# Research Papers — 2026-08 · bundle page 221 of 240 > Full-text markdown of papers #11001–11050 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/221 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/220.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/222.md) ### Grounding Agentic VLMs with Dedicated Segmentation for Fine-Grained Vehicle Damage Assessment Authors: Vishwajeet Shivaji Hogale, Anjali Pai, Nitya Ravi Published: 2026-08-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.02470v1 Vision-language models (VLMs) are increasingly deployed as reasoning agents in real-world visual assessment pipelines, yet their spatial grounding remains unreliable for fine-grained, visually ambiguous targets. We study this gap in the context of automated vehicle damage assessment, where fine-grained defects such as scratches and hairline cracks occupy few pixels, produce weak gradient signal, and are easily confused with reflections and surface texture. We show that a state-of-the-art VLM (Qwen-VL) achieves strong semantic classification accuracy (87.3%) on this task but is systematically ungrounded at the spatial level: it hallucinates damage in reflective regions, misses elongated scratches entirely, and produces spatially inconsistent outputs when prompted for localization. We propose TinyDamage, a hybrid architecture that delegates spatial grounding to a dedicated multi-task segmentation model while reserving the VLM for semantic reasoning and report generation. On the segmentation side, we find that the choice of loss function has an outsized and underexplored effect on tiny-object grounding: focal loss, widely used for class imbalance, collapses tiny-damage detection to zero, while a supervised contrastive objective measurably improves damage/background separability. We integrate the segmentation model into a 7-node LangGraph agent pipeline that grounds every VLM generation step in the segmentation output, and show that this grounding reduces the report hallucination rate from 92% (text-only) and 78% (image-only) to 31% in a controlled evaluation on 100 human-verified reports. We introduce DET_l, a permissive per-category detection metric for evaluating tiny-object grounding under class imbalance, and report latency and reliability characteristics of the deployed pipeline. --- ### Calibrated Similarity and Graph Clustering for Open-Set Animal Re-Identification Authors: Mohamed ElBassat, Seifeldin Elkerdany, Mohamed ElBialy, Gamal Abouelhamd, Jana Ghoneim, Assem Elkady, Mohamed Elboraay, Nelly Semenova Published: 2026-08-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.02469v1 AnimalCLEF26 addresses discovery-oriented animal re-identification, where systems must both attach query images to known individuals and discover unseen individuals by clustering them correctly. We present a similarity-to-clustering pipeline for this setting across Eurasian lynx, fire salamander, loggerhead sea turtle, and Texas horned lizard images. The method first isolates the target specimen using segmentation and then applies lightweight species-specific preprocessing for lynx, sea turtle, and salamander images to enhance identity-relevant visual cues, while Texas horned lizard images are used after segmentation only. Pairwise similarities are then estimated with WildFusion by calibrating and combining a MiewID global descriptor with two local matching branches, ALIKED + LightGlue and DISK + LightGlue. The resulting query-query similarities are refined and converted into identity clusters using graph-based clustering, while query-database similarities are used to attach confident samples to known identities. We evaluate training-free and fine-tuned MiewID variants, including Dynamic ArcFace and SphereFace2-Focal adaptations, and combine them in the final ensemble. Our selected ensemble substantially improves on the WildFusion baseline, achieving the best public ARI of 0.72124 and a private ARI of 0.70393, while a simpler preprocessing-before-calibration variant achieves the best private ARI of 0.71087. These results indicate that calibrated global-local fusion with species-aware preprocessing choices is effective for open-set wildlife re-identification under challenging field conditions and visual variation. The implementation code is available on GitHub. --- ### ISRS-DETR: Detection-Guided Click Propagation for Remote Sensing Interactive Segmentation Authors: Thanh Duc Pham, Anh Nguyen, Duong Duc Hieu, Minh-Tan Pham Published: 2026-08-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.02468v1 Interactive segmentation reduces the prohibitive cost of pixel-level annotation by allowing users to delineate objects with a few clicks. However, applying this paradigm directly to remote sensing imagery is non-trivial: ultra-high resolutions, small object sizes, and sparse spatial distributions all degrade segmentation quality. Recent work has addressed the resolution barrier and achieved competitive results in interactive segmentation for remote sensing (ISRS). However, they treat all instances of a class within an image as a single objective target. Consequently, interactions spent on one object contribute nothing to its same-class neighbours, and satisfactory masks may demand up to 40 clicks per image, hindering the practicality of these frameworks. We observe that remote sensing scenes exhibit markedly strong inter-object correlation, meaning a single clicked object is highly informative about the rest of its category. Building on this, we propose ISRS-DETR, a detection-guided interactive segmentation framework that injects object-level evidence into both training and inference. Our ISRS-DETR employs an RF-DETR decoder with the interactive segmentation backbone to localise co-occurring same-class objects, and introduces a Dynamic Top-K Click Selection strategy that retains only reliable proposals and converts each into a simulated click, so one user interaction propagates across an entire class. Experiments on three standard remote sensing benchmarks show that ISRS-DETR achieves state-of-the-art accuracy while substantially reducing Number of Clicks per Image (NoC-I). All codes and data splits will be released for reproducibility upon acceptance. --- ### Real-Time Detection and Repair of LLM Agent Failures Authors: Sunny Dubey Published: 2026-08-03 Categories: cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2608.02464v1 LLM agents fail mid-episode -- they loop, cascade tool errors, drift off goal, fabricate results, or silently absorb corrupted content -- and the standard remedy, judging every step with a second LLM, costs more than the agent itself. We ask how much detection is achievable from observable step telemetry alone, using monitors costing microseconds per step and trained only on healthy runs. On 2,823 committed agent episodes across three frameworks, three local models (qwen2.5 7b/3b, llama3.1 8b) and a commercial API (gemini-2.5-flash), a one-class echo-state-network ensemble with CUSUM alarms detects 0.71 of failures at a 5% false-alarm budget (AUROC 0.872). Its advantage over a memoryless baseline is a monotone function of post-onset horizon (+0.09 at <=3 steps, +0.40 at >=9), predicting its own failure region out of sample on AFTraj-2K. Ranking transfers with no retraining to two corpora from other groups (AFTraj-2K 0.745, ATBench 0.779). Monitors carry two burdens: a per-deployment healthy null (they do not transfer -- AUROC 0.527 cold against 0.885 recalibrated) and a residual false-alarm rate. We add a layer carrying neither: deterministic verification, which recomputes a run's stated total from the tool results it actually received and confirms every required call was made. Head-to-head it catches 60% of failures (96% with the coverage check) at 0 of 63 false positives against the monitor's 54% at 17%, transfers unchanged to llama3.1:8b (110 of 110 at 0 of 10), and trips on 0 of 1825 healthy episodes. Detection is then closed into repair: each flagged run is rolled back and re-run live, recovering 45% of failures against a 16% resampling control (p=0.0005) and lifting task success from 52% to 73% for about one extra model call per run. The system runs at ~200 microseconds per step, three orders of magnitude below a judge call. Code, traces and results are released. --- ### Syntax Meets Semantics: Understanding Scientific Formulae Authors: Yuni Susanti, Moritz Schubotz Published: 2026-08-03 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2608.02457v1 Scientific formulae are a fundamental component of scholarly communication, yet their dual nature -- as structured syntax and carriers of semantics -- remains underexplored in scholarly information retrieval. Although prior studies show that jointly modeling syntactic and semantic modalities improves retrieval performance, the relationship between their underlying representations has not been systematically investigated. In this work, we empirically study cross-modal correspondence between formula syntax and semantics. We find that their native representation spaces exhibit extremely weak observable correspondence despite strong latent correlation, indicating a substantial representation mismatch between the two modalities. We further evaluate whether this mismatch can be reduced using standard representation learning and alignment techniques. We represent syntactic structure using graph-based encoders and semantic information using text-based encoders, then apply contrastive learning to induce a shared representation space. Results show that the learned alignment substantially improves cross-modal retrieval, suggesting that explicit representation learning can recover correspondence absent from the original representation spaces. --- ### Aggregate-then-Calibrate for Human-centered Assessment with Theoretical Guarantees Authors: Zejun Xie, Xintong Li, Guang Wang, Desheng Zhang Published: 2026-08-03 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.02455v1 Human-centered assessment tasks, which are essential for systematic decision-making, rely heavily on human judgment and typically lack verifiable ground truth. Existing approaches face a dilemma: methods using only human judgments suffer from heterogeneous expertise and inconsistent rating scales, while methods using only model-generated scores must learn from imperfect proxies or incomplete features. We propose Aggregate-then-Calibrate (AtC), a two-stage framework that combines these complementary sources. Stage-1 aggregates heterogeneous comparative judgments into a consensus ranking using a rank-aggregation model that accounts for annotator reliability. Stage-2 calibrates any predictive model's scores by an isotonic projection onto the order, enforcing ordinal consistency while preserving as much of the model's quantitative information as possible. Theoretically, we show: (1) modeling annotator heterogeneity yields strictly more efficient consensus estimation than homogeneity; (2) isotonic calibration enjoys risk bounds even when the consensus ranking is misspecified; and (3) AtC asymptotically outperforms model-only assessment. Across semi-synthetic and real-world datasets, AtC consistently improves accuracy and robustness over human-only or model-only assessments. Our results bridge judgment aggregation with model-free calibration, providing a principled recipe for human-centered assessment when ground truth is costly, scarce, or unverifiable. --- ### Infinite Trace Objectives with Finite Trace Techniques: Translating LTL to LTLf+ Authors: Christoph Weinhuber, Maximilian Prokop, Giuseppe De Giacomo, Moshe Y. Vardi Published: 2026-08-03 Categories: cs.AI, cs.FL, cs.LO arXiv: https://arxiv.org/abs/2608.02454v1 Linear Temporal Logic (LTL) is one of the most widely adopted languages for specifying temporal extended objectives in AI, with applications ranging from reactive synthesis to stochastic planning in Markov decision processes and reinforcement learning. Traditionally, solving any of these problems requires translating the LTL specification to a nondeterministic automata on infinite words and then determinizing it, a step that is notoriously difficult in theory and in practice. Recent work has introduced LTLf+, which lifts the finite-trace logic LTLf to infinite traces. LTLf+ has the same expressive power as LTL, yet it retains most of the crucial advantages of its base logic LTLf. Most reasoning in LTLf+ rests on finite automata on finite words, for which we have not only a canonical minimal representation but also an efficient determinization procedure. In this work we present the first translation from LTL to LTLf+. We first normalize an LTL formula into the syntactic reactivity fragment of the Manna-Pnueli hierarchy, to create the general fragment-based shape of LTLf+. We then present linear translations for each individual component of that fragment. As a consequence of this translation, the expanding body of techniques developed for LTLf+ now becomes available to many AI problems currently formulated in LTL. We further show that this comes at no asymptotic cost, as the pipeline from LTL to automaton via LTLf+ remains doubly exponential. --- ### MoRAL: Sensor-Grounded BEV Reasoning for Compact VLMs toward Edge-Oriented Autonomous Driving Authors: Ambarish Govindarajulu Kaliamurthi, Kaikai Liu Published: 2026-08-03 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.02449v1 Deploying vision-language models (VLMs) for safety-critical spatial reasoning on resource-constrained autonomous driving platforms requires both compact model size and reliable metric grounding. We present MoRAL (Multimodal Reasoning for Autonomous Language Models), a two-stage fine-tuning pipeline that teaches Cosmos-Reason2-2B to first read a physics-encoded Bird's Eye View (BEV) representation and then reason over it for driving decisions. The BEV image encodes LiDAR metric distance as color bands, object class as cluster morphology, and radar Doppler velocity as directional wedge overlays, externalizing spatial perception into the input image so that no learned 3D backbone is required at inference. Stage 1 fine-tunes the vision encoder on 60,000 grounding records; zero-shot baselines produce no parseable BEV outputs, confirming the vocabulary requires explicit training. Stage 2 fine-tunes the full model (52M parameters, 2.4% of total) on 57,696 chain-of-thought records generated by Cosmos-Reason2-8B as teacher, spanning eight driving question types. On 2,304 held-out nuScenes frames evaluated by Gemma 4 (31B) calibrated against human review, MoRAL wins seven of eight question types over a zero-shot 8B baseline despite using four times fewer parameters, with the largest margins on question types requiring structured multi-step physics reasoning. Emergency braking recall improves from 10.8% to 47.8%, output degeneration falls from 94.1% to 20.8%, and the full pipeline fits a consumer 8 GB GPU at 42 tok/s without quantization. These results establish a reproducible foundation for compact, physics-grounded VLM reasoning on mobile edge platforms. --- ### UAV-Based Environmental Monitoring of Rip-Current Indicators Using Wavelet-Derived Texture Features Authors: Yonatan Ben Avraham, Baruch Binyaminov, Yehudit Aperstein Published: 2026-08-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.02448v1 Rip currents are recurrent coastal natural hazards that threaten beachgoers and create operational challenges for lifeguards and coastal managers. Reliable monitoring from standard RGB (red-green-blue) imagery acquired by unmanned aerial vehicles (UAVs) remains difficult because hazardous channels often appear as subtle gaps in breaking waves, foam texture, or sediment patterns, and these signatures are affected by illumination, sea state, and environmental noise. This study presents a physically informed coastal environmental monitoring workflow for detecting visually expressed rip-current indicators that integrates wavelet-derived spatial-frequency texture features with deep learning. We evaluate multiple strategies for incorporating Discrete Wavelet Transform features into convolutional architectures, from computationally efficient channel replacement to dual-stream fusion with attention mechanisms. Performance is assessed against a standard RGB baseline using a task specific convolutional neural network for image-level presence classification and a YOLOv8 model for object-level localization. Under the evaluated dataset conditions, integrating wavelet derived texture features improves performance over RGB-only models. The dual-stream architecture achieves the strongest classification performance, exceeding 95% accuracy with high recall, while channel replacement is most effective for YOLOv8 object detection, reaching 94% mAP@50 for localization. Explainable artificial intelligence analyses provide qualitative evidence that the models attend to visually plausible wave-gap regions associated with rip currents. These results suggest that under the conditions of the evaluated dataset, physically informed wavelet integration may support UAV-based decision-support tools for interpretable beach-safety risk mitigation. --- ### Advancing Relevance Measurement with Vision-Language Models for Web-Scale Search Authors: Han Wang, Alex Whitworth, Pak Ming Cheung, Zhenjie Zhang, Krishna Kamath, Xi Chen, Roberto Konow, Kurchi Subhra Hazra Published: 2026-08-03 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2608.02446v1 Relevance evaluation plays a crucial role in personalized search systems, serving as a guardrail alongside user engagement metrics to ensure that search results align with user queries and intent. While human annotation is the traditional method for relevance evaluation, its high cost and long turnaround time limit its scalability. In this work, we present a VLM-based automated relevance evaluation pipeline deployed within Pinterest Search for online A/B experiments. We rigorously validate the alignment between VLM-generated judgments and human annotations, demonstrating that VLMs can provide reliable relevance measurement for experiments while greatly improving the evaluation efficiency. Leveraging VLM-based labeling further unlocks opportunities to expand the query set, optimize sampling design, and efficiently assess a wider range of search experiences at scale. This approach leads to higher-quality relevance metrics and significantly reduces the Minimum Detectable Effects (MDEs) in online experiment measurements. --- ### ParEvalLayer: When Partial LLM-Agent Evaluations Support a Decision Authors: Wei-Jung Huang, Bonan Shen Published: 2026-08-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.02444v1 LLM-agent evaluations often produce task outcomes long before the full benchmark run is complete. A partial score is tempting to report, but it does not show whether the observed tasks support the same conclusion as the completed evaluation. Early tasks can omit important parts of a benchmark, running cheaper tasks first can distort the observed sample, and a rule that decides only easy pairs can appear accurate while leaving many comparisons unresolved. We introduce ParEvalLayer, a decision layer that reads paired outcomes for two agent systems and a comparison policy chosen in advance. For each partial run, it records whether the tested agent system is better by the required amount, is not better by that amount, needs more evidence, or should abstain. We evaluate ParEvalLayer by replaying completed public benchmark data as if each evaluation had stopped earlier. At each point, ParEvalLayer applies the policy using only the outcomes observed so far; if it reaches one of the two comparison judgments, we check whether that judgment matches the completed data for the same system pair. With the main comparison rule, three of the public benchmarks reach the same decision as the completed evaluation after observing only 15% to 25% of task outcomes. Other benchmarks require more task outcomes. This variation shows why a partial score alone is not enough: reports should also state the decision rule and how many comparisons remain without a decision. --- ### Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks Authors: Xuan Ren, Weiqi Zhai, Tianle Pu, Yihua Zhu, Yihua Zhu, Hu Wei, Bing Zhao Published: 2026-08-03 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.02442v1 Scientific reasoning benchmarks typically evaluate large language models (LLMs) using final-answer accuracy. However, a correct answer does not necessarily demonstrate the reasoning capability targeted by the problem. We identify Solution Hacking, a failure mode in which an LLM reaches the correct answer through invalid shortcuts, such as numerical search, enumeration, guessing, or answer-first verification, without providing a valid task-targeted derivation. We systematically analyze this phenomenon across difficulty levels, scientific domains, and frontier models. Solution hacking increases sharply with benchmark difficulty, from 2.2\% on common problems to 28.3\% on Olympiad-level problems and 37.4\% on HLE. Moreover, 8.2\%-44.1\% of answers credited as correct across frontier models are identified as hacked solutions. We further develop expert-inspired anti-hacking strategies, including an automatic judge and a test-time instruction. The results show that suppressing shortcut behavior substantially reduces reported accuracy while having a smaller effect on correct and non-hacked accuracy. These findings reveal that answer-only evaluation can overestimate the scientific reasoning capabilities of frontier LLMs. --- ### Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce Authors: Shicheng Fan, Mingdai Yang, Duohao Wang, Canyu Chen, Yongfeng Zhang, Hua Wei, Manling Li, Julian McAuley, Kun Zhang, Philip S. Yu, Kejing Yu, Zhiwei Liu Published: 2026-08-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.02441v1 In vibe coding, people describe software in natural language and delegate implementation to AI agents. By analogy, vibe commerce allows people to express buying or selling goals in natural language and delegate the corresponding tasks to agents. Commerce, however, requires independently controlled Buyer and Merchant agents to interact in a shared market while preserving their private objectives and distinct authority. We introduce Agentic Commerce World (ACWorld), an environment for evaluating such agents across ongoing transactions. Through its Vibe Commerce Protocol (VCP), ACWorld validates agent actions before updating shared transaction state and records the resulting interactions, making agent behavior auditable and evaluation reproducible. The ACWorld Benchmark contains a 200-task capability-coverage track and a 60-task large-catalog track that searches 785,022 transactable listings. Across ten models, mean scores range from 65.9% to 85.6% and from 56.1% to 91.4%, respectively. Our analysis shows that process-level evidence is necessary: final state alone can miss evaluated errors, incomplete trajectories still retain useful process signals, and large-catalog tasks expose bottlenecks across stages. --- ### Intention Inference Under Execution Noise: Separating Aleatoric and Epistemic Uncertainty in Social Dilemmas Authors: Kival Mahadew, Jonathan Shock Published: 2026-08-03 Categories: cs.GT, cs.LG arXiv: https://arxiv.org/abs/2608.02440v1 In noisy social dilemmas, intended actions are stochastically corrupted before execution, so an observed defection may reflect hostile intent or action error. Standard Markov Decision Process (MDP) formulations treat executed actions as states, structurally precluding this distinction and causing systematic over-retaliation. We introduce a Partially Observable MDP (POMDP) formulation encoding opponent intentions as latent states and executed actions as noisy observations, solved within the active inference (AIF) framework with a cost function that decomposes into epistemic and pragmatic components that jointly address inferring current intent and learning how intent evolves. In the Iterated Prisoner's Dilemma with symmetric noise, we derive a critical noise threshold governing cooperation collapse, connecting it to a fixed-point condition on learned priors. Experiments reveal that the value of intention inference is context-dependent: the POMDP provides consistent advantages against conditionally cooperative opponents, but mutual intention inference under sufficient noise produces correlated belief-driven collapse. The advantage is specific to games where intent attribution is decision-relevant. --- ### xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding Authors: Zheng Wang, Davis Wertheimer, Yu Chin Fabian Lim, Mudhakar Srivatsa, Raghu K. Ganti, Minjia Zhang, Naigang Wang Published: 2026-08-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.02438v1 Block-diffusion drafters like dFlash generate an entire block of draft tokens in a single forward pass, drastically reducing the overhead of multiple-token drafting in speculative decoding. The crucial final step of the single-pass discrete denoising process involves using the logit distribution at each position to sample conditionally independent tokens. The resulting draft is thus a set of per-position marginals, rather than a joint distribution: no draft token is guaranteed to depend on its predecessors. Such independently sampled marginals tend to produce sequences with tokens that are individually likely, but jointly improbable under the target model's distribution, which verifies each token conditionally. This can cause early rejection and limits acceptance length. To address this, we propose xPress as a means to restore the missing causality in diffusion drafters. xPress is a lightweight causal refiner that reconciles the whole diffusion block at once through parallel refinement, restoring and propagating causal dependencies across the draft without a token-by-token loop. On Qwen3-8B, across seven math, code, and chat benchmarks, xPress raises acceptance length by about 30% on average (up to +56%) and its end-to-end decoding throughput by about 1.3 on average (up to 1.7) compared to the original dFlash diffusion drafter. --- ### InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis Authors: Jiawei Wang, Hao Yu, Yongzhen Hu, Xinyi Yang, Tao Ni, Xin Zhan, Junbo Chen, Xiaowei Zhou, Ruizhen Hu, Sida Peng Published: 2026-08-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.02437v2 Single-image feed-forward 3D Gaussian Splatting (3DGS) aims to directly generate a renderable 3D scene representation from one input image, avoiding the cost of multi-view capture and per-scene optimization. However, existing methods are often constrained by a pixel-aligned representation, where Gaussians are predicted from fixed image-grid locations. Such pixel-aligned primitives can produce promising nearby-view renderings, but they remain weakly coupled to underlying scene surfaces and struggle to preserve coherent structures under large viewpoint shifts. We present InfiniSplat, a feed-forward single-image 3DGS framework that moves from a pixel-aligned representation toward a surface-aligned representation. InfiniSplat constructs this representation by first using geometry-guided sampling to place 2D supports according to depth-induced local surface structure, and then applying a query-conditioned implicit decoder to predict Gaussian attributes from the image features queried at these supports. By grounding support locations in geometry while decoupling Gaussian prediction from fixed pixel centers, InfiniSplat produces Gaussian layouts that better follow scene surfaces and reduce scattered primitives caused by grid discretization. Across multiple cross-dataset NVS evaluations, InfiniSplat achieves state-of-the-art performance compared with single-image feed-forward baselines, and demonstrates zero-shot generalization from Hypersim indoor synthetic training to complex open-world scenes. Project page: https://zju3dv.github.io/InfiniSplat. --- ### Foundations of Reinforcement Learning and Control:Connections and New Perspectives Authors: Claire Vernade, Onno Eberhard, Martha White, Florian Dörfler, Csaba Szepesvári, Miroslav Krstic, Michael Muehlebach Published: 2026-08-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.02433v1 Reinforcement learning and control theory are two adjacent scientific fields that focus on optimizing the controller of unknown dynamical systems using feedback. While both fields have common roots in dynamic programming, they have evolved with distinct methodologies, goals, and cultures. Despite decades of mutual influence, a significant gap persists between the two communities. This tutorial introduces adaptive control, actor-critic reinforcement algorithms, and a new way to combine these two paradigms for data-driven decision making on a classical locomotion control problem. Our aim is to provide a foundation for understanding the core differences between the two approaches and insights to help experts in each field better understand and engage with the tools and approaches of the other. --- ### Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning Authors: Monan Sun, Bangzhen Liu, Huaidong Zhang, Shengfeng He Published: 2026-08-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.02432v1 Autoregressive models have emerged as an effective paradigm for point cloud generation. However, most existing approaches rely on heuristic tokenization strategies, such as spatial sorting or stochastic downsampling, which often disrupt intrinsic point cloud topology and weaken the structural coherence of the generated shapes. In this paper, we present PointRSP, an autoregressive framework that reformulates point cloud generation as a topology-preserving tessellation process via recursive spectral partitioning. Instead of constructing token sequences heuristically, we introduce a topology-aware partitioning autoencoder that decomposes an unstructured point cloud into a non-balanced binary tree through a hybrid recursive spectral partitioning strategy. This hierarchical representation provides a deterministic geometric blueprint that preserves topological relationships while capturing multiscale structural dependencies within a quantized latent space. To synthesize shapes in this space, we propose a dual-stream cascaded generator that jointly models structural evolution and feature synthesis. In addition, we design a geometry-calibrated positional encoding mechanism that anchors latent embeddings using multi-scale structural centers, which stabilizes cascaded generation during the early stages of structural formation. Extensive experiments show that PointRSP achieves state-of-the-art performance in generation quality and diversity, demonstrating strong generalization across complex 3D topologies. --- ### Wasserstein mixing time of the unadjusted Langevin algorithm Authors: Francesco Pedrotti, Peter A. Whalley Published: 2026-08-03 Categories: stat.CO, cs.LG, math.NA, math.PR arXiv: https://arxiv.org/abs/2608.02430v1 We provide new estimates in Wasserstein distance for the asymptotic bias of the unadjusted Langevin algorithm, in the classical setting of log-smooth strongly log-concave measures. Our bound implies a Wasserstein mixing time of order $κ\sqrt{d}/\varepsilon$, where $κ$ is the condition number, $d$ is the dimension, and $\varepsilon$ is the target precision: this improves by a factor of $\sqrt{d}/\varepsilon$ over the previous state-of-the-art results. --- ### DF$^3$: World Modeling via Decoder-Free Feature Forecasting in Autonomous Navigation Authors: Jiaming Chen, Guoan Xu, Aoshen Huang, Haozhuo Zhang, Yang Li, Wei Pan Published: 2026-08-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.02428v1 Forecasting future states from video sequences is a critical challenge for autonomous robotic systems and a fundamental objective of world modeling. Prior generative methods operating at the pixel level inevitably overemphasize task-irrelevant details, leading to prohibitive computational overhead. While latent-based approaches attempt to mitigate this by predicting features directly, the persistent reliance on heavy decoders for state-to-task mapping remains a computational bottleneck. In this work, we propose Decoder-Free Feature Forecasting (DF$^3$), a novel framework that models world evolution entirely within the latent space and directly derives task outputs, completely eliminating the need for a decoder. Specifically, DF$^3$ injects learnable spatial queries into the terminal blocks of a frozen vision foundation model to extract future state representations directly. By employing a lightweight, unified Motion-Aware Context Fusion (MACF) mechanism that seamlessly integrates coarse flow warping with fine-grained latent cross-correlation, these queries interact with historical token representations to explicitly align and forecast the feature of the next frame. Subsequently, a specialized set of task queries probes these forecasted features for the downstream task. Extensive experiments on public benchmarks and zero-shot deployment in a robotic simulator demonstrate that DF$^3$ achieves performance comparable to state-of-the-art methods while offering superior efficiency and flexibility for integrated perception and control. --- ### Agentic Incident Response through Digital Twin-Enhanced Multiscale Planning Authors: Yiran Gao, Tao Li, Kim Hammar Published: 2026-08-03 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.02422v1 Incident response is currently managed by security operators using predefined playbooks, resulting in slow, labor-intensive security decision-making processes. Consequently, there is a growing need for automated incident response planning. Decision-theoretic approaches based on control, optimization, and reinforcement learning have been proposed to automate such planning tasks with well-grounded approaches, yet most of which, while guaranteeing strong performance, are limited to abstract models and cannot be directly applied to operational systems. A promising approach to mitigate this limitation is to use the security knowledge embedded in large language models (LLMs) to develop agentic response systems. However, current agentic approaches rely on repeated invocations of the LLM to generate a response plan, which is unreliable and limits the planning horizon due to hallucination. In this paper, we develop a principled LLM-based planning method by combining decision-theoretic planning with LLM-generated response commands. The proposed agentic incident response approach uses a rollout planner to compute a high-level response strategy that allocates security resources (the tactical scale), which is then translated into executable commands by a lightweight LLM agent (the operational scale). Within this architecture, we use a digital twin that supports tactical planning through simulation and operational execution through emulation. Across three attack scenarios, our agentic approach reduces recovery execution time by 15.1\% on average and increases the recovery rate by 33.6\% over frontier LLM baselines. --- ### Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes Authors: Nan Chen, Zhouhao Yang, Soufiane Hayou Published: 2026-08-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.02415v1 Intent classification in Large Language Models (LLMs) involves categorizing user prompts into predefined classes. For instance, given a user prompt, the system must determine whether it primarily concerns mathematics, coding, or general text processing. Such classification enables routing prompts to specialized models optimized for specific domains, improving both accuracy and computational efficiency. In this work, we conduct a systematic study comparing training-free vs training-based approaches for intent classification. For this purpose, we consider two lightweight, training-free methods based on statistics of internal representations and compare them against MLP classifiers and linear probes. Our comprehensive empirical evaluation reveals that 1) Both training-free and training-based methods saturate easy benchmarks (mathematics vs. coding vs. natural language), 2) Training-based classifiers have an advantage on harder classification tasks (e.g. Java vs Python), and 3) Training-free methods are generally more robust to mixed-intent and adversarial prompts. --- ### Why Large Language Models Fail at Tabular Prediction Authors: Marta Garnelo, Wojciech M. Czarnecki Published: 2026-08-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.02412v1 Large language models (LLMs) have become the default tool for a remarkable range of tasks, yet they have had conspicuously little success at one of the most common machine learning workloads: predictive analytics over tabular data. This gap is the founding premise of the fast-growing field of tabular foundation models, but the question of why generic LLMs fail has remained open. We study a frontier LLM in its purest inference regime - a single generation pass over a prompt containing the full training and test data, with no tools, no agentic scaffolding, and no fine-tuning - and systematically evaluate five hypotheses for the failure: (a) an inability to handle noisy or non-linearly-separable data; (b) the linearised CSV format obscuring column structure; (c) the tokenisation of numeric values; (d) the number of test points classified per query; and (e) the dimensionality of the input. Controlled experiments falsify (a)-(d). Dimensionality, in contrast, is decisive: sweeping random linear projections of thirty-one benchmark datasets, the LLM is the only method among nine whose accuracy decreases as dimensionality grows, while every classical baseline stays flat or improves. A behavioural comparison against 252 configured classical models finds that in two dimensions the LLM predicts like a local, distance-based method (up to 91.6% grid agreement), but in higher dimensions no classical model - even when augmented with tuned, dimension-dependent noise - reproduces its predictions. We do not claim to have identified the internal mechanism; our results show, more modestly, that the LLM's capability dissolves with dimension in a way no noise-corrupted classical learner mimics - which explains why LLMs, so capable elsewhere, keep losing to fifty-year-old baselines on tables, while leaving the mechanism of the prediction as an open question. --- ### Human-Centered Reflections on Care Robots: A Comparative Study of Caregiver Perspectives Authors: Laura Londoño, Klaus Baumann, Abhinav Valada, Markus Langer Published: 2026-08-03 Categories: cs.RO, cs.AI, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2608.02411v1 Care robots are increasingly being introduced into healthcare settings, raising important questions about their acceptance and ethical implementation. To better understand these challenges, this study investigates caregivers' perceptions of four categories of care robots: delivering supplies, helping patients into bed, monitoring vital signs, and assisting with mobility. We conducted a mixed-methods study employing a mixed-factorial design in which 298 caregivers from the United States, Mexico, and Chile evaluated all four robot categories. Quantitative measures integrated constructs from the Unified Theory of Acceptance and Use of Technology, the Cognitive-Affective-Normative model, and overall acceptance ratings. Qualitative data were collected through open-ended questions and analyzed using a literature-informed ethical framework. The results indicate that participants across countries generally evaluated care robots positively, particularly for logistical and physically demanding tasks rather than those requiring intensive interpersonal interaction. The qualitative findings provide further insight into stakeholders' views of the ethical implications of care robot use. Participants emphasized potential benefits such as reduced workload, lower risk, and greater patient autonomy, while also expressing concerns about dependability, the need for human oversight, and potential job displacement. Although many ethical concerns were shared across countries, participants differed in how they interpreted and prioritized them. These findings advance a context-sensitive and socially informed understanding of responsible design and implementation of care robots. --- ### MonitrLLM: A Community-Centered Evaluation Infrastructure for Large Language Models Authors: Victor Ojewale, Ro Encarnación, Suresh Venkatasubramanian, Danaé Metaxa Published: 2026-08-03 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.02409v1 Benchmark suites assess model capability on controlled tasks; large-scale conversation corpora capture naturalistic use without user feedback; and in-interface feedback mechanisms record satisfaction without task purpose. Together, they leave a critical gap in LLM evaluation: no existing infrastructure routinely links interaction trajectories to user-defined outcomes. We introduce MonitrLLM, open-source infrastructure for community-centered LLM evaluations that links full conversation transcripts to user-reported task intent and outcome assessments, treating all three as primary evaluative signals rather than optional metadata. To demonstrate the value of this approach, we conducted a two-week feasibility pilot with 26 college students using ChatGPT, collecting 206 evaluation reports with full conversation transcripts. The findings from our pilot demonstrate the value of connecting conversation trajectories with user-reported outcomes. For instance, despite reporting high average satisfaction (4.19/5) with their LLM interactions, participants also experience a substantial 23.1% failure rate on their goal tasks. We also find that multi-turn conversations are reported as failing at 2.5 times the rate of single-turn exchanges, a pattern that reframes extended interaction as a signal of difficulty rather than engagement. We conclude by discussing the value of incorporating direct user feedback with observational data for robust LLM evaluations, and the possibilities for infrastructure that enables this goal. --- ### Deep Learning-Based Estimation of Ground Reaction Forces in Parkinsonian Gait Using an Optimized Set of IMU Data Authors: Run Lin, Yingtian Tang, Jiawen Xu, Dongfei Huo, Lefan Wang, Helen Dawes, Dominic J. Farris, Dong Wang, Xijin Hua Published: 2026-08-03 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2608.02408v1 Accurate gait analysis in Parkinson's disease (PD) typically relies on laboratory-based systems to capture biomechanical data, such as ground reaction forces (GRFs). Estimating GRFs using inertial measurement units (IMUs) provides a feasible alternative. However, this approach remains challenging in pathological gait like PD due to its high variability and complexity. Moreover, existing monitoring approaches often require multiple body-mounted sensors, which limit practicality and reduce patient compliance. To date, no study has investigated the application of deep learning approaches to address this challenge. This study proposes, for the first time, a deep learning framework to estimate bilateral vertical GRFs (vGRFs) in PD using an optimized set of wearable IMUs. A hybrid CNN-BiLSTM model was trained separately on data from 61 PD patients and 65 healthy controls (HC) using 13 IMUs. The model achieved high intra-subject accuracy ($R^2$ = 0.98) and strong inter-subject generalization ($R^2$ = 0.93 for HC, $R^2$ = 0.91 for PD). Sensor configuration was found to significantly influence estimation accuracy, with optimal sensor placement varying between PD patients and HC. For PD patients, estimation accuracy dropped markedly when reducing to a single IMU. The optimal configuration for PD used four IMUs. We identified a minimal setup with only two IMUs still enabled robust estimation. This compact setup offers a practical and scalable solution. Overall, the proposed approach supports the development of wearable vGRF-based gait analysis systems for Parkinsonian gait and potentially other pathological conditions, enabling accessible clinical assessments, remote monitoring, and personalized rehabilitation. --- ### Antares: Foundation Models for Agentic Vulnerability Localization Authors: Supriti Vijay, Aman Priyanshu, Didier Chapoteau, Arthur Goldblatt, Jianliang He, Kimia Majd, Fraser Burch, Baturay Saglam, Takahiro Matsumoto, Zhuoran Yang, Amin Karbasi Published: 2026-08-03 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.02407v1 Vulnerability localization is a fundamental step in software security, requiring models to reason over large codebases and iteratively identify vulnerable implementations. We present Antares, a family of compact language models (350M, 1B, and 3B parameters) for agentic vulnerability localization. Based on IBM Granite base models, Antares is trained through a two-stage pipeline that combines supervised fine-tuning on cybersecurity reasoning and repository exploration data with reinforcement learning from verifiable rewards over vulnerable repositories. Across extensive evaluations, Antares-3B approaches GPT-5.5 while outperforming open-weight models over 200x larger in size. The Antares family further enables fast, low-cost local inference, completing a full 500-task evaluation sweep in approximately 15 minutes on a single H100 GPU, corresponding to an amortized evaluation time of under 2 seconds and less than $0.002 per task. --- ### A Unified Kullback--Leibler Divergence Analysis of Generative Diffusion Models via Entropy Production Rate Authors: Han Wu, Zhiwen Zhang Published: 2026-08-03 Categories: math.NA, stat.ML arXiv: https://arxiv.org/abs/2608.02406v1 We introduce a unified framework for the error analysis of generative models based on the entropy production rate of the forward-reverse diffusion process pair. For a pair of continuity equation flows, the rate admits a closed velocity form identity whose time integral decomposes the terminal Kullback--Leibler (KL) divergence into the sum of an initialization error, a score approximation error, and a time-discretization error. By analyzing the entropy production at the level of marginal distributions, rather than in path space, our framework yields a sharp convergence rate of $\mathcal{O}(h^2)$ for the Euler-Maruyama sampler, where $h$ is the step size. This improves upon the $\mathcal{O}(h)$ rates typically obtained from Girsanov's path-space analyses. Furthermore, our framework unifies the analysis of score-based SDEs, probability-flow ODEs, and stochastic interpolants by varying diffusion coefficients within a single inequality, revealing the trade-off between deterministic and stochastic sampling. Numerical experiments confirm the predicted scaling with step size and terminal time. --- ### Loggia dei Lanzi: AI Thermography Enhancement Comparisons through 3D Photogrammetry Authors: Scott McAvoy, Jonathan Klingspon, George Bent, Dave Pfaff, Aviral Agarwal, Maurizio Seracini, Falko Kuester Published: 2026-08-03 Categories: cs.CV, cs.DL arXiv: https://arxiv.org/abs/2608.02404v1 The Loggia dei Lanzi in the Piazza della Signoria is one of Florence's most prominent structures visited by millions every year. Its construction history spans multiple centuries of modification. This paper presents the results of a thermal imaging campaign conducted in December 2025, using a FLIR T1020 HD camera, revealing hidden architectural features including walled-up openings and material transitions beneath the plaster surface. The favorable winter ambient conditions provided a feature-rich benchmark upon which to compare the results of enhancement algorithms and artificial intelligence models. We evaluate the application of AI-based image enhancement to thermal heritage documentation through a comparison of three tiers of image resolution in a photogrammetric Structure-from-Motion (SfM) pipeline: native resolution, FLIR's hardware-based pixel-shifted super-resolution (UltraMax), and state of the art AI-upscaled imagery models. We quantify the effect of each resolution tier on feature detection and tie-point generation, assessing whether the additional detail produced by super-resolution, whether hardware or AI-derived, translates into meaningfully denser and more accurate 3D thermal models. Our results contribute to the emerging intersection of artificial intelligence and heritage thermography by providing a direct comparison of hardware microscanning and AI super-resolution within a thermal photogrammetric workflow for cultural heritage. All datasets are made publicly available and accessible within an interactive 3D archival framework, and integrated into a custom citywide extended reality overlay application. --- ### From fragmented data to actionable design: Physics-calibrated learning for plastic upcycling Authors: Jingyang Bai, Zijia Wang, Xiangyi Long, Marcos Millan, Binjian Nie, Mingyue Ding Published: 2026-08-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.02402v1 Thermochemical upgrading of plastic waste is a key upcycling pathway, yet the experimental literature is fragmented by heterogeneous conditions and incomplete reporting. Complete-case learning would retain only 10.99% of the curated experiments, while target imputation can introduce biased supervision. Here we develop a Physics-Calibrated, Missingness-Gated, and Load-Balanced Mixture-of-Experts (PC-MG-MoE) framework that converts structured missingness into an informative learning signal. PC-MG-MoE learns directly from partially observed experiments without target imputation, reconstructs physically consistent product distributions, accommodates cross-laboratory heterogeneity, and provides interpretable model behaviour rather than black-box prediction alone. Under stringent source-grouped validation, it achieved the lowest aggregate absolute error among the evaluated models, supporting engineering screening under cross-laboratory heterogeneity. Wet-lab experiments provide an external comparison, showing key composition-dependent trends. Implemented as an interactive web-based workflow, PC-MG-MoE enables forward screening, physics-grounded constrained inverse design, targeted experimental planning that supports reduced experimental workload and trial-and-error, and laboratory-specific adaptation with new platform-specific data. This work establishes a transferable framework for converting fragmented literature data into experimentally actionable guidance for model-guided plastic upcycling and broader thermochemical systems. --- ### USP-Mamba: Unmixing-Derived Spectral and Structural Prompting for Hyperspectral Image Super-Resolution Authors: Shi Chen, Jie Zhang, Yicong Zhou Published: 2026-08-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.02401v1 Hyperspectral image super-resolution aims to reconstruct high-resolution imagery while preserving dense spectral information. Recently, Mamba-based models have shown promising potential for this task by capturing long-range dependencies with linear computational complexity. Nevertheless, their causal sequence modeling requires two-dimensional hyperspectral features to be unfolded along predefined scanning orders, which disrupts spatial adjacency and restricts the effective propagation of contextual information. Moreover, state-space parameterization of existing models is predominantly derived from generic learned representations, without explicit alignment with the intrinsic characteristics of the hyperspectral image. To address this issue, we propose an Unmixing-derived Spectral and Structural Prompting Mamba framework, termed USP-Mamba, which adapts Mamba state evolution through composition-aware spectral priors and image-dependent structural prompts. Specifically, an unmixing-informed spectral prompt captures the global material composition of the input image and provides persistent conditioning throughout reconstruction. Injected into the Mamba sequence and progressively adapted across layers, it steers state evolution toward composition-consistent reconstruction. We introduce feature-level structural prompts comprising spatial and frequency components to provide image-dependent local guidance. The spatial prompt promotes structure-sensitive state encoding for local detail preservation, while the frequency prompt enables region-adaptive transitions between homogeneous regions and high-frequency details. Finally, complementary Hilbert and Semantic-Guided Neighboring scans preserve spatial continuity and strengthen non-local semantic dependency modeling. Extensive experiments on different datasets demonstrate that the proposed method consistently outperforms representative approaches. --- ### Network Information Enhances Unreliable News Domain Detection Authors: Raphaela Keßler, Roman David Ventzke, Viola Priesemann, Giordano De Marzo Published: 2026-08-03 Categories: cs.SI, cs.LG, physics.soc-ph arXiv: https://arxiv.org/abs/2608.02399v1 Content-based detection of unreliable news is increasingly difficult, as low-reliability sources mimic credible journalism and generative AI makes fabricated content harder to flag. We ask whether network structure can improve news reliability classification, taking a domain-level approach that shifts the focus from individual articles to source reliability. From URL-sharing patterns in Telegram chats, we build a statistically validated domain co-sharing network and find assortative mixing by reliability: low-reliability domains group together, as do reliable ones. Exploiting this structure, we compare Graph Neural Networks against network-unaware baselines using both content-aware features (multilingual text embeddings) and content-agnostic features (spreading dynamics). GNNs consistently outperform Multi-Layer Perceptrons on identical features, with GraphSAGE best in both settings (accuracy 0.63 with content, 0.53 without), a 13-14% relative gain over the network-unaware baseline. Network topology thus systematically improves domain reliability assessment, and remains effective even when content analysis is infeasible. --- ### Can Foundation Models Hear What Made That Sound? A Tiered Benchmark of Audio-Language Models and Traditional Classifiers for Closed-Set Sound Source Identification Authors: Sajjad Abdoli, Ghassan Al-Sumaidaee, Ahmad ElShiekh, Ahmed Rashad Published: 2026-08-03 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2608.02397v1 We benchmark eleven audio classification methods: five task-aware closed-set LLMs (four Gemini models plus open-weight Kimi-Audio-7B-Instruct), four fixed-vocabulary taggers (YAMNet, PANNs, Whisper-AT, and SSLAM), a zero-shot audio-text model (CLAP), and an audio-grounded LLM (BAT). We evaluate them on a closed-set sound-source identification task over 2,242 clips spanning 23 fine-grained classes and 11 categories. Since these methods differ fundamentally in how they receive the task and how outputs are scored, we group them into four evaluation tiers rather than one leaderboard, reporting macro Precision, Recall, F1, and false-negative rate per tier. The best model, Gemini-3.1-Pro-Preview, reaches 85.6 percent category-level F1 and 56.7 percent fine-grained F1. Kimi-Audio is competitive for its size, reaching 67.5 percent category-level F1 and 32.9 percent fine-grained F1, but fails to answer 1.6 percent of samples. SSLAM and CLAP match or exceed the best closed-set model at the category level without seeing the candidate list, but fall behind at the fine-grained level. Analyzing the Gemini models' chain-of-thought across 8,968 responses, we find that response length does not predict accuracy, an apparent "holistic judgment beats detailed analysis" effect is better explained as a difficulty confound, and wrong answers are stated confidently 92 to 100 percent of the time. We report full per-class confusion matrices and metrics for all eleven methods, identify the structural error modes behind most of the accuracy loss between granularities, and give practical guidance for choosing among these method families. --- ### Does Explainability Transfer? A Controlled Benchmark of Attribution Methods on Vision Transformers and CNNs Authors: Sathiyamohan Nishankar, Nethmi Pathirana, Pubudu Sanjeewani, Asanka Perera, Selvarajah Thuseethan Published: 2026-08-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.02396v1 Most evidence on the effectiveness of explainable artificial intelligence (XAI) attribution methods has been established on convolutional neural networks (CNNs), with limited investigation into whether these conclusions generalize to the diverse Vision Transformer (ViT) architectures that now dominate computer vision. This paper presents a controlled benchmark that evaluates attribution quality across five dimensions: faithfulness, localization, robustness, complexity, and computational cost. A standardized framework assesses 13 attribution methods from four algorithmic families on eight representative backbones spanning CNNs, isotropic ViTs, hierarchical transformers, hybrid architectures, and linear-attention transformers. The results show that attribution performance is strongly architecture-dependent and that rankings established on CNNs do not reliably transfer to transformer-based models. CAM-based methods achieve the highest scores under the conventional bounding-box localization metric on CNNs and most ViTs but perform poorly on linear-attention architectures. Pixel-level dense-mask evaluation further reveals that these gains largely reflect metric saturation rather than accurate localization. CAM-based methods also exhibit limited robustness on global-attention transformers, whereas attention rollout provides consistently stable explanations with poor localization. Furthermore, faithfulness correlation offers limited discrimination between attribution methods, highlighting the limitations of single-metric evaluation. These findings challenge prevailing conclusions on attribution performance and demonstrate the need for architecture-aware, multi-dimensional evaluation. The open-source code for the evaluation framework and benchmark results is available at https://github.com/Nishan-Charlie/VIT_XAI_Bench. --- ### GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience Authors: Sitong Gong, Caixin Kang, Tianyu Yan, Guo Chen, Bo Zheng, Kaipeng Zhang, Yunzhi Zhuge, Xiang Ruan, Huchuan Lu, Yifei Huang Published: 2026-08-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.02392v2 A wearable assistant should both answer questions about its visual history and recognize when that history is useful to the present situation. Existing video-memory systems primarily support question-conditioned recall, whereas proactive assistants typically use separate memory and control mechanisms. We introduce GROVE, a training-free framework that supports both behaviors with one memory grown causally from a continuous video stream. GROVE retains fine-grained perceptual evidence and incrementally consolidates it into time-stamped moments, coherent episodes, and recurring cross-day patterns. Each stratum is paired with a scale-native retrieval skill for locating an observation, replaying an activity, or traversing long-range regularities. Reactive QA and proactive assistance share this memory and access interface, differing in whether retrieval is initiated by a user query or the current situation. Across multiple benchmarks including the challenging MM-lifelong and EgoServe, GROVE achieves the best results among the compared methods. Controlled ablations show that the temporal strata and their access skills are complementary, with patterns providing the largest benefit when evidence spans multiple days. Code will be available at https://github.com/SitongGong/GROVE. --- ### Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training Authors: Zhiyuan Wang, Shengcai Liu, Jiahao Wu, Ning Lu, Hui Ouyang, Shaofeng Zhang, Haoze Lv, Ke Tang Published: 2026-08-03 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.02391v1 Tool-using large language model (LLM) agents produce long, multi-turn trajectories, making gradient-based post-training memory-intensive. Evolution strategies (ES) enable memory-efficient full-parameter post-training without backpropagation and can eventually match the performance of gradient-based reinforcement learning (RL). However, resource-constrained settings typically offer only a few GPUs, so the high GPU-hour requirements of ES translate into prohibitively long training times. To address this, we introduce Cooperative Parameter-subspace Evolution Strategy (CoPES), a cooperative coevolutionary method that decomposes the full parameter space into lower-dimensional subspaces and searches over them cooperatively to improve optimization efficiency. We post-train a Qwen3.5-4B tool-using agent for the math task and evaluate it on five benchmarks of varying difficulty. Under the GPU-hour budget of full-parameter GRPO's best validation checkpoint, CoPES recovers 92% of GRPO's validation-accuracy gain, versus 67% for standard ES, while its theoretical GPU memory requirement is less than one-eighth that of full-parameter GRPO. It consistently outperforms standard ES and LoRA-based GRPO on all evaluated pass@k metrics across the five benchmarks. Additional experiments further show the advantage of CoPES on the question-answering task. These results demonstrate an improved trade-off between memory requirements and training time for agentic LLM post-training under resource constraints. The code is open-sourced in https://github.com/MetaronWang/CoPES --- ### Chess on Ice: Curling Tactical Decision-Making via Backward Induction and Deep Reinforcement Learning Authors: Patrick Oberlin, Matteo Cederle, Aren Karapetyan, Saverio Bolognani, Gian Antonio Susto, Florian Dörfler Published: 2026-08-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.02379v1 Curling is often referred to as "Chess on Ice", owing to the tactical complexity of its decision-making process. Yet unlike chess, curling remains largely underexplored from a machine learning perspective, with prior work confined mainly to statistical approaches. We propose a reinforcement learning framework capable of quantitatively evaluating and comparing tactical options in curling. The game poses several modeling challenges: continuous state and action spaces, stochastic action outcomes reflecting player skill variability, and state transitions that are highly sensitive to small perturbations in the executed action. To address them, we employ the Deep Deterministic Policy Gradient actor-critic algorithm, adapted to exploit the finite-horizon structure of the game. Our experiments show that effective curling strategies can be acquired in a fully self-supervised manner, without any human-annotated data: on a reduced four-rock variant, the learned agent matches a hand-crafted expert heuristic in a regime where that heuristic is close to optimal, a parity we quantify against the intrinsic hammer advantage of the variant. Beyond the resulting policy, the learned critic provides a dense value estimate over the entire continuous action space, enabling the quantitative comparison of tactical alternatives for applications such as post-game performance analysis and decision support during athlete preparation. --- ### Gecko: Fast Private Inference via Secure Public Encoder Offloading Authors: Cheng'an Wei, Kai Chen, Yue Zhao, Congyi Li, Shenchen Zhu Published: 2026-08-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.02378v1 Private inference protects both user inputs and server models during neural network inference, but existing solutions remain too slow for practical deployment. This motivates recent efforts to run a public encoder, such as a pretrained backbone, outside the protection boundary and evaluate only a small private predictor cryptographically. While appealing for efficiency, this design is not inherently secure: naively offloading a public encoder may create a feature-space shortcut: an extraction adversary may learn the remaining private predictor's feature-to-output mapping more easily than the original model's input-to-output behavior. We present Gecko, designed to limit this additional risk while retaining a compact encrypted predictor. We leverage a frozen backbone that contributes hierarchical features, fixed Fastfood projections that compress them, and private feature gating that prepares them for prediction. We formalize ideal independence and information-preservation conditions as design guidance, then separately evaluate component-reuse extraction attacks. Across image and audio tasks, Gecko achieves 0.4-2.2 second inference with at most 10.8 MB communication and accuracy comparable to transfer-learning baselines. Under the evaluated attacks, reusing the offloaded public encoder provides no significant advantage to model-extraction adversaries. Source code and a demo are available at https://github.com/CassiniHuy/gecko-infer. --- ### Token-Native Storage: Read and Write in your Agent's Language Authors: Kumar Shivendu Published: 2026-08-03 Categories: cs.DB, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2608.02376v2 Search and database engines still store text as UTF-8, a format built for humans. But the systems that increasingly read and write that text (embedders, rerankers, and language-model agents) work with token IDs, not characters, so every access pays to translate between the two. As agents become the primary readers and writers of stored text, we argue for token-native storage: keep the text as the model's own byte-pair-encoding (BPE) token IDs. Packing r50k IDs as uint16 already beats UTF-8 by 2.25x on English with no compression, and an entropy coder on top reaches 3.30x. Across six tokenizers and three corpora (English, code, Hindi), compressing token IDs matches or beats every byte codec, even a corpus-trained zstd dictionary. Two findings sharpen the case. BPE numbers tokens by merge order instead of frequency, and re-ranking by frequency lets a plain integer codec (streamvbyte) recover most of the entropy coder's ratio while decoding ~7x faster, a near-free change to how AI labs publish vocabularies. And because a model reads token IDs, not text, a token-native store hands over the IDs directly instead of re-tokenizing on every read. The only requirement is that reader and writer share a tokenizer, and different model families often use different ones today, so we argue for standardization: a published, shared vocabulary, the way ASCII and UTF-8 standardized text. --- ### A Spectral Filtering Approach to Regret Analysis of Distributed Online Control for Linear Dynamical Systems Authors: Ting-Jui Chang Published: 2026-08-03 Categories: math.OC, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2608.02375v1 This paper studies the distributed online control problem over a network of linear time-invariant (LTI) systems in the presence of adversarial disturbances and time-varying convex costs. The network cost is characterized by the summation of local cost functions, where each local function is sequentially revealed only to the corresponding agent. The goal of each agent is to generate a control sequence, using only local observations and neighbor communication, that competes with the best {\it centralized} linear policy in hindsight. We extend the recently proposed Online Spectral Control framework from the centralized setting to the distributed setting. In particular, each agent applies a spectral controller obtained by convolving past disturbances with the leading eigenvectors of a Hankel matrix, while the controller parameters are updated through a distributed online gradient descent step over the local surrogate costs. We formulate this problem this problem as a {\it regret} minimization problem based on the spectral parameterization, and under standard assumptions, we establish a sublinear regret bound of $O(\frac{\sqrt{T}\text{poly}(\log T)}{γ^3})$, where $T$ is the time horizon and $γ$ denotes the stability margin. The resulting bound also captures the dependence on the network size and connectivity. --- ### PredAct-Bench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise Authors: Abdulrahman AlRabah, Xiaocheng Yang, Dilek Hakkani-Tür, Abdussalam Alawini Published: 2026-08-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.02372v1 Large Language Models (LLMs) are increasingly deployed in task-oriented dialogue systems that support multi-step decision-making in high-stakes domains such as education, healthcare, and finance. However, existing benchmarks typically assume perfectly accurate tool outputs, overlooking the reality that deployed systems must operate with noisy tools and human decision-makers whose trust in the agent is itself uncertain. Such conditions are common in practice, for example, a clinician using a diagnostic prediction tool or an advisor relying on a model that forecasts student outcomes from historical records. We introduce PREDACTBENCH, a benchmark for evaluating dialogue agents paired with statistically imperfect tools, using education as a measurable testbed where ground truth outcomes and clear intervention decisions are available. First, we build a benchmark for AI-assisted human decision-making, where the AI uses noisy predictors to help guide a user. Second, we introduce episode-level Relative AI-Reliance (RAIR) and Relative self-reliance (RSR) metrics, extending prior trust calibration framework to multi-turn dialogue. Third, we evaluate 13 state-of-the-art closed and open source LLMs on two educational datasets, OULAD (real assessment trajectories from the UK Open University) and PREDACT-CS (60 courses with real final grade outcomes and synthetically generated weekly score trajectories), alongside a human study with instructors and teaching assistants. We find that when tools are noisy, SOTA models are supposed to provide visibility to teachers so that they do not over-rely on wrong suggestions or hallucinations, but current models fail to do that. We offer PREDACTBENCH to help build better LLMs as AI decision support systems to help teachers. --- ### GLAIM: Learning Global and Local Adaptive Inter-Variable Dependency for Multivariate Time Series Imputation Authors: Mingyang Wang, Rongwen Li, Xiao Wang, Changjian Chen Published: 2026-08-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.02366v1 Multivariate time series imputation is fundamental to downstream analysis, yet modeling inter-variable dependencies with incomplete observations remains challenging. Existing methods learn global dependencies across samples or dynamic local dependencies per sample. Global dependencies are stable but adapt poorly to sample variations and temporal non-stationarity, whereas local dependencies are adaptive yet unreliable when observations are insufficient, causing erroneous information propagation. To address these limitations, we propose GLAIM, a Global-Local Adaptive Inter-variable Dependency Modeling framework for multivariate time series imputation. GLAIM comprises two complementary components. The Stable Global Dependency Constructor derives robust global inter-variable dependencies from complementary temporal representations, providing a stable backbone less affected by sample-specific missingness and noise. The Sample-Conditioned Dependency Refiner adapts this backbone to each sample and time step using its temporal state and available observations, enabling reliable local refinement under incomplete observations. Extensive experiments on nine real-world datasets demonstrate that GLAIM achieves state-of-the-art performance under random and block missingness, remains robust to missing-rate shifts, and benefits from its complementary global and local components. Code is available at https://github.com/LuRenjias/GLAIM. --- ### Faster-WAM: Do World Action Models Need Deep Action Modules? Authors: Liheng Ma, Rui Heng Yang, Zhanguang Zhang, Mateo Clemente, Ziwen Hu, Tongtong Cao, Yingxue Zhang Published: 2026-08-03 Categories: cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2608.02365v1 World Action Models (WAMs) couple robot action prediction with video world models. Existing WAMs with shared-backbone and Mixture-of-Transformers designs generally tie the depth of the action module to that of the video backbone, resulting in substantial computational overhead and high inference latency. To address this limitation, we introduce Dock of Transformer (DoT), a video-centric design principle that treats a pretrained video Transformer as a representation hub and connects lightweight output-heads through docking interfaces. This enables flexible output-head design while providing direct access to representations from all layers of the backbone. We then introduce \textbf{Faster-WAM}, an instantiation of DoT for WAMs, which docks a single-layer action head onto a 30-layer video backbone. The docking interface fuses keys and values from all video layers and applies RoPE realignment. Without additional embodied pretraining, Faster-WAM achieves competitive performance on LIBERO and RoboTwin 2.0 while demonstrating strong out-of-distribution generalization on LIBERO-Plus. Faster-WAM also achieves the lowest end-to-end latency in our controlled comparison, requiring only 66.5 ms per inference --- a \(3.2\times\) speedup over Fast-WAM. Overall, these results demonstrate that the video-centric DoT architecture supports flexible task-specific head design while delivering low inference latency, strong action-prediction performance, and robust generalization. --- ### Fast and Accurate Quotation Attribution in Literary Texts Authors: Gaspard Michel, Hugo Attali, Elena V. Epure Published: 2026-08-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.02359v1 Attributing quotations to their speakers in literary texts remains an open challenge. Standard methods, which independently predict a speaker mention for each quotation, are efficient but still limited in accuracy. In contrast, large language model (LLM) approaches achieve strong performance, but their computational cost limits their use in large-scale literary analysis. We propose an encoder-based efficient formulation that resolves multiple quotation attributions within a shared, large context window. Using our new formulation, \textit{joint scoring}, we report state-of-the-art (SOTA) performance on the Project Dialogism Novel Corpus (PDNC), comprising more than 35,000 manually annotated quotations from 22 English novels. Our best model reaches 94.5\% overall attribution accuracy while processing novels $20\times$ faster than comparable standard methods and more than $1000\times$ faster than LLM-based approaches on an A100 GPU. An analysis of models' representations suggests that joint scoring improves on challenging attribution examples by preserving long-range anaphora resolution signal, an information that we found already present in pretrained encoders. To facilitate adoption, we release ModernBookNLP, a modified fork of BookNLP that replaces its quotation attribution model with our best system available at https://github.com/gasmichel/ModernBookNLP_QA/. --- ### ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step Authors: Vernon Toh, Navonil Majumder, Zhengyuan Liu, Nancy F. Chen, Soujanya Poria Published: 2026-08-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.02358v1 To operate robustly in open-world environments, autonomous agents should be able to infer the behavior of unfamiliar systems through interaction alone, even in the absence of documentation. However, existing tool-use benchmarks expose semantic tool schemas in static environments, allowing agents to rely on prior knowledge rather than autonomous discovery. To address this limitation, we introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning. By removing semantic cues and enforcing a continuous task curriculum, the benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction. The benchmark further introduces dynamic challenges, including mapping drift, stochastic action failures, and temporal execution windows, to evaluate whether agents can revise and adapt their hypotheses as the environment changes. Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation. When faced with structural changes such as mapping drift, agents fail to use deductive strategies such as cycle tracing, and instead exhibit belief inertia or fall back to exhaustive search. Increasing test-time reasoning only amplifies this expensive brute-force search rather than enabling deductive recovery. While equipping agents with persistent memory reduces compounding errors, they remain unable to efficiently infer structural changes, highlighting a gap in current agent reasoning. --- ### SkillTrace: Traversing a Query-Skill Graph for Composable LLM Agents Authors: Yue Yao, Shengyuan Wang, Xin Chen, Minke Zhang, Jia He, Bingjun Luo, Tom Gedeon Published: 2026-08-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.02356v2 Large language model agents increasingly solve complex tasks by composing reusable skills from a library. To address this, the key challenge is not merely to retrieve individually relevant skills, but to identify a complete and executable skill composition. In this paper, we argue that this problem can be solved in a graph with three levels: compositional relations among skill queries, similarity between queries and candidates in the skill library, and the dependencies among the selected candidates. We introduce SkillTrace, which organizes the user query into a semantic hierarchy, matches skill queries and candidates, and propagates over the skill dependencies. Experiments on SkillsBench and ALFWorld demonstrate that SkillTrace achieves state-of-the-art performance, reaching a success rate of 53.17% on SkillsBench and 91.43% on ALFWorld. SkillTrace also delivers consistent improvements across different backbone language models, demonstrating the generality and robustness of graph-based skill retrieval. --- ### Global Optimization and Inference-Time Region Grafting for Agentic Workflows Authors: Donghyeok Koh, Gyuwan Kim, Jinyeong Bak, Seung-Hoon Na, Tao Yang, Haneol Jang, Cheoneum Park Published: 2026-08-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.02353v1 Recent advances in agentic workflow optimization automate workflow design through task-specific workflow search or input-conditioned architecture selection. However, they determine the workflow before execution and cannot adapt failed workflow regions using execution-time label-free quality signals. Naively enabling such inference-time adaptation through whole-workflow re-optimization would be computationally prohibitive. To tackle this challenge, we introduce GRAFT, which preserves a globally optimized workflow while locally replacing only selected regions for each input. Without parameter training, GRAFT evaluates region-level alternatives using label-free execution-quality signals and accepts only replacements that improve local quality while preserving workflow-level consistency, thereby enabling instance-wise adaptation without whole-workflow re-optimization. GRAFT applies without modification across a range of tasks spanning mathematical reasoning, code generation, and multi-hop and knowledge-intensive question answering. Under matched optimizer and executor settings, it improves over the strongest prior workflow-optimization method, MaAS, by 3.85 points on average. Replacing only the executor with a stronger model yields further gains without re-optimizing the global workflow. This suggests that an optimized workflow is not merely a static optimization artifact, but an adaptable execution policy that can evolve with inference-time feedback and stronger executors. --- ### Qwen-CUA: Native Computer Use for (almost) Everything Authors: Dunjie Lu, Shuai Bai, Tianyi Bai, Sicheng Fan, Chang Gao, Jian Guan, Feng Hu, Mianqiu Huang, Xingyang Huang, Yizhen Jiang, Yuheng Jing, Dehui Kong et al. Published: 2026-08-03 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.02352v1 Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive experience, and learning from sparse yet verifiable outcomes. We introduce Qwen-CUA, a native computer-use agent with a 397B-A17B Qwen mixture-of-experts backbone. It observes only screenshots and acts through keyboard and mouse events, without DOM trees, accessibility metadata, or task-specific APIs. Its scaffold maintains up to 20 active screenshots and folds older visual history in fixed-size blocks to retain recent evidence while preserving reusable prompt prefixes. For training, we build a cloud rollout fleet with access to nearly 100,000 vCPUs and tens of thousands of concurrent environments, construct approximately 40,000 verifiable tasks, and collect personalized long-horizon workflows across everyday and professional software. We optimize complete trajectories with verifiable rewards and trajectory slicing, while iterative training runs refresh supervised data and recalibrate reinforcement-learning tasks. Across eight benchmarks, Qwen-CUA outperforms Qwen3.7 and remains competitive with leading proprietary systems, reaching 86.2 on OSWorld-Verified and 18.5/48.4 binary/partial completion on OSWorld 2.0. Scaling the same recipe to a model with over one trillion parameters yields Qwen-CUA-Max, improving these scores to 87.6 and 21.2/53.3. Qwen-CUA also reduces RedTeamCUA attack success from 36.6 to 16.4 relative to Qwen3.7. Efficiency analyses, a browser deployment, and Bash-augmented experiments further characterize practical behavior. These results establish native computer use as a broadly capable agent foundation and highlight scalable verifiable interaction and hybrid tool use as key directions. --- ### KC-Agent: A Dual-Process Cognitive Architecture for Efficient ML Model Improvement Authors: Gusseppe Bravo-Rocca, Jordi Guitart, Ajay Dholakia, David Ellison, Puneet Jain Published: 2026-08-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.02351v1 Data drift poses significant challenges for machine learning systems in production, requiring continuous model updates to maintain performance. We present KC-Agent, a dual-process cognitive architecture for automated ML model improvement that combines fast pattern recognition (System 1) with deliberate incremental updates (System 2). Our approach implements structured memory systems enabling System 1 to leverage successful solutions previously discovered by System 2, achieving efficient pattern-based responses without costly re-computation. KC-Agent incorporates atomic change principles and rollback capabilities to ensure reliable, verifiable updates in production environments. We evaluate our method on five datasets including real-world NASA turbofan data with authentic temporal degradation and synthetic datasets with controlled drift scenarios. KC-Agent achieves state-of-the-art performance (76.8% accuracy) while maintaining optimal efficiency (13.2s execution time), outperforming established cognitive architectures: CodeAct (+2.4%), Tree of Thoughts (+3.6%), ReAct (+8.0%), and Reflexion (+8.9%). Consensus evaluation by a panel of state-of-the-art LLMs confirms superior strategic efficacy (8.33/10 Smartness score), significantly outperforming baseline agents. The knowledge consolidation mechanism delivers 91% speedup over the slow variant while maintaining higher accuracy. Our approach demonstrates both theoretical foundations and practical viability for cognitive-inspired automated ML improvement systems capable of handling complex real-world data drift scenarios. --- ### Self-Supervised Representations for Binary Program Clustering: From Empirical Study to Retrieval-Augmented Learning Authors: Martin Mocko, Daniela Chudá Published: 2026-08-03 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.02348v1 Malware clustering is a critical task in cybersecurity that helps discover threats and analyze evolving malware families. While self-supervised learning (SSL) and tabular representation learning (TRL) have achieved breakthroughs in other domains, their application to binary program clustering (the task of clustering all incoming samples regardless of label) remains largely unexplored. This study presents the first systematic investigation of SSL and TRL methods for binary program clustering, conducted in two phases on the public Ember and Bodmas datasets. In Phase 1, we establish a performance ceiling by adapting prominent vision-based SSL models (BYOL, SimSiam, Barlow Twins, VICReg) for tabular data with supervised pair generation, finding that BYOL and SimSiam achieve performance comparable to fully supervised models, while Barlow Twins and VICReg significantly underperform. In Phase 2, we evaluate purely unsupervised TRL methods against strong baselines (PCA, Autoencoder, UMAP), demonstrating that VIME establishes a new state of the art for binary program clustering. Informed by these findings, we propose VIME-R, a retrieval-augmented extension of VIME that replaces random marginal-distribution corruption with retrieval-based augmentation to generate more informative training pairs. VIME-R further improves upon VIME, achieving 2.7\%-5.8\% higher Homogeneity on both datasets. Our results highlight retrieval-augmented tabular representation learning as a promising direction for enhancing automated malware analysis. Code will be made available. ---