# Research Papers — 2026-08 · bundle page 122 of 240 > Full-text markdown of papers #6051–6100 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/122 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/121.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/123.md) ### Low-Rank Dynamics-Effective Latent Carriers for Counterfactual Rollout in Learned World Models Authors: Yang Liu, Yuming Chen Published: 2026-08-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.15156v4 We ask whether a small, directly addressable hidden-state intervention can place a learned world model on an intended counterfactual future and then let the model's own dynamics carry that future forward. In a controlled two-object collision environment, we study a 192-dimensional recurrent model trained on factual and locally edited counterfactual trajectories. Candidate carriers are learned from training-only counterfactual-minus-factual hidden differences, and an affine map predicts carrier coordinates from the factual state and requested edit without access to the native counterfactual hidden state at test time. For bounded single-component velocity edits, rank 4 is the smallest tested rank on the preregistered grid that satisfies the development criteria. A one-shot rank-4 patch launches a 12-transition autonomous rollout without future observations, teacher forcing, repeated hidden-state correction, or physical-state clamping. The frozen procedure satisfies the preregistered 2-of-3 fresh-checkpoint replication rule and remains reusable at nearby anchors. The same Single-derived carrier and Single-only affine map also support bounded same-object two-component requests. Across the matched training regimes, broader counterfactual support was associated mainly with better Joint rollout accuracy and more additive Joint hidden responses. Composition-related structure is enriched in the rank-4 subspace but is not confined to it, and local recurrent diagnostics show strong one-step coupling from the carrier to the rest of the hidden state. A position-edit stress test fails the required specificity controls. Together, these results support a compact dynamics-effective intervention-entry interface, not a closed four-dimensional state or an intrinsic state dimension. --- ### Beyond Effective Sample Size: Effective Number of Proposals for Adaptive Importance Sampling Authors: Ali Mousavi, Victor Elvira Published: 2026-08-15 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.15154v1 Population-based adaptive importance sampling (AIS) methods use a set of proposal densities to approximate complex target distributions. Their performance is commonly assessed through effective sample size (ESS) and related weight-based diagnostics, which measure the concentration of normalized importance weights. However, a large ESS only indicates that the normalized sample weights are not strongly concentrated; it does not describe how the proposal components are arranged in the sampling space. In population-based AIS, several proposal components may generate samples in the same region of the target, so the sample weights can appear well balanced even though the effective number of distinct proposal components is small. This letter introduces the effective number of proposals (ENP), a similarity-aware proposal-level diagnostic for population-based AIS. ENP combines the total normalized weight assigned to each proposal with a redundancy measure computed from similarities among target-weighted samples, estimating the number of non-redundant empirical proposal contributions to the approximation. We establish basic effective-number properties and show that ENP detects proposal collapse and duplication missed by standard ESS. We also illustrate its use as a targeted feedback signal for proposal rejuvenation. --- ### An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learning Authors: Wenjing Wei, Alla Jammine, Farid Nait-Abdesselam Published: 2026-08-15 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.15153v1 Differentially private federated learning must balance privacy protection against model accuracy and training efficiency. Static gradient clipping applies a fixed threshold throughout training and across model layers, which can cause excessive clipping when the threshold is too small or unnecessarily large noise when it is too large. This paper presents DDP-SA-adaptive, an adaptive gradient clipping and noise adding mechanism for differentially private federated learning with secure aggregation. At each communication round, every client determines a separate clipping threshold for each model layer from the median of its per-sample gradient norms. The resulting layer-wise thresholds adapt to the evolving gradient distributions and calibrate the Laplace noise added before the updates are encoded and secret-shared among intermediate aggregation servers. We evaluate the proposed mechanism on a federated regression task in terms of efficiency, accuracy, privacy, convergence, clipping norm, and noise magnitude. Compared with the static DDP-SA baseline, DDP-SA-adaptive reduces the number of communication rounds by 6.81%, total training time by 19.21%, and average per-round training time by 13.33%, leading to improved training efficiency. It also reduces test loss by 98.74% and increases test R2 by 3.41%, leading to improved model accuracy. To attain R2 = 0.99, the adaptive mechanism operates with a privacy budget of approximately epsilon = 0.1, compared with epsilon = 0.4 for static DDP-SA, thus providing stronger privacy protection and achieving stronger privacy guarantees. These results demonstrate that round-wise, layer-wise adaptation can improve the privacy-accuracy-efficiency trade-off of differentially private federated learning. --- ### Constitutive Priors for Machine Intelligence: A Legitimacy Theory of the Artificial Physical World Authors: Jiang Jiang, Yifu Sun, Qi Shen Published: 2026-08-15 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.15147v2 Machine intelligence's push into the physical world is stuck on a gap: deployment demands auditable judgments from day one, fault samples are scarce or absent, and the norms defining "what counts as a fault" live in design documents, not in operational data. We argue this gap is structural, and locate where it can be legitimately closed. We divide the worlds machine intelligence faces into four (phenomenal, basic physical, artificial physical, artificial symbolic) along one axis of constraint strength, and give the Promulgation Criterion: extracting a prior framework from a world is legitimate if and only if the world is intentionally constituted (C1) and has left a readable generative archive (C2). On the criterion's two gradient axes, exactly one world is high on both: the artificial physical world (buildings, factories, infrastructure), whose norms precede their instances; the legitimate path is to extract the framework from the archive, not to induce it from data. We then show what shape such a framework must take: four construction goals force four incompatible carriers, hence at least four layers (syntax, concepts, knowledge, instances); on a closed concept layer fault localization is decidable in polynomial time, and every judgment is interrogable, traceable to a promulgated clause. The same criterion fixes the runtime division of labor with LLMs: promulgatable duties go to rule engines, on-site judgments beyond promulgation go to LLMs, and every generation sandwiched by promulgated clauses is auditable. The theory is falsifiable: four bets (P1-P4) with explicit falsification conditions -- among them that the next large-scale AI breakthrough occurs in the artificial physical world. Evidence: formal proofs (Appendix A); two cases (Appendix B: a cooling plant; the Curiosity rover Sol 1536 anomaly); eight reverse-read lineages, from BACnet to RDF/OWL (Appendix C). --- ### PureTD: Reinforcement Learning for Backgammon Money Games with No Evaluation-time Search Authors: Alexander L. Strehl Published: 2026-08-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15146v1 We revisit Tesauro's TD-Gammon for backgammon money games in the setting of no evaluation-time search. Both checker play and cube action (use of the doubling cube) are learned from scratch via self-play reinforcement learning (RL), with minimal hand-coded logic and no expert features. In this setting, we demonstrate that pure self-play RL suffices to train models that reach near-state-of-the-art playing strength. Specifically, for cubeful money games, our search-free model evaluates faster and is substantially stronger than the open-source engines GNU Backgammon and Open Sage running a one-move (1-ply) look-ahead search. --- ### ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Models Authors: Xinmei Huang, Jie Song, Peng Li, Fuxin Jiang, Jing Zhang, Tieying Zhang, Jianjun Chen, Chenming Liu, Tao Yang, Maoyin Liu, Wenda Li, Hong Chen et al. Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15145v1 Large Language Models (LLMs) have been increasingly adopted in Text-to-SQL systems, yet SQL errors remain a major obstacle in real-world Text-to-SQL inference pipelines. Existing SQL correction approaches either rely on large-scale, high-quality training data with substantial overhead, or adopt single-path agentic workflows that are brittle to early mistakes and prone to error propagation. To develop a practical SQL correctness system for industrial scenarios, we present a training-free framework that formulates SQL correction as a plan-guided, tree-structured debugging process. By maintaining multiple correction strategies and enabling backtracking, the framework mitigates error accumulation during iterative refinement. We further integrate execution-based verification and clause-level diagnostic tools to support strategy pruning and precise error localization. We evaluate the system on the BIRD-Critic benchmark and observe consistent accuracy gains over strong LLM backbones and representative agent-based baselines, achieving a 9.42% improvement over the previous state-of-the-art method. The framework is also deployed in the Torch Log Service (TLS) of Volcano Engine to support an online Text-to-TLS API. In production, it improves execution accuracy from 36.77% to 53.61% on real user queries with a representative strong LLM backbone (GPT-5). These results demonstrate the effectiveness and stability of our approach in real-world deployments. --- ### A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors Authors: Zhaoqiang Liu, Tongyao Pang, Ruibing Wang, Yang Zheng Published: 2026-08-15 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.15144v2 Pretrained diffusion models represent image distributions through a continuum of progressively smoothed distributions. This multiscale structure organizes generation from global structure to fine detail and supports high-quality, diverse samples. We exploit the same multiscale diffusion prior for linear imaging inverse problems. Rather than using the pretrained model only as a denoiser in an outer iteration, we define a surrogate likelihood whose center is aligned with the clean-image coordinate and whose covariance accounts for residual diffusion uncertainty. This construction defines an explicit surrogate posterior path, from which we derive continuous posterior dynamics. A tunable Langevin component supports target tracking and allows the amount of posterior exploration to be adapted to the application. We prove endpoint consistency and a finite-horizon tracking bound and, in the exact-score setting, first-order weak accuracy. For computation, we derive the Posterior-Dynamics Implicit--Explicit sampler (PD-IMEX), a stable method using one score evaluation per diffusion scale and an implicit data-consistency update. Experiments on deblurring, super-resolution, and inpainting show strong reconstruction quality at 100 score evaluations, coarse-grid stability, and controllable fidelity--diversity behavior. --- ### Translating finite-domain integer constraint models to CP/SMT/ILP/PB/SAT solvers with CPMpy Authors: Tias Guns, Ignace Bleukx, Hendrik Bierlee, Jo Devriendt, Emilio Gamba, Orestis Lomis, Wout Piessens, Thomas Sergeys, Dimos Tsouros, Wout Vanroose, Hélène Verhaeghe Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15143v1 Constraint solving is a declarative approach for solving combinatorial satisfaction and optimization problems. The user specifies their problem through constraints and decision variables, and a generic solver is used to find a solution. Several constraint-solving technologies exist, and certain solvers perform well on certain problems. Therefore, it is useful to try different solvers given a particular application. However, each solving paradigm supports different types of constraints and decision variables. Our goal is to translate high-level constraint satisfaction and optimization problems into any lower-level formalism, including CP, SMT QF-LIA, ILP, PB and (Max)SAT. This allows for comparing different solving technologies for a particular problem, without requiring a user to manually remodel it for each solving paradigm. We define a high-level language of logical and arithmetic operations, and useful additional functions and constraints, which are known as global constraints in the CP community. We then present a modular framework for transforming our high-level modeling language to CP/SMT/ILP/PB and (Max)SAT solvers. While many transformations are partly described in the literature, we observe that they can be implemented through a modular waterfall of smaller components, where lower-level paradigms reuse the transformations of higher-level paradigms. Two recurring challenges are handling the negation of arbitrary subexpressions and avoiding the introduction of auxiliary variables. Additionally, we take special care linearizing non-linear operators for ILP, PB and SAT-solvers. The transformation waterfall is implemented and evaluated in the open-source CPMpy library. Our results show that constraint models significantly change throughout the transformations, and that optimizations to the linearization of constraints are essential for ILP and PB solvers. --- ### HOIMask: Towards Generative Masked Modeling for Human Object Interaction Generation Authors: Yihong Ji, Jinsong Zhang, He Hu, Hongbo Xu Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15141v1 Diffusion-based methods have dominated the HOI generation, as they enable critical contact fusions or signals to guide the diffusion process. However, they often result in high artifacts and unstable interaction quality due to error accumulation during iterative denoising. In this work, we propose HOIMask, the first generative masked framework for modeling HOI motion in discrete space. HOIMask first encodes both motion sequences and contact-aware signals into discrete 2D human and object token maps via HOI Vector Quantization (VQ), preserving fine-grained spatial-temporal structure beyond conventional 1D representations. On this basis, a generative masked modeling framework is employed to jointly capture human-object interaction dynamics, leveraging a transformer architecture designed to model complex spatial-temporal and interaction dependencies. To generate more coherent and physically plausible motions, we further introduce a novel contact-aware reconstruction guidance in discrete space during inference, which fuses contact signals to optimize HOI tokens that forces the generated motion with higher spatio-temporal consistency. With craftily designed motion interaction tokens, dedicated architecture and guidance strategy, HOIMask outperforms state-of-the-art diffusion-based methods, generating more realistic and semantically aligned HOI motions. Please refer to https://jyhflash.github.io/HOIMask/ for more results. --- ### ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Edits Authors: Zhiqiang He, Zhi Liu Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15138v1 Designing an ABR algorithm for one network scenario takes an engineer months, and large language models now do this work in hours, matching or beating hand-built designs. But either way, the design fits only the world visible at its birth, and fails on the world that arrives after. We ask whether an ABR algorithm can keep pace with the world, redesigned in minutes as each scenario arrives, with every change proven harmless to every scenario already served. In this work, we propose ReForge, a continual heuristic learning framework that adapts to continuously changing scenarios. ReForge runs that routine with a large language model (LLM) in the loop. Each round the LLM reads where the current design falls short and proposes one small edit, and a replay over every network served so far decides. Specifically, what it edits is a single page of fuzzy rules that routes every decision to one of a frozen pool of pre-trained policies. The LLM writes the first page from measurements alone, then keeps improving it on its own. Each round it reads where the current rules fall short and proposes one small edit, and a replay over every network served so far decides whether the edit lands. We evaluate ReForge on nine real-world network families arriving one at a time as 3G, 4G, then 5G. A few edits per arrival lift mean QoE from 1.23 to 1.74, past the best single policy at 1.66 and to 94\% of an oracle, and even repair families the loop never saw, one rising from 0.30 to 0.80. All code, data, and experiment records will be open-sourced upon cleanup. --- ### Platform Adaptation Under Governance Interventions: Actor Best-Response Modeling and an External Public-Case Benchmark Authors: Wesley Shu, Peng Wei Published: 2026-08-15 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.15131v1 Digital platforms govern by changing rules: rankings, monetization thresholds, moderation standards, verification systems, disclosure requirements, appeal processes, and access policies. These interventions are rarely absorbed passively. Creators, sellers, advertisers, moderators, users, developers, and strategic operators adapt to the new reward surface. This paper develops a platform-adaptation model for evaluating governance interventions as transitions in adaptive multi-actor information systems. The model represents actor best response, strategic gaming opportunity, moderation burden, user-incentive movement, enforcement response, externality formation, and downstream platform stability. We evaluate the model on 72 external public platform-governance cases covering media monetization, ranking systems, verification, delivery platforms, marketplaces, app stores, community platforms, and creator ecosystems. Across 9 methods and 648 method-case evaluations, the full platform-adaptation simulator achieves mean adaptation quality of 0.836338, compared with 0.669731 for a risk-register baseline, 0.589457 for causal-loop analysis, 0.492750 for generic governance critique, 0.369492 for engagement-only optimization, and 0.331965 for baseline policy review. Paired comparisons show a win rate of 1.00 against all tested baselines and channel ablations. The contribution is an information-systems theory and measurement framework showing why platform governance evaluation fails when it treats policy rules as static controls rather than interventions into adaptive actor-response fields. --- ### Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models Authors: Varvara Arzt, Allan Hanbury, Terra Blevins Published: 2026-08-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.15129v2 We systematically compare word order preferences in decoder-only language models across 192 artificial languages and typologically diverse natural languages. On artificial languages, models exhibit a left-branching preference that aligns with neither natural language universals nor human word order learning biases. On natural languages, monolingual models show no clear base word order bias at small scales, but as data grows, a preference for right-branching subject-verb-object (SVO) languages emerges while SOV falls behind despite being the most frequent order cross-linguistically. This SVO advantage extends to multilingual models and correlates with language resource level and data quality rather than word order. Thus, the same architecture exhibits opposite preferences on artificial and natural languages, establishing that word order biases observed in practice are data-driven. Since highly-resourced languages are overwhelmingly SVO, these biases risk gradually reducing word order diversity, particularly in languages that productively use multiple word orders, with the widespread adoption of LLMs. --- ### From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems Authors: Chaokun Chang, Yukun Zhou, Kaihua Fu, Dakai An, Tianyu Feng, Hanfeng Lu, Sheng Yao, Pu Guo, Yinghao Yu, Yizhou Shan, Bo Li, Binhang Yuan et al. Published: 2026-08-15 Categories: cs.OS, cs.AI, cs.DC, cs.MA arXiv: https://arxiv.org/abs/2608.15127v1 Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state. However, the system behavior of these workloads---where latency, cost, and bottlenecks arise---remains poorly characterized, leaving serving systems to rely on assumptions built for conventional inference. We present AgentSysBench, a benchmark suite and measurement toolkit with ten representative agentic applications and unified systems-level instrumentation. Across controlled deployments and production traces, we identify six properties that distinguish agentic workloads from conventional LLM serving: (1) execution is heavyweight and stateful, with non-LLM components dominating latency in 5 of 10 applications and sandbox working-set memory peaking at 28 GB per session; (2) applications compose components with heterogeneous resource affinity---GPU-bound inference, memory-bound retrieval, CPU-bound sandboxes---whose task latencies diverge by up to 32x; (3) bottlenecks shift across requests, models, and deployments; (4) production sessions hold state idle for minutes to hours between active steps; (5) a control-plane tax---auxiliary LLM calls and context overhead from tool schemas and observations---crowds out productive compute and context; and (6) production traces from three applications reveal heavy cross-request redundancy in search queries and web fetches, exposing a large caching opportunity. Four design explorations demonstrate that these findings are actionable: task-aware serving reduces latency by 29--40%, communication-aware placement by up to 4.5x, state offloading reduces memory usage by 4.6x, and tool-result caching removes 35.2% of redundant search calls and saves 19.3% of aggregate search latency. --- ### Decision-Driven Regularization: A Blended Model for Learning and Optimization Authors: Gar Goei Loke, Qinshen Tang, Yangge Xiao, Xun Zhang Published: 2026-08-15 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2608.15124v1 In contextual optimization, the decision-maker seeks optimal decisions to minimize a cost function, that varies based on observed features. This context is common in many business applications ranging from on-demand delivery and retail operations to portfolio optimization and inventory management. In this paper, we study the learning and optimization approach, which first learns how outcomes result from the features, and then selects optimal decisions based on these outcomes. We focus on the integrated learning and optimization literature, and identify that a lack of control for prediction accuracy can lead to overfitting and a loss of decision effectiveness against simple separate learning and optimization models. Instead, we propose a bi-objective formulation that balances prediction accuracy and cost minimization, termed decision-driven regularization. It also addresses ambiguity in the definition of the cost function via a surrogate that depends on a new hyperparameter. We additionally show that alternative perspectives for formulating the problem, namely robust optimization and regret minimization, lead to models that are closely related to our proposed model. As a consequence, our framework generalizes models such as SPO+. Our model is shown to be numerically superior to other benchmarks, such as OLS, Random Forest, XGBoost, SPO+, Perturbation Gradient, and Learning and Rank, in our synthetic studies. --- ### Sufficient Dimesion Reduction via Generalized Stein's Lemma Authors: Ye Tian Published: 2026-08-15 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2608.15121v1 Sufficient dimension reduction (SDR) seeks the minimal subspace of the predictors that captures the full conditional distribution of the response, which is known as the central subspace (CS). When the response is multivariate, the problem becomes considerably more challenging, particularly when the sample size is limited. Existing methods face different limitations:inverse regression approaches rely on strong distributional assumptions and matrix inversion, and their multi-response extensions suffer from severe slice sparsity; forward regression methods depend on computationally intensive iterative smoothing whose cost grows with the response dimension; and deep learning-based approaches demand large amounts of labeled data. To circumvent these shortcomings, we propose an SDR framework based on the generalized Stein's lemma. Our method constructs a cross-moment matrix between the multivariate response and the marginal score function of the predictors, and recovers the CS via its singular value decomposition. The proposed method does not rely on the linearity condition, avoids matrix inversion as well as iterative smoothing, and can leverage unlabeled data when available. We establish convergence guarantees for the proposed estimator under standard regularity conditions. Moreover, we propose a practical rank-selection algorithm to estimate the dimension of the CS. Extensive simulation studies and a real data application demonstrate that the proposed methods consistently outperform existing approaches across a variety of settings, particularly in moderate-dimensional, label-scarce scenarios with high noise levels. --- ### Anatomy of a Quantized Agent: VRAM Stability and Forecasting in Code-Synthesis Agentic Workloads Authors: Anubhab Banerjee Published: 2026-08-15 Categories: cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2608.15117v1 Analytical models of peak VRAM consumption for LLM inference decompose memory into weight-storage, KV-cache, and activation terms parameterized by step count, tool invocations, and context expansion. We evaluate this decomposition empirically within a strictly scoped measurement study: a LangGraph-based CUDA-kernel-synthesis agent (AgentK), a 4-bit quantization family (Q4 K M), a single NVIDIA H100 GPU, and four LLM backbones across 1,920 trajectories. Focusing on peak-memory forecasting behavior, we report two primary observations. First, closed-form analytical models achieve competitive accuracy when provided with two empirical constants: loaded-weight VRAM and a fixed activation-memory overhead. Supplied with live GPU readings and ground-truth trajectory parameters, the closed-form model matches or outperforms the best learned baseline on three of the four backbones (test MAPE 2.2-4.4% vs. 3.4-6.5%, p = 0.76). The exception is the smallest backbone (Phi-4-mini), where minimal VRAM variance (CV 0.3%) causes dynamic modeling to underperform simple regression. Second, compile success strictly bifurcates by backbone capacity (from 5.7% for Phi-4-mini to 62.0% for Qwen2.5-Coder-14B), demonstrating that functional code synthesis remains constrained by intrinsic LLM capabilities rather than available memory. Furthermore, because overall peak-memory variance is remarkably low across all backbones (CV 0.3-9.4%), learned prompt-feature regression offers statistically insignificant improvements over a constant-mean baseline. Consequently, we find no justification for deploying complex predictive VRAM models in highly quantized, weight-dominated regimes. We release the evaluated corpus and anonymized framework to support replication. --- ### Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples Authors: Kaisheng Liang, Yiming Cao, Bin Xiao Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15115v1 Adversarial examples generated on a surrogate deep neural network (DNN) can often successfully fool other black-box DNN models. This cross-model transferability poses serious security threats to DNNs in practical applications. Input transformation techniques are widely used to enhance adversarial transferability by increasing the diversity of input images. However, existing methods primarily rely on local operations with limited degrees of freedom (DOF), such as block-wise shuffling and resizing, overlooking global perspective transformations that naturally arise from viewpoint changes. In this work, we propose a Perspective-Invariant Attack (PIA), which introduces a multi-DOF vertex sampling strategy that systematically covers the perspective transformation hierarchy from 2-DOF translation to 8-DOF projective mapping. By generating geometrically diverse input variations, PIA effectively reduces overfitting of adversarial perturbations to the surrogate model, thereby improving adversarial transferability. We further propose PIA-Mix, a generic extension that maintains a complementary transformation pool and efficiently combines our perspective transformation with auxiliary methods for improved transferability. Extensive experiments involving various DNN architectures, advanced defense mechanisms, and multimodal large language models (LLMs) demonstrate that PIA and PIA-Mix outperform state-of-the-art transfer-based attacks. --- ### Fast Test-Time Refinement for Robust Learned Image Compression Authors: Jiaming Liang, Chi-Man Pun, Weisi Lin Published: 2026-08-15 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.15113v1 Learned image compression (LIC) has demonstrated remarkable rate-distortion (RD) performance in benign settings. However, the high representational capacity endowed by deep neural networks (DNNs) comes at the expense of increased adversarial vulnerability. This hinders their adoption as trusted standardized codecs. Recent work has sketched test-time refinement (TTR) as a defense in gray-box scenarios, despite its original purpose of improving benign RD performance. Unfortunately, extensive iterations of TTR incur prohibitive overhead, while the robustness mechanism lacks theoretical understanding. Moreover, TTR has not been evaluated in white-box settings or against attacks beyond $\ell_2$-bounded rate and untargeted distortion objectives. To bridge these gaps, we present a systematic study. Our study reveals an Asymmetric Adversarial Trajectory (AAT) property in LIC systems: transitioning from adversarial to benign regions is significantly easier than the reverse process, where adversarial examples can often be roughly recovered within only 1-2 steps. We provide a two-dimensional Tube Model to explain this phenomenon. Based on AAT, we propose a Fast Test-Time Refinement (FTTR) framework for practical and robust LIC systems. We establish that the robustness arises from the contraction of adversarial regions induced by the Input-as-Label property of LIC systems, rather than from obfuscated gradients. Extensive evaluations with diverse strong adaptive attacks across multiple LIC systems demonstrate the promise of the proposed FTTR framework. The code is available at https://github.com/chinaliangjiaming/FTTR.git. --- ### Probability-Preserving Transformer for the Time-Dependent Schrödinger Equation Authors: Mushtaq Ali, Muzamil Tariq, Niaz Ali Khan Published: 2026-08-15 Categories: cs.LG, math-ph, quant-ph arXiv: https://arxiv.org/abs/2608.15112v1 Solving the time-dependent Schrödinger equation (TDSE) via traditional numerical methods is computationally intensive. Transformer models offer a compelling alternative, but standard implementations rely on soft constraints that cannot rigorously guarantee probability conservation. Here, we introduce a Transformer architecture that enforces TDSE probability conservation as a hard constraint. The design intrinsically ensures unitarity across temporal evolution without requiring repeated retraining. Our empirical findings show that this hard-constraint approach is not only physically exact but also computationally superior to conventional soft-constraint methods. --- ### CETalk: Continuous Valence-Arousal Control for Audio-Driven 3D Talking Head Generation Authors: Peng Jia, Li Dai, Zhen Xiao, Xueliang Liu, Jia Li Published: 2026-08-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.15110v1 Emotional 3D talking head generation aims to synthesize expressive facial animations with accurate lip synchronization. However, existing methods often rely on discrete emotion categories, which fail to capture the continuous evolution of affect. They also overlook the temporal frequency mismatch between audio articulation and emotional expression. In this paper, we propose CETalk, an audio-driven 3D facial animation framework conditioned on continuous Valence--Arousal (VA) representations for fine-grained emotion control. CETalk predicts a sequence of FLAME parameters through three key components: a Dynamic Emotion Modulation Module that adaptively scales emotional intensity using audio-derived cues; a Multi-Scale Temporal Modeling mechanism that employs parallel branches to decouple high-frequency articulatory movements from low-frequency emotional dynamics; and a Dynamic Fusion Mechanism that integrates these multi-scale features via an adaptive gating network. To support training and evaluation, we construct 3D-VA-MEAD, a large-scale dataset with automatically estimated VA annotations and reconstructed 3D facial motions. Extensive experiments demonstrate that CETalk outperforms state-of-the-art methods in both lip-sync accuracy and emotional expressiveness, while enabling smooth and controllable emotion transitions. --- ### Constraint-Aware Synthetic Tabular Data Generation via Inter-Column Constraint Discovery with LLM Agents Authors: Jianxing Zhao, Mao Guan, Dongyu Liu Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15109v1 Generating structurally valid synthetic tabular data remains difficult: outputs with high statistical fidelity and downstream utility can still violate semantically meaningful domain constraints. We study the discovery and enforcement of three complementary inter-column constraint families---equations, linear inequalities, and logical dependencies. Our unified tool-grounded workflow represents all three as machine-executable hypotheses and applies a common interface for full-table validation, deterministic diagnosis, and counterexample-guided revision. A generator-agnostic postprocessor coordinates family-specific repairs on outputs from unchanged tabular generators. Across curated behavioral audits and end-to-end evaluations, the complete workflow improves held-out violation detection over one-shot direct prompting, while postprocessing yields zero measured violations for every retained, applicable constraint, improves downstream utility on most datasets, and largely preserves univariate marginals. --- ### Beyond Direct Access: Resource Hijacking in LLM Agents Authors: Puyu Zeng, Qibing Ren Published: 2026-08-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.15108v1 Large language model agents are increasingly connected to high-value resources such as computing infrastructure, credentials, usage budgets, identities, private knowledge, communication channels, and organizational workflows. Existing agent security research mainly studies attacks on instructions, data, and tool behaviors, while high-value resources accessible to agents have received much less attention as direct attack targets. We are the first to identify and systematically study agent resource hijacking, a security blind spot in which attackers induce agents to invoke, consume, transfer, or control high-value resources for their own goals without directly obtaining those resources or their credentials. To study this threat, we introduce ResourceHijackBench together with an automated pipeline for generating resource hijacking cases. We organize high-value agent resources into six categories and construct 300 attack scenarios with 900 attack prompts. Each case runs in an isolated local environment that records actual resource use, allowing attacks to be evaluated from agent behavior rather than text responses alone. Without additional defenses, OpenClaw reaches an average attack success rate of 84.06%. The attack remains effective across different model backends, with average success rates ranging from 69.98% to 89.58%. Existing defenses reduce part of the risk, but the strongest evaluated defense still leaves an average attack success rate of 55.11%. These results show that high-value resources accessible to agents form an important and previously overlooked attack surface, and that current agent defenses are not sufficient to protect them from resource hijacking. --- ### Global Federated Learning Strategies for Building Efficient Personalized Models Authors: Seongyoon Kim Published: 2026-08-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15107v1 Federated learning (FL) is a practical framework that can train models on distributed user data while guaranteeing data privacy; however, due to heterogeneity in which each user has a different data distribution, problems frequently arise where both global and personalization performance deteriorate simultaneously. This dissertation presents methodologies for building efficient personalized models by identifying which strategies are effective in the global training stage and by showing how to preserve global knowledge while securing user-specific performance during local adaptation. First, we show that as data heterogeneity increases, the collapse of feature vectors is a more fundamental bottleneck than classifier weights, and propose a method that directly mitigates the discrepancy in representation magnitude between local and global models. Second, we analyze that a training approach that strengthens local alignment can induce forgetting of global knowledge (e.g., categories not observed locally), and propose a method that achieves both local alignment and global knowledge preservation by combining feature distillation based on the global model's feature vectors. Third, in federated personalized reward model learning with preference heterogeneity, we empirically verify the conventional belief that "increasing the number of global models yields better initialization," and we show that when sufficient local fine-tuning is allowed, a single global initialization can instead provide stronger personalization performance. This study redefines the role of global initialization under data and preference heterogeneity and provides practical training strategies that simultaneously satisfy global knowledge preservation and personalization. --- ### EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations Authors: Tanapat Ratchatorn, Masayuki Tanaka Published: 2026-08-15 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2608.15105v1 Recent progress in optimization research has highlighted the sharpness of the loss landscape as a key factor in narrowing the generalization gap. Motivated by this insight, Sharpness-Aware Minimization (SAM) was proposed as a training strategy that enhances generalization. Despite the promising performance, SAM suffers from its twice computational cost due to its core algorithm requiring an extra gradient computation during the perturbation step. To overcome this limitation, we introduce Exponential Moving Average Sharpness-Aware Minimization (EMASAM), a computationally efficient variant of SAM. EMASAM does not require the loss gradient in the perturbation step. Instead, EMASAM defines the perturbation direction based on the discrepancy between the main model and the EMA shadow model. This perturbation travels away from the stable average position toward the less stable area, acting as a softer yet cheaper alternative to SAM's worst-case scenario perturbation. Moreover, since EMASAM's perturbation does not rely on noisy mini-batch gradients, it mitigates the gradient-induced instability inherent in SAM. Hence, EMASAM eliminates the need for an extra backpropagation while also preserving the generalization ability of the SAM-style training. Several experiments have been performed and confirm the efficiency and robustness of our method. --- ### ProjFormer: Point Cloud Completion via Geometric-Projective Transformer and Cross-Modal Semantic Constraints Authors: Sheng Liu, Meng Wang, Ruihui Li, Huilong Pi, Zhuo Tang, Kenli Li Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15104v1 Point cloud completion is inherently ill-posed due to severe sparsity and ambiguity in partial observations. Existing multi-view methods alleviate this by incorporating 2D semantics, but often rely on learned attention and fixed fusion, which lack geometric consistency and adaptability. We propose ProjFormer, a cross-modal framework that enforces geometry-consistent 2D-3D interaction through explicit projection and adaptive feature routing. A Projective Guided View Attention module aligns 3D points with multi-view features via deterministic projection, enabling efficient and geometrically consistent aggregation. Building on this, a geometry-aware routing network performs point-wise adaptive fusion of structural and observation-driven features for progressive refinement. Experiments show that, under a lightweight design, ProjFormer delivers competitive performance with improved structural completeness. --- ### A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models Authors: Amrit Gopinath, Raghul, Durairaj Thenmozhi Published: 2026-08-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.15102v2 We investigate whether Mixture-of-Experts (MoE) language models develop linguistically structured expert routing during bilingual language acquisition. Inspired by the Declarative-Procedural framework, we analyze lexical, grammatical, and syntactic processing in a decoder-only English-German MoE Transformer trained under sequential language exposure. We construct a probe-based validation set and extract token-level routing distributions to quantify category-dependent specialisation using mutual information, routing entropy, and Jensen-Shannon distance. The curriculum-trained model exhibits a peak mutual information of 0.1148 at layer 5, indicating category-dependent differences in routing distributions across linguistic categories. Surprisingly, a no-curriculum baseline trained on mixed English-German data shows stronger aggregate specialisation, reaching a peak mutual information of 0.2599 at the same layer. These results suggest that interpretable linguistic organization emerges within MoE routing patterns even without sequential language exposure. A replication at a second training seed shows that the no-curriculum condition's specialisation concentrates on a single language whose identity is seed-dependent, whereas the curriculum consistently yields a stable, language-balanced routing profile; rather than uniformly increasing specialisation, staged bilingual exposure reduces single-language dominance. The official Github repository: https://github.com/Amrit828/DP-Theory-MOE-Interpretability-Research --- ### Second-Order Policy Effects as State Transitions: A Source-Linked Benchmark for Policy Simulation Authors: Wesley Shu Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15101v1 Policy evaluation often estimates direct benefits and costs while treating the institutional environment as fixed. In practice, a policy changes the system it enters: actors adapt, enforcement capacity shifts, burdens move, and new equilibria form around capture, gaming, compliance theater, irreversibility, and repair costs. We formalize this as second-order policy-effect prediction and present a source-linked benchmark for policy simulation. The benchmark contains 96 named public-policy cases across eight domains and four balanced action classes: implement, modify, pilot, and block. Each case includes source locators and state variables for benefit, capture, gaming, burden shift, instability, uncertainty, irreversibility, distributional risk, and implementation capacity. The runner regenerates method outputs and aggregate results from the case table, and the simulator never reads the expert action target. We report a protocol-based transition-channel audit with recall, precision, F1-style efficiency, and selective top-channel stress diagnostics, so universal channel coverage is not mistaken for field validation. The side-effect simulator achieves mean policy-effect quality of 0.945, compared with 0.838 for the risk-register baseline and 0.879 for the causal-loop baseline. Its advantage is concentrated in side-effect recall and aggregate transition scoring; it does not dominate the best structured baselines on exact policy-action choice. The evidence remains benchmark-based, but supports a bounded claim: transition-state variables make policy simulators more sensitive to downstream institutional effects. --- ### MODAL: Multi-Modal Object Re-ID via Model-Driven Sparse Decoupling and Text-Image Differential Filtering Authors: Chengbo Huang, Jun-Jie Huang, Long Lan, Tianrui Liu, Xueqiong Li, Yuanxi Peng, Xinwang Liu, Meng Wang Published: 2026-08-15 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2608.15096v1 Multi-modal object re-identification (Re-ID) aims to facilitate cross-camera object retrieval in complex environments by leveraging complementary information from visual (e.g., RGB, NIR, TIR) and textual modalities. However, existing approaches often lack principled feature disentanglement and coherent multi-modal integration, leading to entangled representations that introduce cross-modal conflicts, obscure discriminative cues, and suffer distribution shift under modality-missing conditions. To tackle these challenges, we propose MODAL, a novel multi-modal object re-identification framework, grounded in coupled sparse coding theory and differential suppression principles. A core component of MODAL is a Multi-modal Feature Sparse Decoupling module, developed in a model-driven deep unrolling manner based on multi-modal coupled sparse coding. It explicitly decomposes multi-modal features into uni-modal specific, bi-modal and tri-modal shared representations, thereby achieving more transparent and effective feature disentanglement. Benefiting from the principled feature disentanglement, MODAL naturally mitigates performance degradation in incomplete-modality scenarios via a Modality-Aware Subspace Activation that selectively activates only the consistently shared subspaces. Moreover, we propose a Text-Image Differential Filtering module that leverages coarse-grained textual semantics to adaptively suppress task-irrelevant responses in the decoupled visual representations, thereby enhancing discriminative information. Extensive experiments on four datasets demonstrate that MODAL achieves state-of-the-art performance with superior transparency. --- ### Validation-Frontier Representation Selection under Constrained Observation Authors: Wesley Shu Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15095v1 AI systems deployed outside clean benchmark settings often rely on observations that are incomplete, unstable, costly, or degraded by monitoring failures. This paper studies representation selection under constrained observation: choosing a state representation when raw accuracy is not the only operational criterion. We propose a validation-frontier selector that combines balanced accuracy with penalties for feature cost, overfit gap, and validation-test instability. In a focused public-tabular benchmark using three scikit-learn datasets, five observation regimes, 45 matched task cells, 720 candidate actions, and 405 representation rows, the adaptive selector improves frontier score over full trace features by 0.025801 while reducing mean feature count by 22.733. Balanced-accuracy difference is small and not statistically significant. A broader offline stress test gives mixed results. The supported claim is therefore bounded: adaptive representation selection can improve a constrained-observation robustness-efficiency frontier in matched benchmark settings, but does not universally dominate trace baselines. --- ### WeSCE: A Benchmark for Measuring Security Drift in LLM-Driven Code Editing Authors: Zhiyu Zhang, Tingyue Wen, Senke Sun, Dengxiang Liang, Enhao Huang Published: 2026-08-15 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.15092v1 In this work, we introduce WeSCE, a benchmark for quantifying security drift in code editing under weak-security constraints, where tasks specify only functional objectives without explicit security requirements. WeSCE consists of 400 executable programs derived from real-world code, covering feature addition, feature removal, bug fixing, and refactoring. To quantify security drift, we propose a continuous risk representation that aggregates heterogeneous vulnerability signals through a unified formulation, and define drift measures capturing changes in overall risk, worst-case severity, and vulnerability distribution under code transformations, providing a multi-scale view of security spanning average-case behavior to worst-case emphasis. --- ### Distribution-free false-alarm calibration and chance-corrected spatial evaluation for industrial anomaly detection Authors: Jie Deng Published: 2026-08-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.15090v1 Studies of industrial visual inspection commonly report the area under the receiver operating characteristic curve (AUROC) and the overlap between anomaly maps and defect masks. Neither measure specifies the false-alarm rate at a selected threshold, while recurrent defect locations and mask geometry can inflate overlap. We combine a distribution-free upper tolerance threshold with a paired-minus-crossed spatial test. This test compares each detector's score-contributing locations with the matched defect mask and with masks from other images; the difference in rates defines spatial-evidence lift relative to the empirical chance-overlap rate. We evaluate three detectors on 120 point-defect images from three ISP-AD modalities and three fixed data splits. Of 378 alarms, 230 overlap the matched mask. Paired and crossed rates are nevertheless similar in eight of nine detector--modality cells; only DINOv2--ASM has a positive 95\% bootstrap lower bound (lift 0.259, 95\% interval 0.159--0.347). On the independent Magnetic Tile Defect dataset, the same analysis gives lifts of 0.203 (0.169--0.236) for Wide ResNet-50 (WRN50) patch memory and 0.231 (0.202--0.262) for Vision Transformer B/16 (ViT-B/16) patch memory, with one-sided permutation $p=10^{-5}$ for both. When crossed masks are restricted to the same defect class, the lifts remain 0.185 and 0.210. Exact sample planning shows that, with 150 calibration normals, a 95\%-confidence distribution-free claim is supported only for target false-positive rates of 1.98\% or higher; a 1\% target requires at least 299 normals. The results support reporting operating-point performance and chance-corrected spatial evidence alongside AUROC and raw mask overlap. --- ### StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Authors: Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang, Kai Wang Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15089v1 Long-horizon agents can fail even when their underlying models can solve the constituent steps. They may lose track of mutable state, fail to reactivate lessons from earlier executions, skip known procedures, or stop prematurely. We bet on harness scaling to improve the execution system around an agent without changing its model weights. We introduce StateM, an agent-native runtime that organizes execution around durable states, phase-local context, checked transitions, recoverable runbooks, and versioned procedural practices that agents and users can inspect together. On Terminal-Bench 2.1, StateM raises GPT-5.5 xhigh to 92.1\%, versus 83.1\% reference and GPT-5.6 Sol Ultra at 91.9\%. The runbook transfers unchanged to GPT-5.6. With GPT-5.6 Sol xhigh, StateM reaches 95.3\% raw accuracy across 445 trials and succeeds on all 89 tasks at least once. The frozen profile raises GPT-5.6 Luna from 76.7 to 85.4\%, above the 84.9\% Sol xhigh reference. Using the same runtime, runbook structure, and golden rules, less than \$38 of adaptation raises DeepSeek-V4 Flash from 82.7 to 88.1\% under standard timeouts and to 89.1\% on an 88-task common core. Extending only the remaining latency-sensitive task matches the reported 88.8\% GPT-5.6 Sol max result. Final-score API usage is about \$15 versus \$574.68 for the GPT reference; total DeepSeek expenditure is \$52.22. On BusinessBench, family-specific runbooks built on development sets yield held-out gains of 0.55 macro and 1.34 micro points; two mechanism-matched families improve by 10.04 points. Concrete rules generalize when tasks share execution structure, while the control methodology applies broadly. StateM turns selected postmortem findings into persistent, executable preconditions and practices, making learned controls explicit and enforceable through stateful controls. Code at github.com/henryqin1997/statem. --- ### Max-Q Selective Imitation for Human-in-the-Loop Online Robot Learning Authors: Zihang Wang, Yishan Wang Published: 2026-08-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.15088v1 Human-in-the-loop (HIL) online reinforcement learning for real robots must absorb human interventions quickly while continuing to improve beyond the human prior. We present a training method for this setting based on two components. First, an \emph{MC Q-chunk} critic regresses chunk-level action values onto Monte Carlo returns from the replay buffer, performing sample-average (behavior) policy evaluation so that intervention trajectories are credited directly rather than diluted by current-policy TD backups. Second, \emph{max-Q selective imitation} updates the actor by imitating, at each state, the higher-$Q$ action between the current policy action and a buffer sample under a hard winner-take-all rule. This rule automatically switches between learning from interventions and on-policy self-improvement: when the autonomous policy is stronger, targets align with the policy distribution, reducing the policy--target-sample gap that otherwise induces execution-time distribution shift. In practice we score candidates with a standard critic ensemble mean to reduce comparison noise, without softening targets or introducing score-gap thresholds. On a real USB pick-and-insertion task with 20 demonstrations, ACT QChunk-MCBC attains 99\% success within 30 minutes of HIL training, whereas HIL-SERL requires about 5 hours to converge. In simulation on Peg Insertion and Square, ACT/Flow Q-chunk variants similarly reach $\ge$96\% success within roughly half an hour of effective training, outperforming HIL-SERL, EXPO, and E2HiL on the success--time frontier. --- ### Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs Authors: Yihang Du, Juhao Liang, Zhengzhao Lai, Siyu Li, Yan Hu Published: 2026-08-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.15085v1 Multimodal large language models (MLLMs) exhibit substantial performance degradation in non-English visual reasoning, despite the strong multilingual competence of their text-only backbones. While mechanistic evidence from text-only models suggests that non-English inputs are routed through an English-centric latent space, the multimodal implications of this phenomenon remain unexplored. Through rigorous mechanistic analysis, we identify the \textbf{Ghost Anchor} phenomenon: a temporal modality asynchrony where linguistic translation to the English semantic manifold completes in early layers, while visual semanticization remains immature. Consequently, visual signals are physically present yet functionally invisible during the early alignment window. To rectify this, we propose \textbf{ANCHOR}, a training framework employing Proactive Visual Anchoring (PVA) to accelerate early visual semantic emergence, ensuring visual representations proactively guide linguistic translation. Mechanistic interventions confirm that ANCHOR successfully restores the causal influence of visual signals during early translation. Furthermore, extensive experiments on XMMMU, MaXM, and CVQA demonstrate that ANCHOR consistently outperforms standard baselines, achieving robust visual reasoning across both fine-tuned and zero-shot languages. --- ### GATTA: Graph Active Learning with Test-Time Augmentation Authors: Zsombor Bánfi, András Gézsi, András Formanek Published: 2026-08-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.15084v1 Test-time augmentation (TTA) has proven effective for improving model robustness and uncertainty estimation in computer vision, yet its application to graph-structured data remains largely unexplored. We introduce GATTA (Graph Active Learning with Test-Time Augmentation), a framework for enhancing active learning by aggregating predictions across multiple augmented views to produce more reliable uncertainty estimates. To address the challenge of label-preserving graph augmentations, GATTA incorporates a consistency-based filtering mechanism that discards augmented views yielding unreliable predictions. We systematically evaluate GATTA across multiple graph datasets, GNN architectures, and acquisition strategies. Our results show that simple uncertainty-based methods, such as Entropy and Least Confidence, benefit most from TTA, achieving performance competitive with more sophisticated and computationally expensive approaches. GATTA generalizes across architectures, outperforms model-side ensemble methods such as MC Dropout. We further show that GATTA scales efficiently with both ensemble size and graph size. Extensive analysis of augmentation types, strengths, and filtering strategies provides practical guidelines for effective deployment. Our findings demonstrate that augmenting simple methods with TTA offers a more efficient path to strong active learning performance than engineering complex acquisition functions, enabling practitioners to achieve competitive results with lower computational overhead and reduced implementation complexity. --- ### Beyond Thresholds: A Quality-Aware Decision Intelligence Framework for Cold Chain IoT Systems Authors: Aashna Sofat, Balwinder Sodhi Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15082v1 Cold chain logistics has advanced technologically, yet most deployed systems remain reactive monitors, not decision-making agents: thresholds trigger alerts, but nothing relates violations to cumulative product degradation or converts degradation signals into logistics decisions. We address this gap with a Quality-Aware Decision Intelligence (QADI) framework combining three capabilities: a structured quality state representation, $S_q = (L, Q, U, R)$ -- remaining shelf life, degradation rate, estimation uncertainty, and operational risk, all derived and computable from the framework equations; a hybrid quality modeling layer combining physics-based microbial kinetics with a data-driven correction term; and a reasoning layer built on Microsoft Phi-4~\cite{Phi4} with retrieval-augmented generation over a structured domain knowledge base. We benchmark against five baselines -- threshold monitoring, physics-only, physics-plus-noise, optimisation-based decisions, and a rule-based expert system -- across eight cold chain scenarios, using pasteurised milk as the primary case, with ground truth shelf-life drawn from published dairy studies~\cite{Singh1994, Smigic2015} independent of our model. Comparisons use Wilcoxon signed-rank tests with Holm correction. Across milk and broccoli scenarios, the framework attains mean absolute shelf-life error of 7.2 hours (versus 30.9 hours, physics-only; $p<0.001$), spoilage rate of 14.5% (versus 16.6%, physics-only and rule-based; p=0.08), and oracle-optimal decisions in 99.5% of scenarios. Removing the LLM reasoning component drops optimality to 45.5% ($p<0.001$). Expert-rated explanation quality reaches 83% ($κ= 0.71$). Ablations show hybrid modeling and LLM reasoning contribute distinct gains, while RAG retrieval mainly drives explanation quality. Code: https://bit.ly/4d6t44C. --- ### A Pilot Study of Autocompleting Tokenizers Authors: Samuel Wexler, Mark Hopkins Published: 2026-08-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.15080v1 Modern input methods routinely rely on autocomplete to omit information that can be recovered from local context. Inspired by these autocomplete-assisted writing systems, we investigate whether Transformer inputs can be compressed in a similar manner. Byte-level tokenization offers a simple and language-independent alternative to subword tokenization, but its longer input sequences typically result in increased computational cost and reduced model quality. We propose a compression scheme that employs a lightweight autoregressive byte language model to identify and remove bytes that are easily predictable from their surrounding context before Transformer processing. The resulting compressed representation is then provided as input to a standard encoder--decoder Transformer. Experiments on machine translation show that a substantial fraction of source-language bytes can be omitted without degrading translation quality. On English--French, our best method preserves translation performance while reducing source sequence length by nearly one-third. Additional experiments on Finnish--English, Russian--English, and Chinese--English demonstrate that the approach generalizes across diverse writing systems and morphological typologies, yielding comparable or improved translation quality at compression ratios between 0.47 and 0.67. These findings suggest that many input bytes are predictable enough to be represented implicitly rather than explicitly, providing a simple mechanism for reducing the sequence-length overhead associated with byte-level models. --- ### SA-GEM: Scale-Adaptive and Geospatial Evidence-Modulated Token Pruning for Efficient Remote Sensing Large Vision-Language Models Authors: Kexin Ma, Jing Xiao, Bowen Xing, Liang Liao, Chia-Wen Lin Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15075v1 RS-LVLMs have advanced multimodal understanding of Earth observation imagery, yet their performance is fundamentally constrained by high-resolution processing, as visual token counts grow quadratically with linear input resolution while important visual evidence is inherently sparse and increasingly diluted across the expanded sequence. Existing token pruning methods largely rely on scale-agnostic resolution policies and isolated importance cues, limiting task-aligned granularity adaptation and holistic evidence preservation. To address this, we present Scale-Adaptive and Geospatial Evidence-Modulated Token Pruning (SA-GEM), a plug-and-play framework that unifies task-adaptive token granularity allocation with holistic geospatial token importance modulation. Specifically, a lightweight router selects the resolution based on query-dependent token granularity, while a token importance modulator jointly models task relevance, spatial structure, and local redundancy to preserve holistic geospatial evidence. We show that higher resolution is not universally beneficial and, once sufficient granularity is reached, token quality matters more than token quantity. Experiments across various benchmarks demonstrate that SA-GEM achieves consistent gains in both accuracy and efficiency over existing pruning methods. On XLRS-Bench, it surpasses GeoLLaVA-8K by 2.3% in accuracy with a 2.4 times total inference speedup. --- ### Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents Authors: Tianxin Wei, Zhan Shi, Minhua Lin, Bing He, Zewen Liu, Yisi Sang, Yuanchen Bei, Xuying Ning, Jiaru Zou, Ting-Wei Li, Xiao Lin, Yanjun Zhao et al. Published: 2026-08-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.15071v2 Learning from experience is critical for developing capable, self-improving large language model (LLM) agents. Existing methods typically extract knowledge from accumulated trajectories via reflection, memory, rules, or skills. However, agents in realistic environments continuously encounter novel tasks, often offering only a one-shot opportunity to improve. These executions yield rich but highly noisy contexts, entangling broadly useful lessons with task-specific artifacts. Critically, prior works rarely validate their effectiveness on complex real-world tasks or isolate the underlying drivers of improvement. To address these gaps, we formulate online harness learning, where a frozen agent improves by continually updating a structured harness across sequential tasks. This formulation enables a systematic study of key self-improvement factors through our proposed Evo-Harness. At its core, context-to-harness skill compilation distills noisy, single-shot executions into reusable skill harnesses for cross-domain and topic-level adaptation. To demonstrate the efficacy of one-shot skill compilation, we evaluate across five realistic benchmarks (TerminalBench2, SWE-bench, CL-Bench, -bench, WebArena-Infinity). Our extensive analysis demonstrates the effectiveness of Evo-Harness and provides a principled understanding of how LLM agents can effectively learn on the fly. Our code is available at https://github.com/A-EVO-Lab/a-evolve/tree/release/evo-harness. --- ### Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning Authors: Chanhee Park, Sungbin Han, Jeongho Yoon, Seongtae Hong, Heuiseok Lim Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15065v1 Large Reasoning Models produce diverse, sometimes inconsistent answers across repeated queries on the same problem, so multi-sample inference is a prerequisite for reliable deployment. Majority voting at k rollouts is the standard solution and the de facto accuracy target for this regime, but it is prohibitively expensive at the scale LRMs require. We introduce Funnel of Thoughts (FoT), an inference-time method that preserves the full 32-trajectory voted accuracy while halving its attention FLOPs, a 28.8% reduction in full-model inference cost. Across 115K reasoning trajectories from six LRMs, we find that unproductive trajectories often reveal themselves through repeated hesitation markers such as "Wait", "Actually", and "perhaps." These trajectories are less likely to reach the correct answer and consume disproportionate attention FLOPs, degenerating into no-answer loops in the worst case. Built on this training-free lexical signal, FoT identifies the vocabulary that captures these pathological patterns and prunes affected trajectories before completion, reducing online generation attention FLOPs by 56.1% and wall time by 37.6% without any additional model inference; the same signal transfers without retuning across held-out architectures and out-of-domain tasks. --- ### LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documents Authors: Yuefeng Zou, Yichen Lu, Jingxiao Yang, Bingtao Fu, Gaoyang Zhang, Xiongfei Bai, Tian Chen, Xiang Qi Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15064v1 Parsing visual documents into machine-readable representations is fundamental to document intelligence. Existing benchmarks focus on page-level element recognition, reading order, formula recognition, and table structure. Long documents, however, also require document-level structure recovery. This includes reconstructing cross-page table-of-contents (TOC) hierarchies and identifying typed links from tables and figures to their captions, notes, and sources, often in one-to-many form. Because these structures are covered only partially or subsumed within broader parsing protocols, existing benchmarks cannot directly evaluate two key document-level tasks: \emph{Table-of-Contents Hierarchy Recovery} and \emph{Contextual Relationship Recovery}. To benchmark these two tasks, we introduce \textsc{LongDocBench}, comprising 85 real-world financial reports, textbooks, and academic papers spanning 2,582 pages, with up to 105 pages per document. It provides human-verified annotations for 3,937 heading nodes (mean node depth 3.55; maximum depth 9) and 3,258 contextual relationships annotated across 2,680 table and figure objects. We further evaluate both the downstream utility and recoverability of these structures. Long-document question-answering experiments show that human-verified TOC hierarchies and contextual relationships improve reasoning, with their combination providing complementary benefits. Meanwhile, representative document parsers remain limited on both recovery tasks despite strong page-level performance. To support further progress, we publicly release \textsc{LongDocBench} and its evaluation protocol and reproducible testbed for advancing document-level structure recovery in long documents. --- ### Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation Authors: Amr Hegazy, Amr Alanwar, Mostafa Elhoushi Published: 2026-08-15 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.15062v4 Scaling transformer language models creates an inherent tension between expressivity and memory efficiency. While unique weights across layers preserve functional specialization---from input-grounding to abstract refinement---they incur a substantial memory footprint. Conversely, standard depth-sharing enforces uniform transformations that collapse representational diversity and degrade modeling quality. We introduce Gated Recurrent Transformer, a recurrent depth transformer where fixed-depth prelude and coda blocks bracket a single shared core iterated R times. Inspired by gated recurrent neural networks, we employ a lightweight projection and an elementwise update gate---conditioned on the hidden state, the fixed prelude output, and noise resampled at every step---to modulate the recurrent update. This allows the model to specialize the input to the same few layers across recurrences, rather than requiring many unique layers to achieve functional diversity. Under an isoFLOPS constraint, a 3-layer Gated Recurrent Transformer matches the accuracy of a 12-layer GPT-2 Small baseline with similar training and inference FLOPs, and leads MoR and heavy-tail depth sampling in all nine scale-by-budget cells; at medium and large scale it approaches dense quality at the standard token budget and overtakes it at medium scale once that budget is doubled. Under an isoPARAMS constraint, deeper recurrence achieves a 2.76 validation loss versus 2.84 for a non-recurrent counterpart at matched parameter and data budget. Our results demonstrate that adaptive depth reuse is a principled strategy for trading parameters for quality: at large scale, 63% fewer parameters and 59% less peak decoding memory for a 10% increase in compiled generation latency. --- ### Do Visual Grounding Decoders Need Feed-Forward Networks? A Controlled Study over Frozen Vision-Language Features Authors: Tarun Tomar Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15061v1 Do feed-forward networks (FFNs) in visual grounding decoders add essential computation once a pretrained vision-language model has already encoded image and language context? We compare a four-block attention-only decoder (A4), a matched four-block attention-plus-FFN decoder (S4), and an eight-block attention-only parameter control (A8) over frozen VLM features. A4 matches or slightly exceeds S4 on RefCOCOg and Ref-Adv-s. FineCops-Ref reveals a small A4 deficit of 0.52 percentage points at IoU@0.5 (95% CI (0.12, 0.95) in favor of S4), but A8 recovers it and finishes 0.26 points above S4. Official FineCops levels do not show a monotonic increase in the gap. A4 reduces trainable decoder parameters by 44.4% and cached-decoder latency by 10.1%, although end-to-end latency remains backbone-dominated. These results concern the trainable grounding decoder, not a complete attention-only VLM. --- ### EgoTac: In-the-wild Tactile Prediction from Egocentric Vision Authors: Wenkang Zhang, Chengbo Yuan, Zicheng Zhang, Zhengxue Cheng, Yang Gao Published: 2026-08-15 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.15060v1 Touch is fundamental to dexterous manipulation, yet most egocentric human data increasingly used for robot learning lacks tactile information. Directly collecting large-scale tactile data is challenging due to sensor limitations, while human video data is abundant, contact-rich, and easily scalable. This motivates a natural question: can tactile signals be inferred purely from vision? To address this, we introduce EgoTac, a generalizable model that predicts rich tactile information directly from egocentric human videos. EgoTac is trained on a unified corpus of over 5.7M image-tactile pairs, covering both continuous force measurements and binary contacts. By learning from this diverse dataset, EgoTac captures nuanced touch dynamics across varied interactions. Experiments demonstrate strong performance: in-domain prediction achieves an average force error below 0.06N. On out-of-domain contact prediction benchmarks, EgoTac consistently outperforms the state-of-the-art contact estimator. It also captures the rise and fall patterns of real tactile data and enables zero-shot predictions on unconstrained real-world videos. Scaling analyses further reveal that both data diversity and volume improve performance steadily. Overall, EgoTac provides a scalable pathway to extract tactile priors from egocentric human videos, enabling broadly applicable tactile-aware robot learning. --- ### MEDR: Query-Independent Frame Selection via Multi-Signal Event Modeling and Dynamic Rescoring Authors: Xinlei Pu, Weijie Shi, Wen Yang, Yi Cao, Hao Chen, Yuanjun Liu, Wenwei Ding, Jia Zhu, Jiajie Xu Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15058v1 Frame selection is a fundamental component of multimodal large language models, enabling long videos to be processed under limited visual-token and computational budgets. Uniform sampling preserves temporal coverage but may miss informative content that appears only briefly. To alleviate this limitation, query-dependent methods can retrieve question-relevant frames. However, because the selected frames depend on the current question, the same visual input cannot be directly shared across different questions, and frame selection must be repeated in multi-turn video dialogue. This motivates us to seek a query-independent frame selection method that preserves the reusability of a fixed visual input while improving the coverage of informative events beyond uniform sampling. We propose Multi-Signal Event Modeling and Dynamic Rescoring (MEDR), a training-free and query-independent frame selection method. Multi-Signal Event Modeling organizes complementary visual, motion, and text signals into signal-specific temporal events. Dynamic Rescoring then iteratively reevaluates each candidate relative to the current selected set, updating its score according to frame-level signal strength, additional event coverage, and temporal proximity. The resulting fixed frame set is constructed without observing the query and can be reused across different questions. On the standard benchmark evaluations, MEDR improves model accuracy by 0.63%-0.89% on Video-MME. On the long-video subset of LongVideoBench, it improves accuracy by up to 1.23% with Qwen3-VL-8B. MEDR further improves overall accuracy by 0.53%, while reusing exactly the same frame set for every question about a video. --- ### GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG Authors: Zafar Ali, Asad Khan, Aalia Malik, Pavlos Kefalas Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15056v1 Multimodal retrieval-augmented generation (RAG) systems often rely on long unstructured contexts or aggressively expanded evidence graphs, which can introduce noisy evidence, weaken multi-hop reasoning, and increase unsupported generation. We present GraphLoom, a reliability-calibrated multimodal knowledge-graph RAG framework for compact and faithful evidence routing. Given a question and its associated multimodal input, GraphLoom constructs an instance-level multimodal knowledge graph from grounded scene descriptions, extracted relational triples, and external commonsense knowledge. Instead of injecting all retrieved evidence into the generator, GraphLoom performs reliability-aware subgraph retrieval with bounded expansion and selectively routes high-utility evidence through hierarchical graph memory slots and joint graph-sequence attention in a frozen language model. To improve robustness in complex reasoning settings, GraphLoom further combines interleaved retrieval with budgeted corrective retrieval, enabling adaptive multi-hop evidence refinement under noisy retrieval conditions. We evaluate GraphLoom on ScienceQA, MultiModalQA, and OK-VQA, including large distractor evidence pools that approximate noisy external knowledge retrieval. Experimental results show consistent gains in answer quality and evidence faithfulness over strong multimodal RAG, graph-retrieval, and open-source vision-language baselines, with improved retrieval quality on MultiModalQA and stable performance under noisy evidence pools. Additional analyses using MiniCheck-based verification, human evaluation, and latency profiling show that reliability-calibrated graph evidence routing provides an effective alternative to long-context multimodal evidence injection. --- ### TAHB: A Comprehensive Benchmark for Text-Attributed Hypergraph Learning Authors: David Yoon Suk Kang, JungHyun Kim, Juhyun Jeon, Sang-Wook Kim Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15055v1 Hypergraphs effectively model higher-order groupwise relationships beyond pairwise interactions, while pretrained language models (PLMs) and large language models (LLMs) provide rich semantic understanding from textual attributes. However, research on combining language models with hypergraph learning remains limited due to the lack of public text-attributed hypergraph benchmarks. To address this limitation, we present TAHB (Text-Attributed Hypergraph Benchmark), the first public benchmark integrating hypergraph structures and raw textual attributes. TAHB contains 10 real-world datasets from four domains - e-commerce, academia, movies, and politics networks - enabling systematic evaluation of text-aware hypergraph representation learning. Experimental results show that TAHB preserves key structural properties of real-world hypergraphs and consistently reproduces performance tendencies observed in existing benchmarks. Furthermore, experiments under both LLM-as-Enhancer and LLM-as-Predictor settings demonstrate that LLM-enhanced textual semantics improve hypergraph learning performance, while structural and textual information jointly provide the best setting for LLM-based prediction. Our benchmark provides a foundation for future research at the intersection of hypergraph learning and language models. --- ### Frequency and Edge-Guided Segment Anything Model for Remote Sensing Image Semantic Segmentation Authors: Feng Gao, Zizhe Pan, Haoting Wang, Ruzhuang Hua, Jingchao Cao, Junyu Dong, Qian Du Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15054v1 Remote sensing image semantic segmentation (RSISS) has attracted significant attention due to the growing demand for fine-grained land cover information. The Segment Anything Model (SAM), proposed as a foundation vision model, offers strong segmentation performance and generalization capabilities for RSISS tasks. However, existing SAM-based approaches face two limitations: (1) Insufficient adaptation of SAM's features to the diverse characteristics of land cover types. (2) Semantic ambiguity at object boundaries, which hinders accurate delineation. To address these limitations, we propose Frequency and Edge-guided SAM (FE-SAM), a scalable and efficient framework for RSISS. Specifically, we introduce a Frequency-Modulated Adapter (FMA) that adaptively decomposes and modulates frequency-domain features based on the input data. It selectively enhances informative high- and low-frequency components corresponding to different land cover types. Furthermore, to improve SAM's ability to capture fine-grained details, we design EGRefiner, which integrates multi-scale edge-enhanced information extracted from the input image. Extensive experiments on three benchmark datasets demonstrate that FE-SAM outperforms state-of-the-art methods. The source codes are available at: https://github.com/oucailab/FE-SAM. --- ### Andy: A Mathematical Agent for Rigorous Proof and Autonomous Research Authors: Zi'an Wang Published: 2026-08-15 Categories: cs.AI, math.OC arXiv: https://arxiv.org/abs/2608.15052v2 Andy is an autonomous mathematical research agent that turns a mathematical problem into a traceable proof. It solves or verifies a submitted problem, formulates a literature-grounded new problem through a research-value gate, and carries it through proof construction and final verification. It organizes proof steps in an executable DAG, verifies each step independently and binds the result to a certificate, retains verified work whose interfaces remain unchanged during local repair, and records the full path from problem formulation to final proof. The system separates proof generation from correctness evaluation and can acquire, retain, retrieve, and reuse knowledge from existing results. Starting from a self-triggered impulsive consensus result, Andy formulates a global exponential leader-follower synchronization problem for delayed heterogeneous networks with switching communication topologies. The proposed hybrid control combines self-triggered impulses with execution delay and continuous feedback over a recovery window. After each delayed impulse, the feedback cancels the delayed error channel until the pre-impulse history leaves the active delay interval. Sufficient conditions for global exponential synchronization are established, Zeno behavior is excluded for both timing sequences, and a numerical example illustrates the result. --- ### A Unified Mamba--MoE Surrogate for Closed-Loop Simulation and Measurement-Window Forecasting of Inverter Transients Authors: Haoguang Wang, Huy Hoang Le, Akhila Kandivalasa, Christian Moya, Marcos Netto, Guang Lin Published: 2026-08-15 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2608.15051v1 This paper proposes a Mamba surrogate model with mixture-of-experts (MoE) routing to represent the transient dynamics of inverter-based resources. A Mamba surrogate model is a predictive machine learning model built on the Mamba architecture. MoE routing uses a router network to assign data-dependent weights to specialized subnetworks (experts). The resulting Mamba--MoE surrogate can perform two tasks: (i) closed-loop simulation and (ii) measurement-window forecasting of inverter transients. A single Mamba backbone with task conditioning and expert routing serves both tasks, replacing two separate specialists. Task-matched objectives fit each prediction form, and an adaptive conformal layer provides prediction intervals for both tasks. For the considered grid-following inverter, the unified surrogate model remains in the same low-error regime as a Mamba specialist pair while using 13% fewer parameters. The prediction intervals achieve 94--96% empirical mean marginal coverage across the two tasks. For transient dynamics---that is, beyond the vicinity of an equilibrium point---our surrogate model with MoE routing yields lower errors across all outputs in both tasks compared to a shared Mamba backbone without expert routing. A controller hardware-in-the-loop simulation validates our results and shows that adapting only the shared output head with limited measured data reduces held-out forecasting error. ---