answers when users push back. We study this in two small instruction-tuned models from different families, Qwen2.5-1.5B and Llama-3.2-1B, over TriviaQA: the model answers, is challenged with one of four scripted pushback styles, and answers again. Conditioned on an initially correct answer, the models flip to a wrong answer in 41.8% and 43.1% of episodes. Which pressure works is a property of the model, not the pressure: the same within-question paired comparison (bare doubt vs. emotional appeal), specified in advance, is Bonferroni-significant in opposite directions across families (Qwen: bare doubt > emotional, OR 2.5, p=.040; Llama: emotional > bare doubt, OR 4.0, p=.001). Failure mode is also model-dependent: Llama abandons answers without recommitting at six times Qwen's rate (8.2% vs. 1.4%). Identical pushback repairs initially wrong answers only ~13% of the time; pushback is net epistemically destructive. We then ask whether capitulation is linearly decodable from the pre-response residual stream, a prerequisite for steering-vector interventions at that locus. A naive difference-in-means probe appears to succeed (in-sample AUROC 0.81/0.71), but a validation protocol combining question-level cross-validation, shuffled-label nulls, and a known-direction positive control shows the signal is overfitting: the best cross-validated AUROC is 0.582 in Qwen and 0.548 in Llama, both near or below their permutation thresholds and far under a pre-registered usability bar of 0.70, while the identical pipeline recovers a pushback-presence control direction at AUROC 1.000 in both. We further quantify a measurement hazard: substring grading underestimates capitulation by 18-24 percentage points. Code, prompts, transcripts, and analysis are released. --- ### Talking Head Synthesis with Facial Landmark Guidance via 3D Gaussian Splatting Authors: Ziheng Yang, Yinfeng Yu, Yongming Li Published: 2026-07-16 Categories: cs.AI, eess.SP arXiv: https://arxiv.org/abs/2609.17422v1 Audio-driven digital human generation plays an important role in virtual communication, immersive interaction, and media production. With the development of Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), recent talking-head systems have obtained more faithful 3D facial geometry and appearance modeling. A remaining difficulty is that speech features mainly describe temporal acoustic patterns rather than explicit facial layouts. As a result, directly driving 3D facial deformation with audio may produce inaccurate mouth motion, weak expression details, and local artifacts. To address this issue, we propose a facial-keypoint-guided spatial enhancement module. The predicted landmarks provide structural cues for selecting and enriching spatial points around expression-sensitive facial regions. We further introduce a global landmark compensation mechanism, where the full set of keypoints is encoded into a conditioning vector to refine 3DGS attributes. This compensation supplies whole-face structural information to the underlying shape representation. Experiments under self-driven and cross-driven settings show that the proposed method improves visual quality, facial realism, and lip synchronization. --- ### Transformer-Based Token Fusion and Dynamic Graph Planning for Audio-Visual Navigation Authors: Shaohang Wu, Yinfeng Yu Published: 2026-07-16 Categories: cs.AI, eess.SP arXiv: https://arxiv.org/abs/2609.17421v1 Audio-Visual Navigation (AVN) requires an agent to localize and navigate toward a continuously vocalizing target relying solely on visual observations and acoustic cues. Currently, systems lack the ability to adaptively correct and replan when faced with incomplete or misleading visual perception. Furthermore, relying on physical collisions to compensate for missing visual information results in inefficient and unsafe navigation, whereas existing methods are overly dependent on passive visual perception. To address these issues, we propose the Transformer-based Token Fusion and Dynamic Graph Planning (TDGP) model, which incorporates high-level perception layers and leverages the Transformer model to fuse multimodal cues for precise local planning. Next, a low-level planning layer is designed that uses physical collision penalties to remove edges that collide with the map in real time and apply corresponding penalties, forcing the agent to automatically re-plan to compensate for the lack of visual information. Experiments show that our TDGP model outperforms baseline models on the Replica and Matterport3D (MP3D) datasets, and that the model's sound enhancement strategy significantly improves generalization in unheard acoustic scenarios. --- ### PhysPlan: Grounded Physical State Reasoning and Graph-Guided Optimization for Physically Plausible Video Generation Authors: Minh-Loi Nguyen, Xuan-Vu Le, Trung-Nghia Le, Tam V. Nguyen, Minh-Triet Tran, Thanh-Toan Do Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.13006v2 Video diffusion models (VDMs) synthesize photorealistic content, yet they often fail to follow the course that a physical phenomenon should take within a given scene. Recent training-free methods let a vision-language model (VLM) plan the phenomenon and guide a frozen VDM toward the plan; however, such plans are derived from the prompt and consumed as whole keyframes or trajectories, which leaves unspecified where the consequences land in the observed scene and turns incidental visual details into optimization targets. We observe that a phenomenon specified in words unfolds as sparse, local changes to the physical state of the observed scene. Building on this observation, we present PhysPlan, a training-free image-to-video framework that represents a phenomenon as a grounded state graph and uses this graph to decide what, where, and when the guidance constrains. Grounded Physical State Reasoning decomposes the phenomenon into physical deltas, each stating which objects change, to what state, and by which physical rule, and translates each delta into graph edits, verified by deterministic checks, that leave all other objects unchanged. Graph-Guided Test-Time Optimization renders a keyframe for each state, measures the denoised estimates only along the properties selected by the edits, and concentrates the update on the edited objects. On PhyGenBench and Physics-IQ, PhysPlan raises its base model from 0.52 to 0.77 and from 27.1 to 38.2, surpassing the strongest prior I2V method (0.60 and 34.6), and lowers FVD by over 20%. Project page: https://physplan.github.io --- ### Novel hybrid protein scaffold gap filling using weighted machine learning ensemble, beam search, and mass-constrained reranking Authors: Tahmid Enam Shrestha, Md. Manzurul Hasan, Md. Rafiqul Islam Published: 2026-07-16 Categories: q-bio.BM, cs.LG arXiv: https://arxiv.org/abs/2609.05436v1 Protein scaffold gap filling is an important computational task in protein sequence reconstruction, where missing amino acid regions must be inferred from incomplete scaffold information. This study proposes a hybrid machine learning and mass constrained reranking framework for protein scaffold gap filling under known-gap-size and known-gapmass settings. Homologous protein sequences from MabCampath, P5A proteoform, and carbonic anhydrase 2 were used to generate masked 11-mer residue-level samples and fullgap evaluation cases. The residue prediction task was formulated as a 20-class amino acid classification problem using first-, middle-, and last-position masking. Multiple classical machine learning models were trained using raw encoded, row-average, and SVD-reduced features, and the strongest models were combined through a validation-accuracy-weighted ensemble. For known-size gap reconstruction, beam search was used to generate complete missing peptide sequences from residue-level probability estimates. For known-mass reconstruction, mass-constrained homologous candidate retrieval was combined with hybrid reranking based on mass validity, homologous frequency, context support, ensemble likelihood, mass error, and length penalty. The proposed framework achieved 95.41% residue-level validation accuracy, 87.50% known-size exact-match accuracy, and 100% top-5 recovery on seven CAH2 known-mass benchmark cases. These results indicate that the proposed framework can effectively reconstruct missing protein regions by integrating local sequence learning, homologous evidence, peptide mass constraints, and biochemical validation. --- ### Refusal Is Not Robustness: Auditing Confident Fabrication in Large Language Models on a Provably Uninformative Clinical Pain Speech Transcript Authors: Sagnik De, Sreenija Pavuluri Published: 2026-07-16 Categories: cs.AI, cs.ET, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2608.26167v1 Hallucination and abstention benchmarks rarely establish that a model could not have known the correct answer, making it difficult to distinguish appropriate abstention from an unsupported prediction. Seven large language models were evaluated on the TAME Pain speech corpus. Participants read phonetically balanced Harvard Sentences while one hand was immersed in cold or warm water and reported pain only during periodic pain statements. This protocol generated 5,750 no signal Harvard Sentence utterances whose transcripts contained no lexical pain information and 1,294 signal pain statement utterances in which the pain rating was explicitly spoken. In the no signal arm, pain was recoverable from acoustic features (AUC 0.622, 95% CI 0.553 to 0.662), whereas transcript based prediction was near chance (AUC 0.489, 95% CI 0.418 to 0.504). Because automatic speech recognition removes the acoustic pain cues, any pain score inferred solely from the transcript is unsupported by the available evidence. Under cooperative prompting, six models abstained on nearly all no signal transcripts, correctly extracted spoken pain ratings in the positive control task with accuracies ranging from 0.939 to 1.00, and maintained an expected calibration error of at most 0.100. Under authority framed prompts, abstention became prompt dependent, with the same model ranging from 0.18 to 1.00 across equivalent prompt phrasings. Most models produced low confidence estimates when forced to answer, whereas Gemini 2.5 Flash and Llama 3.1 8B consistently generated confident pain scores with confident fabrication rates of 0.53 and 0.76, compared with at most 0.15 for all other models. No significant demographic effects were observed in forced responses, with all $p$ values greater than or equal to 0.20. --- ### PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks Authors: Bowen Jiang, Yuan Yuan, Zhuoqun Hao, Yuchen Liu, Maohao Shen, Sihao Chen, Gregory Wornell, Chris Callison-Burch, Lyle Ungar, Dan Roth, Qi Guo, Xiangjun Fan et al. Published: 2026-07-16 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2608.21381v1 Personal intelligence is becoming a central frontier for user-facing AI agents. To be helpful in everyday life, agents must understand users across the digital contexts where their preferences, intents, habits, social relationships, and needs unfold over time. Today's systems can personalize within individual apps or tasks, but personal intelligence as a whole remains under-measured: how agents build cross-context user understanding, support steerable recommendation systems, act proactively across platforms, and avoid over-personalization. We introduce PersonaMem-v3, a real-world-grounded benchmark and evaluation harness for omni-platform personal intelligence. PersonaMem-v3 is seeded from more than one million anonymized real-world engagement histories, most of which are implicit signals, and uses them to construct time-indexed user digital worlds across social media, chatbot, calendar, and AI-companion with preference evolvement over time. The benchmark brings personalization, LLM-powered recommendation, proactiveness, agentic tool use, and geo-temporal reasoning into one framework, anchored in psychology, social-linguistics, and user-behavior theories. It evaluates whether AI agents can infer holistic user understanding from cross-platform evidence, personalize responses, rerank recommendations on social media, follow user steering through natural language, and hold back when personalization would be inappropriate, repetitive, outdated, or unnecessary. PersonaMem-v3 points toward LLM-powered personal intelligent agents that work with existing scalable recommendation infrastructure while making personalization more interactive, agentic, and aligned with how real users experience their digital lives. --- ### RoboShape: Information-Theoretic Point Cloud Representations for Privacy-Aware Robot Perception Authors: Oguzhan Baser, Mirac Sozen, Kaan Kale, Sandeep Chinchali, Sriram Vishwanath Published: 2026-07-16 Categories: cs.RO, cs.AI, cs.CV, cs.IT arXiv: https://arxiv.org/abs/2608.21380v1 With the increased adoption of robotic agents operating in human environments by scanning and sharing 3D representations (e.g., for fleet learning, cloud-based planning, or collaborative mapping), collected point clouds reveal not just the objects in a scene but also sensitive spatial context, such as room function or information that occupants never consented to disclose. Traditional point cloud encoders offer no principled control over this: either all is preserved, or none. Hence, we introduce RoboShape, an information theory guided compression head following the frozen {\tt Sonata} encoder. We project voxel-level embeddings using the Donsker-Varadhan formulation of mutual information (MI). Specifically, we maximize the MI between embeddings and object-level understanding while minimizing it for private attributes. RoboShape leads to 87.5\% smaller embeddings that retain 98.7\% of object classification utility while collapsing sensitive attribute predictions by 39.3\% across the three real-world indoor LiDAR datasets. Its privacy-preserving embeddings are cheaper to transmit over the network or to train a model for any downstream tasks. We release the RoboShape codebase to give the robotics community a practical, encoder-agnostic tool for building perception pipelines that are compact, privacy-aware, and deployment-ready. --- ### Global Index on Responsible AI 2026 : Conceptual Framework and Methodology Authors: Fola Adeleke, Rachel Adams, Ayantola Alayande, Daniela Benavente, Ana Florido, Nicolás Grossman, Leah Junck Published: 2026-07-16 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.18122v1 This report presents the methodology of the Global Index on Responsible AI (GIRAI), 2nd Edition. This edition refines the 1st Edition by strengthening the distinction between framework existence and implementation, restructuring dimensions from three to five thematic areas, introducing more granular variables for framework quality, and applying a multi-stage review and validation process. An independent statistical pre-audit was conducted to assess the coherence and robustness of the framework. GIRAI assesses responsible AI governance across five dimensions: Inclusion and Diversity, Ethics and Sustainability, Labour and Skills, Trust and Safety, and Use of AI in Public Service. Each dimension has a number of indicators (38 in total), organised into three pillars, namely AI Policy (17 indicators on government frameworks and implementation, assessed through primary data), CSO Engagement (5 indicators, primary data), and Enabling Conditions (15 indicators on the structural factors shaping responsible AI governance, assessed through secondary data), and a government Use of Unacceptable Risk AI (URAI) indicator (primary data), applied separately as an accountability penalty to the final score. Data was collected by 135 country-level researchers through a structured global survey, complemented by secondary datasets. The count, scope, enforceability, thematic coverage, and implementation levels of the data points are coded into numerical variables, normalised to a scale of 100, aggregated through pillar weights of 60% (AI policy), 10% (CSO Engagement), and 30% (Enabling conditions). A deduction penalty is applied for countries with evidence of URAI. This documentation enables systematic cross-national comparison, supporting policymakers, civil society, and AI developers to identify where commitments are translating into enforceable protections and where critical gaps remain. --- ### Which CS1 Students Will Fail? Identifying Digital Markers from Learning Analytics in Computer Systems and Architecture Using Weighted Academic Momentum and Interaction Logs Authors: Lighton Phiri, Mutune Chaibela, Ivy Chisha, David Pungwa, Danny Siabbaba, Bydon Simukoko Published: 2026-07-16 Categories: cs.CY, cs.LG arXiv: https://arxiv.org/abs/2608.16914v1 Digital learning platforms generate rich behavioural traces (digital markers) that offer the potential to identify struggling students early. This paper investigates whether a combination of traditional and digital markers can predict failure in a first-year CS1 course (Computer Systems and Architecture) with sufficient recall to enable timely intervention. Using data from four cohorts (2017-2021, N=284) at a large public university in sub-Saharan Africa, we conducted a mixed-methods stakeholder elicitation to identify ten candidate factors. These were operationalised into a comprehensive feature set spanning demographics, self-reported surveys, Moodle interaction logs, and continuous assessment scores. A systematic ablation study using logistic regression with 5-fold cross-validation and SMOTE+ENN resampling revealed that the most predictive feature subset was Base + Demo + LMS: weighted academic momentum (M = 0.1Q1 + 0.15Q2 + 0.2Q3 + 0.55T1), basic demographics (gender, sponsorship, COVID-19 cohort), and a binary indicator of any LMS activity. On a held-out test set, logistic regression achieved 74.7% accuracy, 0.742 macro F1, and an AUC of 0.800. At the default threshold of 0.5, the model identified 87% of failing students (recall = 0.87) with a 41% false positive rate. SHAP analysis confirmed that weighted academic momentum is the strongest predictor, followed by its interaction with LMS engagement. These results demonstrate that simple digital markers can power a practical early-warning system by the fifth week of the semester. Our main contributions are: (1) a multi-source dataset and a stakeholder-guided methodology; (2) an ablation study quantifying feature group contributions; and (3) an interpretable, high-recall model ready for deployment. --- ### Learning Agent Execution for KV-Cache Management in Agentic Serving Authors: Rui Zhang, Chaeeun Kim, Shaoting Feng, Kuntai Du, Yuhan Liu, Yi Zhong, Cheng-Wei Ching, Junchen Jiang, Liting Hu Published: 2026-07-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.14624v1 Multi-agent LLM systems have emerged as an important deployment paradigm for AI services, where each user request is decomposed into a sequence of specialized agents. Across these workflows, every agent repeatedly executes a fixed context consisting of system prompts, tool definitions, and few-shot examples, creating substantial opportunities for KV-cache reuse. Existing LLM serving systems, however, manage KV-cache reactively using prefix caching and recency-based replacement, causing reusable agent contexts to be evicted before their next invocation and forcing repeated recomputation. We present CacheScout, an agent-aware KV-cache runtime layer for multi-agent LLM serving. The key insight is that future KV-cache reuse is governed by agent execution semantics rather than cache recency alone. CacheScout captures these semantics by learning agent execution transitions online, without requiring predefined workflow graphs or offline training, and uses the learned execution model to guide both cache eviction and proactive prefetching while leaving the serving critical path unchanged. We implement CacheScout on top of vLLM. Across representative real-world multi-agent workloads, CacheScout improves KV-cache hit rate by 10-18 percentage points, reduces mean TTFT by 18-45%, lowers mean per-turn latency by 29-38%, and increases peak throughput by up to 57%. These benefits also generalize to larger models, reducing TTFT by up to 54% while sustaining 37% higher throughput. ---