# Research Papers — 2026-08 · bundle page 12 of 240 > Full-text markdown of papers #551–600 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/12 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/11.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/13.md) ### Semantic-Spatial Discriminability Enhancement for Generalized Visual Grounding Authors: Kaiyan Lei, Xu-Yao Zhang Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30233v1 Generalized Visual Grounding (GVG) task aims to localize targets in an image based on referring expressions, extends the classical visual grounding paradigm by integrating multi-target and non-target scenarios. Previous methods typically rely on global semantic matching or coarse-grained region interactions for localization, where the discriminative cues are primarily derived from sentence-level semantics or regional context. In complex multi-target scenarios, such approaches tend to confuse visually similar targets, making it difficult to establish stable instance-level decision boundaries. To address these limitations, this paper proposes a novel Semantic-Spatial Discriminability Enhancement (SSDE) framework for generalized visual grounding, which aims to enhance the discriminative ability on fine-grained semantics and spatial localization, improving both cross-modal understanding and instance-level grounding. Specifically, to enhance the semantic discriminability of query representations at the fine-grained level, we propose a Semantic Discriminability Enhancement (SeDE) module, which leverages spatially guided cross-attention to disentangle fine-grained target-relevant visual attributes and integrates them with the textual subject semantics. Furthermore, to strengthen the spatial discriminability of the referred targets, we introduce a Spatial Discriminability Enhancement (SpDE) module, which models an instance center density map to characterize the spatial distribution of targets, and explicitly constructs instance separation structures in the spatial domain by employing them as an auxiliary supervision signal. Extensive experiments show that SSDE achieves superior performance on ten datasets across both classic and generalized visual grounding tasks. --- ### "More Is Different'' in Neural Circuits: Algebraic Emergence of Effective Theories in Canonical Recurrent Motifs of Biological Neuronal Networks Authors: Nima Dehghani Published: 2026-08-31 Categories: q-bio.NC, cs.FL, cs.NE, nlin.CD, physics.bio-ph arXiv: https://arxiv.org/abs/2608.30231v1 Canonical neural circuit motifs are usually described functionally: divisive normalization rescales population activity by a pooled signal, and winner-take-all competition selects one pattern through recurrent excitation and shared inhibition. We represent them, and their compositions, algebraically as finite transformation systems and analyze the transition monoids generated by their input-conditioned updates, distinguishing structure already present in a generator from structure that appears only through composition, and, on a joint state space, structure inherited from one factor from structure that lives on a joint configuration. Individually aperiodic updates can generate non-aperiodic monoids. In the WTA, every frozen-drive generator collapses to fixed points, yet short input sequences create local cycles of winner-dependent inhibitory gating: globally dissipative dynamics with a reversible action. The strongest result arises in WTA-to-DN composition. The composed monoid then contains a genuinely composite local cycle in which normalization state and the winner's gating state change together, although every primitive generator is aperiodic. Holonomy analysis certifies this as a group component of the Krohn-Rhodes cascade rather than an incidental cycle, and finds most group-carrying image sets on joint configurations, whereas the uncoupled product has none. An exhaustive interface sweep shows that the composite cycle is a property of the coupling rather than of a chosen map. If motifs are building blocks of neural computation, composing them is a form of programming: one chooses primitives and interfaces so that the generated algebra has the intended repertoire. The transition monoid is that repertoire - what a primitive presents to any later construction. Recurrent circuits are compositional transformation systems; their algebra constrains what they can be programmed to compute. --- ### Rethinking the Test-Time Prompt Tuning Objective from the Perspective of Calibration Authors: Jungwon Choi, Hyeonseo Jang, Kibok Lee, Eunwoo Kim Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30230v2 Test-time prompt tuning (TPT) has emerged as a powerful paradigm, refining prompts for each test sample via entropy minimization (EM) over multiple augmented views. However, we identify a limitation in the standard EM-based adaptation: it inherently drives the model toward overconfident predictions disregarding sample-specific uncertainty, leading to significant calibration degradation. To address these limitations, we propose a new objective that replaces the conventional EM loss by aligning the original-view prediction with a target distribution derived from augmented views via cross-entropy, while adversarially incorporating the entropy of the target distribution to capture sample-specific uncertainty. Furthermore, to better construct this target distribution, we apply confidence-aware temperature scaling to each augmented-view prediction according to its confidence, sharpening confident predictions while softening uncertain ones. This formulation allows the model to increase confidence only when the target distribution is reliable, while preserving uncertainty when it reflects ambiguous or conflicting augmented-view predictions. Extensive experiments across diverse benchmarks demonstrate that our approach not only achieves state-of-the-art accuracy but also significantly improves model calibration. --- ### Quantifying and Mitigating Korean Jamo-Level Typographical Vulnerabilities in Large Language Models Authors: Seojin Lee, Hwanhee Lee Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30229v1 Korean introduces an additional typographical perturbation level not captured by ordinary character-level edit models: because syllable blocks are internally composed of sub-character units called jamo, keyboard-level errors can occur within a syllable, either producing a valid but semantically altered character or exposing raw jamo on the surface. Both outcomes disrupt sub-word tokenization and are not reliably corrected by existing grammatical error correction pipelines, leaving LLMs directly exposed to corrupted inputs. To quantify this vulnerability, we apply five jamo-level perturbation types to the KMMLU benchmark and evaluate four language models, finding that accuracy declines monotonically with perturbation intensity and that parameter scaling does not confer robustness against intra-syllabic noise. We further show that typo-corrupted inputs induce a distinct shift in internal representations that is not reducible to ordinary answer incorrectness, and that a simple linear probe trained on these representations detects unseen perturbation types with high AUROC. Motivated by this signal, we propose Typo-Aware Chain-of-Thought (TACoT), which routes inputs to chain-of-thought inference only when the probe detects a likely typo, recovering a substantial portion of the CoT accuracy gain at a fraction of the inference cost. --- ### LaMoC: Loss-Aware Modular Compression for LLMs Authors: Mohanad Odema, Jacob Song Published: 2026-08-31 Categories: cs.AI, cs.CL, cs.PF arXiv: https://arxiv.org/abs/2608.30226v1 Modular compression has enabled considerable parameter reduction in LLMs while preserving strong language understanding and downstream task accuracy. However, existing joint modular compression methods primarily rely on activation statistics, leaving loss-sensitivity information and its module-level characterization underexplored. We investigate addressing this gap with LaMoC, a loss-aware modular compression methodology that blends activation and Empirical Fisher statistics through gradient-error alignment. LaMoC improves joint compression by selecting compression statistics that better align local module reconstruction error with the downstream loss. Our contributions are three-fold: (1) We characterize the Empirical Fisher as a module-level loss-aware proxy that can be blended with the activation statistics required for compression. (2) We reformulate joint modular compression as a two-tiered optimization problem that minimizes module reconstruction error while tuning the activation and gradient information blending rate. (3) We implement an empirically driven methodology with statistical validation to solve the resulting compression problem. We evaluate LaMoC across four model families spanning eight models. On the 4-8B models, LaMoC achieves an average 2.5% reduction in perplexity and a 1% relative improvement in task accuracy over state-of-the-art modular compression methods. --- ### The Differential Reasoning Router: Operationalizing Cost-Aware LLM Annotation in E-commerce Authors: Cheng Lyu, Jingyue Zhang, Vinny DeGenova, Mengwei Li, Yuanli Pei Published: 2026-08-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.30224v1 Large Language Models (LLMs) are increasingly used to annotate structured product data in e-commerce, but early deployment often begins as a cold-start problem: only limited pre-launch labels are available, the value of expensive reasoning is unknown, and human review is needed before the system can be trusted at scale. This challenge is especially common in rule-based annotation workflows, where each item must satisfy multiple business rules and both model errors and ambiguous rule boundaries affect final decisions. We introduce the Differential Reasoning Router (DRR), a cost-aware framework for cold-start LLM annotation that jointly optimizes model selection and human escalation. Rather than treating a reasoning model as a default fallback, DRR estimates separate success probabilities for a direct model and a reasoning model at both the sample and business-rule levels, enabling adaptive routing: easy cases are handled directly, reasoning is reserved for cases where it is expected to improve the decision, and likely double-failure or rule-disagreement cases are escalated to human annotators. The resulting labels provide targeted ground truth for prompt engineering, supervised fine-tuning, calibration, and rule refinement, enabling a gradual shift from human-heavy cold-start annotation toward high-confidence automated routing. In a production e-commerce workflow, DRR reaches accuracy parity with the strongest confidence-based router while achieving more than 60\% reasoning-token cost savings. --- ### Fairness in multi-class multi-group classification problems via contextial coherent risk measures Authors: Darinka Dentcheva, Xiangyu Tian Published: 2026-08-31 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.30223v1 We propose a new design of fair classifiers for multi-class classification problems in the presence of vector-valued sensitive attributes. In that scenario each sensitive attribute has multiple values and forms several groups relevant to the fairness consideration. Naturally those groups are overlapping and one should also analyze the interaction of factors. Additionally, the decision makers aided by the classification should not violate individual rights at the expense of satisfying fairness metrics at the group level. We propose an approach using the theory and methods of coherent measures of risk aiming at resolving the fairness challenges. Further, we propose a specialized numerical method for solving the resulting optimization problem. The method scales well with the increase of the number of observations. Additionally, we note that the obtained classifier is robust with respect to corrupted data or to situation when data is scarce. We demonstrate the advantages of the proposed framework in comparison to the support-vector machine framework and other methods handling fairness. --- ### Amortized Anchor Refinement for Deployable Continuous-Time 4D Gaussian Reconstruction Authors: Jingong Chen, Qingwen Zhang, Sanghyeon Jun, Chulwoo Pack, Kyle Gao, Kwanghee Won Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30218v1 Continuous-time 4D reconstruction remains impractical on standalone XR headsets. Per-scene optimization demands deployment-infeasible compute, and lower budgets cause collapse rather than degrade gradually. Feed-forward prediction is fast, but struggle to recover scene-specific detail. We present Amortized Anchor Refinement, which uses a frozen backbone to predict an initial Gaussian representation and a short optimization to specialize it under a fixed compute budget, with a capacity floor preserving representational density. A training-free stage then applies a persistent-homology constraint to prune unstable Gaussians while preserving topologically persistent structures, and streams the resulting trajectories directly as scene flow. On the Stage-Capture benchmark, Amortized Anchor Refinement achieves 24.31$\pm$2.22dB, while our deployment experiments demonstrate reconstruction within the target budget on a single consumer GPU and playback on a standalone XR headset. --- ### Label Semantic Expansion via Label Guided Neural Topic Modeling Authors: Haojia Zheng, Yuyin Lu, Juntian Huang, Fan Ou, Yanghui Rao, Haoran Xie, Fu Lee Wang Published: 2026-08-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.30216v1 Topic models are widely used for content analysis, where users often analyze corpora around predefined labels rather than unordered latent topics. Existing label-aware topic models mainly follow a labels-for-topics perspective, using labels to guide topic learning, while the learned topics are not directly usable for label-centered analysis. We explore the reverse topics-for-labels perspective and instantiate it as Label Semantic Expansion (LSE), which enriches sparse label representations with corpus-grounded descriptive topic words. To exploit topics in LSE effectively, we propose a Label-Guided Neural Topic Model (LGNTM), which learns dedicated label-aligned topics, grounds them in lexical and document semantic spaces, and preserves consistency between topic structures and label structures. Experiments on label-topic alignment, label expansion, topic quality, and downstream classification demonstrate strong overall performance across complementary evaluation dimensions. --- ### SPARK: Skeleton-Guided Reasoning Synthesis from Large-Scale Scientific Literature Authors: Yu Li, Wei Li, Xin Gao, Mengyuan Sun, Xiaoyang Wang, Qizhi Pei, Lijun Wu Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30214v1 Scientific reasoning remains challenging for open-source models, largely due to the lack of high-quality scientific reasoning data. Existing datasets are often dominated by factual recall or formulaic problem solving, with limited emphasis on mechanism understanding, evidence-grounded reasoning, and hypothesis evaluation. To address this, we introduce SPARK (Scientific Paper Abstracted Reasoning sKeleton), a paper-oriented synthesis framework built on Sci-Base, a large-scale corpus of research papers spanning 10 scientific disciplines. Instead of directly converting papers into question-answer pairs, SPARK treats the claim-evidence-derivation structure of a paper as the fundamental unit of reasoning synthesis. Specifically, SPARK (1) distills each paper into a compact reasoning skeleton capturing its central claims and supporting evidence, enabling self-contained question generation, and (2) synthesizes reasoning tasks from four scientific perspectives: mechanistic reasoning, hypothesis falsification, quantitative derivation, and boundary calibration. A final consistency verification stage further removes unsupported or contradictory outputs. Using this framework, we construct Spark-234K, a scientific reasoning dataset with substantially higher difficulty and diversity than existing resources. Experiments show that Spark-234K consistently outperforms existing scientific reasoning datasets while achieving stronger performance with significantly fewer training samples. --- ### Towards a Joint Khmer Text Recognition and Word Segmentation Authors: Marry Kong, Rina Buoy, Sovisal Chenda, Nguonly Taing, Masakazu Iwamura, Koichi Kise Published: 2026-08-31 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2608.30213v1 Text recognition, or extracting electronic text from document images, has been indispensable for knowledge retrieval tasks, such as retrieval-augmented generation (RAG). For Khmer, extracted text is subject to an extra word segmentation step, as Khmer does not use any visible word delimiters to denote word boundaries. Thus, a recognition-then-segmentation pipeline for Khmer requires two separate sequential models; this is not only error-prone but also adds significant latency for large-scale document processing. This paper proposes a novel joint Khmer text recognition and word segmentation framework in a unified model. The proposed model, using a connectionist-temporal-classification (CTC) decoder for fast, parallel decoding, can be instructed to recognize Khmer text with ($b=1$) and without ($b=0$) word segmentation. Experimental results on different benchmark datasets of different document modalities (document, scene, and handwritten images) show that the proposed model can not only recognize characters in document images but also locate word boundaries, removing the need for an extra word segmentation step in a conventional sequential pipeline. --- ### Frontier vision-language models have overtaken young adults at detecting AI-generated portraits -- but not their calibration Authors: Sunwhi Kim, Sunyul Kim, Meounggun Jo, Jini Tae Published: 2026-08-31 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2608.30210v1 AI image generators now create face portraits that are hard to tell from real photographs. Vision-language models (VLMs) are increasingly proposed to flag such images. We benchmarked 19 VLMs on the same 198 face portraits -- real photographs and identity-matched ChatGPT-4o and Imagen 3 versions -- under the same task as our earlier study of 1,667 adults (85% correct overall; accuracy fell steeply with age). The June-2026 cohort of 14 models only matched adults in their 20s-30s. Four weeks later the ceiling broke. Among five July-2026 releases under the identical protocol, gpt-5.6-sol reached 92.8% balanced accuracy (five-draw mean 92.1%), clearly above adults in their 20s (88.5%), and claude-fable-5 detected every AI image while averaging 91.9%. Model sensitivity now exceeds young adults decisively (d' up to 3.4 versus ~ 2.4). What has not been overtaken is human calibration. Model criteria spread from c = -1.10 to +1.45 while humans sit near zero at every age; both new leaders are biased (+0.44, -0.97), and only a few mid-ranked models approach the human balance. Changing the labelled examples still flipped about one answer in four. The best machines now out-see young adults here, without matching the human balance between suspicion and trust. --- ### DICS: Exploring Data Intrinsic Consistency for Visual Instruction Selection Authors: Yuyang Hong, Jinhui Guo, Jiaqi Gu, Lubin Fan, Ruixiang Wang, Kun Ding, Yue Wu, Shiming Xiang, Jieping Ye Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30209v3 Visual instruction tuning is crucial for advancing the vision-language alignment and instruction-following capabilities of Vision-Language Models (VLMs). However, identifying optimal subsets under a fixed ratio constraint from rapidly expanding datasets remains a significant bottleneck. While existing methods largely depend on distribution diversity or heuristic filtering, they often overlook the internal coherence within individual samples. To bridge this gap, we propose Data Intrinsic Consistency (DIC), a self-scoring metric designed to quantify the sample-level inter-component consistency. DIC consists of two modules: Visual Information Consistency (VIC), evaluating the alignment between visual content and instructions, and Response Information Consistency (RIC), assessing response coherence relative to the instruction. Building upon DIC, we introduce Data Intrinsic Consistency Selection (DICS), an adaptive data selection method that optimizes the trade-off between high intra-sample consistency and global distributional diversity under varying data budgets. Extensive experiments demonstrate that DICS consistently outperforms state-of-the-art methods across diverse dataset scales and model architectures, surpassing full-dataset fine-tuning while using only 25% of the LLaVA-1.5-665K data. We further curate DICS-6M, a 6M-sample multi-modal instruction corpus that enables the largest-scale visual instruction selection study to date; remarkably, DICS reaches 94.52\% of the official InternVL3-8B-Instruct performance using less than 25\% of its reported training data. Code can be seen at https://github.com/cqu-student/DICS --- ### SIR: Self-improving Red-teaming for Compute Use Agents Authors: Chen Xiong, Zhiyuan He, Pin-Yu Chen, Stjepan Picek, Tsung-Yi Ho Published: 2026-08-31 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.30207v1 Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal, and they are increasingly deployed to automate everyday digital tasks. Because they can be exposed to untrusted content while operating, they are vulnerable to indirect prompt injection (IPI), in which an adversary plants instructions in content the agent will read and redirects it toward actions that violate the user's intent. Existing CUA safety benchmarks evaluate fixed injections written by hand, which may underestimate the risk posed by an adaptive adversary. We present SIR, a black box IPI attack that (i) composes stealthy injections from a small library of reusable principles stated in plain language and (ii) wraps composition in an iterative feedback loop that diagnoses the victim's failed trajectories and distills the bypasses into new, named strategies that are reapplied across tasks. Unlike prior red teaming of web agents, we target CUAs at the operating system level and score attacks with a fully deterministic oracle, using checks on filesystem, service, and permission state rather than an LLM judge. On experiment, we evaluate three frontier CUAs. Composing principles with feedback raises the attack success rate over a baseline written by hand, for example from 4% to 24% on Claude Opus 4.8 and from 0% to 28% on Gemini 3.5 Flash, while the benign task still completes. Principles discovered against one model further transfer to a different architecture with no additional feedback. --- ### Diffusion-Based Refinement for Kilometer-Scale Probabilistic Precipitation Nowcasting Authors: Dohyun Park, Changhoon Song, Tengyuan Chang, Yoo-Geun Ham, Youngjoon Hong Published: 2026-08-31 Categories: cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2608.30205v1 Localized extreme precipitation is a major trigger of urban flash floods and landslides, yet producing nowcasts that combine fine spatial detail with probabilistic uncertainty remains challenging. Here we introduce exPreCast-ENS, a conditional residual diffusion framework that transforms the deterministic 4 km radar nowcaster exPreCast into a 1 km probabilistic ensemble while correcting systematic forecast errors. Conditioning on both the forecast and preceding radar observations lets the ensemble-mean correct the baseline rather than perturb it, while members represent unresolved fine-scale variability. Over the Korean Peninsula, skill improves with ensemble size. In two high-impact events in 2023, a 30-member ensemble recovers 38-47% of heavy-rain pixels missed by exPreCast while retaining approximately 95% of its correct detections and alarming on under 1% of the pixels it correctly left clear. The method generates a 1-h forecast in 3.4 s on a single GPU and yields consistent improvements on the French regional MeteoNet radar dataset. --- ### When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detection Authors: Yongjian Chen, Pengfei Wei, Yiqun Sun, Zhu Li, Lawrence B. Hsieh Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30204v1 Multimodal Large Language Models (MLLMs) process speech and text jointly, yet whether they exploit prosodic cues for pragmatic inference or rely on surface acoustic patterns has received little systematic investigation. We address this through sarcasm detection, evaluating Qwen2.5-Omni and Qwen3-Omni on Mandarin Chinese and English under five modality conditions that decompose the contributions of lexical content, vocal semantics, and prosodic structure. Adding audio systematically inflates false positives without improving true positive detection. Acoustic error diagnosis reveals that model errors cluster on a shared stereotype of expressive prosody, namely elevated pitch and irregular pausing, that diverges from the actual cues marking sarcasm in both languages. Targeted manipulation of only these two dimensions causally confirms the heuristic, inducing false positive rates of up to 60%. Applying the same manipulation template to Gemini~3 Flash Preview without modification replicates the effect, suggesting that the stereotype extends beyond the Qwen Omni family rather than arising from a single model architecture. --- ### Certified Safety Radii in Forecast-Error Space for Wasserstein Distributionally Robust Small Signal Stability-Constrained AC Optimal Power Flow via Lifted Spectrahedral Containment Authors: Ziqi Zhang, Xi Chen Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30201v1 Directly robustifying small-signal stability in AC optimal power flow is challenging since the stability boundary in the original uncertainty space is implicit, highly nonconvex, and changes with the operating decision. This paper exploits an alternative geometry. For a fixed model-specific stability certificate admitting suitable physical lifts, the small-signal stability requirement becomes an affine positive semidefinite constraint in the lifted variables, thereby defining a convex certified safe region. Instead of approximating the nonlinear instability boundary itself, we optimize a sample-wise safe radius in the original uncertainty space and certify, in the lifted space, that the entire power-flow image of the corresponding uncertainty ball is contained in the convex stability region. To this end, a componentwise Perron certificate guarantees existence, uniqueness, and Jacobian regularity of the target AC power-flow branch throughout each ball. An adjoint elimination then provides an exact affine-quadratic representation of the stability-relevant quantities, while rigorous matrix remainder bounds convert their nonlinear variation into finite robust PSD constraints. The resulting radii are certified lower bounds on the distances from empirical samples to failure and can therefore be coupled directly to the distance-based reformulation of a Wasserstein distributionally robust chance constraint, without directly approximating the instability boundary. Numerical studies demonstrate the effectiveness of the proposed framework. --- ### When Errors Become Memories: Causal Pathway Tracing in Multi-Turn Memory-Augmented LLMs Authors: Shuyao Xiao, Shengling Wang, Xuan Chen, Ke Chao, Ming Cui, Feifei Qian, Fanlin Meng, Chaoyang Mei, Chaoyong Jiang, Qi Ouyang, Junxi Yi Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30198v1 Long-term memory enables large language models (LLMs) to preserve and reuse information across interactions, but it can also turn localized errors into persistent risks. Existing work mainly evaluates whether memory systems store and retrieve information correctly, leaving limited understanding of how errors propagate across responses, memory states, and future interactions. We propose a structural causal model (SCM)-based framework for cross-turn error propagation in memory-augmented LLMs. We model user questions, model responses, and memory states as a dynamic causal process, and identify two entry pathways: internal memory updating and external question feedback. By intervening on these pathways, we construct four counterfactual trajectories and quantify their downstream effects and interaction. Error influence is evaluated at four levels: memory retention, natural responses, targeted diagnostic probing, and probability-level error preference. Experiments show that error influence generally decays with interaction distance, while the memory-update pathway contributes more persistent effects than question feedback; latent errors may remain even after disappearing from natural responses. Propagation patterns also vary across memory categories and memory mechanisms. Pathway-guided restoration further validates this decomposition: Question Repair reduces residual error by 27.5%, Memory Repair by 70.2%, and Joint Repair by 98.3%, nearly eliminating residual propagation. --- ### ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives Authors: Hoejoon Kwon, Byeonggeuk Lim, Kahyeon Kim, YoungBin Kim Published: 2026-08-31 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2608.30197v1 Safety alignment is essential for deploying large language models, requiring systems to prevent harmful compliance while preserving helpfulness on benign requests. Activation steering offers a training-free inference-time approach to safety control, but effective safety steering requires addressing two coupled questions: when to intervene and how generation should be shaped after intervention. However, existing safety steering methods remain limited along both dimensions, as their triggering mechanisms can be unstable across domains and refusal-oriented steering often yields rigid refusals rather than constructive safe guidance. To address these limitations, we propose ALTSTEER, an inference-time framework that couples selective intervention with refusal-anchored constructive redirection within a single inference pass. ALTSTEER uses an internal refusal-relevant signal to decide when to steer, and applies staged steering to shift generation from refusal-oriented control toward constructive alternatives. Evaluations on Llama-3.1 and Qwen2.5 show that ALTSTEER preserves benign utility while improving constructive safe-completion behavior, especially on models that otherwise tend to produce short refusals for harmful requests. --- ### NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation Authors: Yujiang Pu, Yu Kong Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30194v1 Diffusion models have recently advanced text-to-video (T2V) generation, yet they still struggle with fine-grained compositional alignment, such as attribute binding, spatial relations, and object interactions. While reward-based fine-tuning improves alignment, it is susceptible to reward hacking and adapts poorly to new prompt distributions. In this work, we propose NoisEasier, a test-time scaling framework that improves T2V generation through differentiable reward-guided noise optimization without modifying the underlying model. By combining efficient short-step generators with a multi-objective reward formulation, NoisEasier enables stable and practical test-time optimization under realistic inference budgets. Our key insight is that jointly optimizing the entire stochastic trajectory accelerates reward convergence and improves compositional alignment over optimizing only the initial latent, with negligible additional computational and time cost. Experiments on VBench and T2V-CompBench demonstrate consistent improvements across multiple backbones, achieving over 10% average gains on challenging dimensions such as attribute binding, object interaction, and numeracy. Overall, NoisEasier serves as both a flexible alternative and a complementary enhancement to reward-based fine-tuning, establishing test-time scaling as an effective paradigm for controllable text-to-video generation. --- ### FaVOR: LLM-Based Agentic Framework for Factor Mining via Empirical Validation Authors: Hyeonjin Kim, Minseok Kim, Seunghyeon Jung, Sujin Pyo, Huisu Jang, Woojin Lee Published: 2026-08-31 Categories: cs.AI, cs.CE arXiv: https://arxiv.org/abs/2608.30192v1 Traditional finance relies on experts to hand-craft factors through a principled process grounded in economic rationale. Recent LLM-based multi-agent systems have automated this process, scaling factor mining far beyond manual effort. However, these automated approaches optimize directly for returns and rarely check whether a generated factor still expresses the economic hypothesis that motivated it. We identify this inconsistency between mathematical form and economic meaning as a structural failure mode of return-oriented automation. The resulting factors blur the line between real signals and spurious correlations and break down across regime shifts. We propose FaVOR (Factor Validation through Observable Reasoning), an agentic framework that restructures factor mining around hypothesis-level evidence rather than return outcomes. In place of the standard hypothesis-to-formula leap, FaVOR enforces a three-stage consistency loop tying mathematical form to economic rationale throughout. (1) Decomposition splits a broad economic hypothesis into independent observable conditions. (2) Validation checks whether each factor reflects its intended condition. (3) Integration merges them into a composite whose structure remains interpretable. On the CSI 500 and S&P 500 in 2025, FaVOR outperforms existing baselines while remaining effective across regimes. FaVOR shows that hypothesis-grounded factor discovery produces signals that are interpretable by construction, regime-robust, and economically faithful. The code is available at https://github.com/damilab/FaVOR. --- ### GPAgentBench-2K: Benchmarking Large Language Model Agents in Complex Clinical Action Space Authors: Boqi Chen, Xudong Liu, Yunke Ao, Heejin Do, Jianing Qiu Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30188v2 Large Language Models (LLMs) show great potential as clinical agents, yet existing benchmarks reduce clinical workflows to static predictions or unconstrained Markov Decision Processes (MDPs) with coarse action sets. To address this, we introduce GPAgentBench-2K, the first Constrained MDP (CMDP) LLM-agent benchmark for primary-care clinical decision-making, constructed from expert-validated records of real-world GP encounters. Our environment models a full spectrum of six foundational clinical actions, imposes a topological workflow prior over the action space, and operationalizes safety-informed abstention as a first-class outcome. Evaluating 16 state-of-the-art LLMs reveals a significant performance degradation as the action space scales. Crucially, we uncover a clinical quality-safety gap: even frontier models with the highest diagnosis accuracy violate safety constraints in over half of high-risk cases. Finally, we establish a reference point using Constrained Group Relative Policy Optimization (C-GRPO), and show that while explicitly modeling constraints improves performance over unconstrained RL methods, it remains far from clinically acceptable safety. --- ### The PUR-1 Cyber-Physical Digital Twin Authors: Vasileios Theos, Jonah Lau, Konstantinos Gkouliaras, Zachery Dahm, Konstantinos Vasili, Noah Fillgrove, William Richards, True Miller, Brian Jowers, Stylianos Chatzidakis Published: 2026-08-31 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2608.30186v1 Digital twin technologies have the potential to improve operational flexibility and responsiveness capabilities of nuclear systems. To provide decision support, cyber event characterization, state estimation, predictive control, and real-time dynamic processing of operational data, however, an efficient digital twin needs to integrate multiple models (data-driven as well as physics-based) with explainability while at the same time maintain two-way synchronization with the physical facility at a time constant less than its operational cycle. In this work, we present the Purdue University Reactor One Digital Twin (PUR-1 DT), a cyber-physical digital twin with a complete high-fidelity physics-based and AI-driven virtual model stack (neutronics, thermal-hydraulics, point kinetics) which provides closed-loop explainable diagnostics, forecasting, predictive control, and action recommendation back to the reactor via two-way communications and a cyber-physical testbed. We demonstrate real-time synchronized state estimation and short-term forecasting over a full reactor operational cycle and conduct a series of benchmarking experiments to validate accuracy and latency. Our results show good agreement with experimental results and lay the groundwork for further development and experimental demonstration of DT-enabled functionalities in real-world facilities. --- ### ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation Authors: Jiahao Wu, Jie Liang, Die Hu, Jiayu Yang, Kaiqiang Xiong, Xiang Li, Xiaoyun Zheng, Chao Wang, Ronggang Wang Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30184v1 Volumetric video enables immersive free viewpoint rendering of dynamic real world scenes, yet existing methods struggle with long sequences and complex motions, often leading to temporal instability and visual artifacts. To address these challenges, we propose \ourname, a Gaussian splatting based framework for volumetric video reconstruction. Our key insight is that explicitly tracking long term complex motion with individual Gaussian primitives is inherently unstable. Instead, we organize Gaussians around time conditioned anchors that localize their spatial and temporal support, thereby reducing long range motion complexity. We further introduce a temporal windowing strategy to activate only anchors relevant to the queried time, which improves scalability and temporal coherence. In addition, to ensure spatial and temporal stability, we design a compact set of multi level anchor features that encode global features, local spatial features, and local temporal features, jointly constraining Gaussian generation. Extensive experiments demonstrate that \ourname \ consistently outperforms prior methods on long sequence volumetric videos with complex motions. Project page: https://github.com/WuJH2001/ATGS. --- ### ConCA: Concentration-Aware Channel Attention for Fine-Grained Visual Recognition Authors: Yu-Sheng Liu, Yu-Chen Tung Published: 2026-08-31 Categories: hep-ex, cs.CV arXiv: https://arxiv.org/abs/2608.30183v1 Lightweight channel attention mechanisms are widely used in image classification, yet their effectiveness in fine-grained visual recognition (FGVR) remains limited. Most modules summarize each channel by global average pooling (GAP), which captures activation magnitude but ignores spatial concentration, so channels with different spatial distributions but identical means receive the same descriptor. We propose Concentration-Aware Channel Attention (ConCA), which pairs the mean with a shift-invariant negative-input entropy (NegEnt), computed via a softmax over the negated activations, forming a dual descriptor that jointly encodes magnitude and concentration. A depthwise 1-D convolutional multi-layer perceptron (MLP), whose parameter count is linear in the number of channels, maps the pair to a per-channel weight. On six fine-grained benchmarks, ConCA improves over attention-free, SE-Net, and ECA-Net baselines as well as four richer descriptor-based modules under a controlled from-scratch protocol, and it generalizes across eight backbones on iNat2021-mini. These results indicate that the channel descriptor, together with the per-channel gating that maps it to attention weights, is an important but underexplored aspect of lightweight channel attention in FGVR. --- ### A.X K2 Technical Report Authors: Cheolseung Baek, Dhammiko Arya, Eunki Kim, Gun Song, Gyoungeun Han, Hyunho Yang, Hyunjun Eun, Jin Kim, Junyoung Park, Juyun Wee, Minki Hong, Minkyung Park et al. Published: 2026-08-31 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.30181v1 We introduce A.X K2, a 688B-parameter Mixture-of-Experts (MoE) language model trained from scratch as a high-performance foundation for \emph{agentic} applications. Trained on approximately 8.5T tokens---fewer than its predecessor, A.X K1---on a smaller but higher-quality mixture with substantially expanded agentic and software-engineering data, it nonetheless improves over A.X K1 across the board, by over 30 percentage points on some benchmarks, reflecting large gains in token efficiency. To support long contexts efficiently, we introduce Sparse Gated Attention (SGA), which combines sparse attention with gated attention, and adopt Gated Norm (GN) to stabilize large-scale training. SGA is trained natively at 128K through a \emph{sparse} indexer warmup that optimizes the indexer against its own sparse top-$k$ selection rather than the dense attention distribution, making adaptation markedly cheaper: each query reads only 2,048 positions, yet long-context quality is unchanged and A.X K2 scores 94.6 on RULER out to 256K. The outlier suppression of GN in turn keeps 4-bit NVFP4 serving within one point of FP8 accuracy. A simple yet effective Think-Fusion recipe further lets users switch between thinking and non-thinking modes within a single unified model. Extensive evaluations show that A.X K2 performs competitively against strong open-weight baselines, matching or exceeding them on math and Korean-language benchmarks. --- ### Benchmarking Peptide-Protein Affinity Prediction Across Peptide and Target Shifts Authors: Jiaxin Tian, Darren An, Jun Li Published: 2026-08-31 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2608.30175v1 Peptide-protein affinity models are often evaluated with a single data split, obscuring whether they interpolate among measurements for observed targets or generalize across peptide or target shifts. We integrated three sources of quantitative peptide-protein binding data to obtain 11,349 deduplicated pairs and benchmarked ten peptide representations, ESM-2 protein embeddings, and six regressors under peptide-similarity, within-target, and leave-target-out partitions. Across 60 matched representation-regressor configurations, mean test Spearman correlations were 0.462, 0.669, and 0.530, respectively. The top configuration shifted from ECFP-16 count fingerprints with random forest in the first two settings to HELM-BERT with Extra Trees when exact target sequences were excluded. Representation-rank correlations ranged from -0.042 to 0.624 across partitions, whereas regressor-rank correlations ranged from 0.771 to 0.943. Learning curves showed that representation differences were largest with limited supervision and narrowed as training data increased. PeptideCLM-2 adaptation and simple element-wise interaction features provided no consistent gain over a frozen encoder and direct concatenation under the tested protocols. These conclusions are specific to a dataset that pools transformed Kd, Ki, and IC50 measurements and to target exclusion at the exact-sequence level. Peptide-protein affinity benchmarks should therefore align data partitions with the intended use and jointly assess the effects of data scale, molecular representation, and downstream learner. --- ### Science sandboxes measure the scientific capability of AI agents Authors: Arya S. Rao, Rodrigo I. Castro, Sager J. Gosai, Kenneth B. Hsu, Yasha Ektefaie, Shantanu Singh, Sangeeta N. Bhatia, Steven K. Reilly, Ryan Tewhey, Eric S. Lander, Pardis C. Sabeti Published: 2026-08-31 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2608.30165v1 Scientific progress depends not only on finding solutions, but on learning the rules that explain why they work and using that understanding to design better experiments. We introduce science sandboxes, a framework for studying this capability in AI agents through repeated cycles of experimentation, feedback, and hypothesis revision. Science sandboxes invite an agent to query the natural world in different ways, ranging from "wet" physical experiments, to "damp" predictive models trained on empirical data, to "dry" invented rules. By establishing a common experimental loop and a protocol for evaluating agents within it, science sandboxes allow assessment of both quantitative performance on specific metrics and qualitative scientific reasoning, across a spectrum of empirical verifiability. Here, we instantiate this framework in two biological settings, models of regulatory genomics and protein fitness prediction, and examine the capabilities of frontier agents. Across these settings, we could see when agents successfully optimized a quantitative metric without understanding the rules underlying the system. In particular, their scientific reasoning deteriorated when they encountered systems whose rules fell outside familiar biological priors. By highlighting such failure modes, science sandboxes make the frontier of scientific capability measurable and provide a controlled setting in which to study and ultimately expand it. --- ### Doc-REFRAG: Rethinking Multimodal Document Retrieval-Augmented Generation Authors: Ruofan Hu, Shengyang Xu, Minjie Hong, Xiaoda Yang, Sashuai Zhou, Ke Lei, Tao Jin, Zhou Zhao Published: 2026-08-31 Categories: cs.IR, cs.CV arXiv: https://arxiv.org/abs/2608.30163v1 Real-world knowledge resides in multimodal documents, necessitating retrieval-augmented generation (RAG) for accurate question answering. However, existing multimodal RAG models are primarily designed for single-image or closed-document settings and exhibit limited accuracy in realistic multi-image scenarios. Moreover, processing numerous retrieved images incurs substantial computational overhead from irrelevant visual tokens. To address these challenges, we introduce DocLongRAG, a large-scale dataset of 343K question--answer pairs, each associated with an average of 37.4 retrieved images to reflect authentic RAG workflows. Building on this dataset, we propose Doc-REFRAG, a question-guided framework that compresses visual tokens into coarse chunks and selectively expands question-relevant ones via a lightweight RL-based selector. Experiments on six benchmarks show that Doc-REFRAG outperforms eleven strong baselines, achieving state-of-the-art accuracy with significantly lower inference latency. Our resources are available at https://github.com/Collab-Gen/Doc-REFRAG. --- ### Reinforcement Learning for Symbolic Equation Solving Authors: Kevin P O Keeffe Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30162v1 We present a reinforcement-learning agent that solves symbolic equations step by step, covering both nonlinear closed equations (radicals, exponentials, trigonometric) and a controlled class of restricted-open families requiring a change of variables (CoV) such as completing the square. We cast algebra as an MDP with a dynamic action space and a tree-structured policy (TreeMLP). The main policy learns from reward alone with no supervised solution traces; the CoV substitution comes from a supervised generator interchangeable with a CAS call. On closed equations the agent matches the prior best on CommonCore (0.93 greedy vs. ConPoLe's 0.925) under a single policy. On four hand-designed restricted-open families (quadratic, cubic, quartic, exponential) it reaches 0.79 beam / 0.67 greedy, exceeding the strongest non-learned search (A-star, 0.64). Learned CoV timing has content only on the exponential family, the one requiring a nested CoV, where a natural rule solves none of the held-out equations while the policy solves 75% from reward alone. At 10x scale a sharp seed-level bimodality emerges; a UCB learning-progress curriculum shows a non-significant positive trend toward mitigating it. We do not claim general open-equation solving: every open-equation result is confined to these four controlled families. --- ### AI-enabled Low-Cost 3D Maize Ear Morphometry Platform at Breeding Scale Authors: Therin Young, Elijah Rodriguez, Lisa Coffey, Talukder Zaki Jubery, Adarsh Krishnamurthy, Patrick Schnable, Baskar Ganapathysubramanian Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30161v1 Maize ear geometry (length, width, curvature, and volume) is closely tied to yield and grain-filling outcomes, but existing high-throughput phenotyping pipelines remain constrained by the cost, labor, and specialized hardware they require. We developed and validated a low-cost pipeline that reconstructs a watertight 3-D mesh of a maize ear from a single 20-second video captured with a consumer-grade DSLR on a motorized turntable under uniform LED illumination. Camera poses from a multi-seed COLMAP procedure initialize a Neural Radiance Field (NeRF), and a cylindrical holder of known diameter, visible in every frame, provides automatic metric scaling with downstream geometric quality control. Applied to 300 ears spanning a diverse maize inbred panel, 250 (83.3%) passed automated processing and quality control. Skeleton length agreed with manual caliper measurements across all 250 ears (R^2 = 0.964, RMSE = 4.68 mm), and convex-hull volume agreed with water-displacement volume on a 15-ear subset spanning the full size range (R^2 = 0.982, RMSE = 5.26 mL). Residual length error grew with ear curvature, whereas bounding-box height, which records the same straight-line chord as calipers, showed no such trend; the discrepancy therefore originates in the measurement definition, since calipers record the chord while skeleton length traces the geodesic arc. The capture hardware costs approximately 607 USD, and operator involvement fell from roughly five minutes to one minute per ear, with all downstream processing running unattended. The platform provides a foundation for breeding-scale 3-D ear phenotyping. --- ### CPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation Authors: Kwangmin Ki, Yunhun Nam, Jongheon Jeong, Jaehyung Kim Published: 2026-08-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.30158v1 Supervised fine-tuning (SFT) is the de facto standard for adapting large language models (LLMs) to target domains, but it often degrades the model's general capabilities, a phenomenon known as catastrophic forgetting. Existing approaches typically modify the SFT loss to mitigate forgetting, but they inevitably operate along a domain-generality trade-off. In this work, we step outside this trade-off by decoupling the two capabilities at the model level: we keep the original base model for general capability, and selectively invoke the SFT expert only when domain-specific knowledge is required. Specifically, we propose CPR (Critical-Point Routing), a token-level routing framework between a base model and its expert derivative, based on critical tokens where the base model fails but the expert succeeds. We train a lightweight hierarchical router that estimates the expert-call probability per token, and pair it with a tailored inference procedure that combines momentum smoothing and threshold gating. Across diverse model-domain configurations, CPR achieves state-of-the-art across all settings, surpassing SFT expert by 1.4-5.5% in domain performance while recovering its general-capability drop from 3.4-14.5% to at most 0.5%, with minimal overhead from invoking the expert on only one-third of tokens. --- ### Reactivating Test-Time Scaling for Plane Geometry Problem Solving Authors: Xiaoqiang Kang, Shengen Wu, Maizhen Ning, Xiaobo Jin, Kaizhu Huang, Yutao Yue, Xiaowei Huang, Qiufeng Wang Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30156v1 Plane geometry problem (PGP) solving has become a critical benchmark for multimodal reasoning because it requires accurate visual perception and precise multi-step symbolic deduction. Although test-time scaling (TTS) has demonstrated remarkable success in general mathematical reasoning, it fails to scale effectively under the symbolic-program paradigm for plane geometry. We identify two key obstacles: limited reasoning diversity induced by rigid symbolic programs and insufficient explicit visual grounding before symbolic deduction. To address these issues, we propose Multi-Trace Synthesis (MTS), which converts each symbolic program into heterogeneous reasoning traces, including executable Python scripts and CoT-augmented variants. We further propose Perception-Augmented (PA) training, which parses diagrams into structured semantic clauses before deduction, and Consensus-Guided Multi-Trace Ensemble (CG-MTE) for efficient self-adaptive inference. Experiments on three geometry benchmarks show that our method consistently improves PGP-solving across model scales and achieves strong performance against both general-purpose MLLMs and specialized geometry solvers. Under test-time scaling, CG-MTE achieves comparable accuracy to high-budget self-consistency while reducing sampling cost by up to 8x. Code and data are publicly available at https://github.com/Jason8Kang/ReTTS-PGPS. --- ### Converse and Collision-Based Achievability for Node Localization with Hybrid Distance-Spectral Graph Positional Encodings Authors: Zimo Yan, Yifan Li, Hao Li, Zheng Xie, Chang Liu, Zheming Tu, Yuan Wang Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30152v1 Graph positional encodings are widely used in graph neural networks and graph Transformers, yet it remains unclear when the code itself can identify nodes. We study a hybrid distance-spectral encoding that combines anchor-distance profiles with quantized low-frequency Laplacian-energy coordinates. Treating the encoding as an observation map yields a simplex-refined converse, an exact collision factorization \(κ_H=κ_Dκ_{S|D}\), and the collision information \(I_H=-\logκ_D-\logκ_{S|D}\). On random regular graphs, the criterion is made explicit through a bounded-correlation Gaussian-wave surrogate; for actual Laplacian-energy coordinates, we give the distance-conditioned spectral collision condition sufficient for conditional actual-coordinate achievability. Experiments show that \(I_H/\log n\) calibrates localization success, and PE-only structural task probes on Universal Dependencies trees show that hybrid encodings better recover syntactic-tree geometry than distance-only or spectral-only baselines. --- ### CedarCypress3D: an annotated UAV-LiDAR dataset of individual trees in planted cedar and cypress forests Authors: Katsuto Shimizu, Fumiaki Kitahara, Tomohiro Nishizono, Hideki Saito, Masayoshi Takahashi, Shingo Obata, Shunsuke Tei, Naoyuki Furuya, Tomoya Goto, Eiji Kodani, Yusuke Yamada Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30149v1 Individual tree measurements derived from Light Detection and Ranging (LiDAR) mounted on Unmanned Aerial Vehicles (UAV) provide valuable information for forest inventory, ecosystem monitoring, and sustainable forest management. Recent advancements in machine learning have increased the demand for annotated datasets to develop and evaluate point cloud-based approaches, especially for individual tree segmentation. However, publicly available annotated UAV-LiDAR datasets in temperate forests are limited. In this article, we present CedarCypress3D, a manually annotated UAV-LiDAR dataset collected in Japanese cedar (Cryptomeria japonica) and Japanese cypress (Chamaecyparis obtusa) plantations in Japan. The dataset consists of UAV-LiDAR point clouds and field survey measurements from 34 circular plots across two sites with different topographic characteristics, along with terrestrial LiDAR point clouds available for a subset of 22 plots. A total of 1,627 trees were measured in the census field survey and manually annotated to match the corresponding trees in the UAV-LiDAR point clouds. For the subset of plots with terrestrial LiDAR data, semantic labels (i.e., stem and non-stem) were additionally assigned to tree points in the UAV-LiDAR data. CedarCypress3D provides high-quality annotated UAV-LiDAR data for developing and evaluating individual tree instance segmentation and semantic segmentation methods in temperate planted forests. The dataset can also support research on tree attribute prediction and multi-platform LiDAR analysis. The dataset is publicly available at https://doi.org/10.5281/zenodo.22168721. --- ### CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents Authors: Amir Saeidi, Zehua Zhang, Rishitosh Singh, Naman Ahuja, Vivek Gupta, Ali Payani, Gaowen Liu, Jayanth Srinivasa, Chitta Baral Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30147v1 Large language model (LLM) agents are increasingly deployed in long-horizon, interactive, and stateful environments. In these settings, a single wrong action, such as refunding the wrong purchase, can cause irreversible task failure and must be intercepted before execution. Such failures may not appear in every single run, but can emerge across repeated trials, making reliability across steps and trials critical. However, ensuring agentic reliability is challenging: even frontier LLMs struggle to explain why an action may be wrong, especially in long, intertwined trajectories governed by domain-specific policies. Much recent work relies on prompt-based critique agents, while optimization-based methods lack a systematic way to produce rich verification rationales for training. We address this gap with CAST, a critique-aware training framework that converts sparse task outcomes into action-level supervision for critique learning and policy optimization. CAST analyzes agent trajectories to synthesize structured rationales explaining action validity under partial observability. The resulting critique model is used to construct critique-aware training data for optimizing the policy model. Fine-tuning Qwen3-family models on dynamic tool-calling benchmarks, CAST improves reliability across domains, outperforming GPT-OSS-120B by over 10% pass^4 on Retail tasks and yielding an additional 9% improvement on Telehealth in an out-of-domain setting. These results demonstrate that critique-aware training improves the robustness of LLM agents in realistic dynamic environments. --- ### Repeatability Characterisation and Error Budget of a Consumer Structured-Light Scanner for 3-D Wound Geometry:A Rigid-Phantom Study Authors: Pushkal Kumar, Aadit Aggarwal, Karlen Aleksanyan Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30143v1 We characterise the measurement error of a free- hand consumer structured-light scanner used to derive three- dimensional geometric wound descriptors. Rigid wound-care phantoms cannot change, so every difference between repeat scans of one site is measurement error; all repeats come from a single scanner unit, nine sites and 23 scans, so this charac- terises one instrument. The 95 percent repeatability limit for reconstructed surface area is a factor of 4.8, with a confidence interval from 3.0 to 7.0, so rescanning an unchanged site can shift the reading from a 79 percent decrease to a 377 percent increase. Forty-four of 45 descriptors fall below an intraclass correlation of 0.50, and none of 248 descriptor and pipeline combinations reaches 0.75. An error budget formed by holding the analy- sis region fixed, leaving sensor and reconstruction untouched, bounds the share of variance attributable to how much surface the operator captured at 75 percent for surface area, 91 percent for hull area and 95 percent for bounding-box diagonal; only hull volume is majority instrumental, at 48 percent, so a better sensor would buy little. No wound is delineated anywhere in the chain, so the comparison against the four-week area reduction used clinically to predict healing, a ratio near 2.1, is a lower bound on the noise an unsegmented pipeline must overcome, not a measurement of wound-area reproducibility. Standardising the analysis region cuts the limit to 2.13, meeting that ratio rather than clearing it. Statistical outlier removal imposes a measured systematic area deficit near 11 percent. --- ### Balancing Privacy, Utility, and Safety in LLM Alignment through Preference Optimization Authors: Dishu Yang, Jingjing Liu, Jize Li Published: 2026-08-31 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.30141v1 Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence privacy-relevant memorization. We examine whether adding synthetic privacy-preference pairs to Direct Preference Optimization (DPO) is associated with lower canary-based memorization signals without modifying the objective or introducing a formal privacy mechanism. We propose Privacy-Pressure Preference Mixing (P3M), a data-composition protocol that varies the amount of privacy-preference data while keeping helpfulness and harmlessness preference data fixed. We evaluate a non-privacy Baseline and privacy-mixing ratios of 0.5, 1.0, and 2.0 using Gemma 3 270M-IT across five random seeds and validate the same four conditions using 4-bit-quantized Gemma 2 2B-IT across three seeds. Overall, under the tested conditions, privacy-preference mixing is associated with lower mean canary suffix log-likelihood proxy values across both model settings and lower aggregate membership-inference attack performance relative to the Baseline in the mixed-source 2B evaluation. Specifically, across the privacy-aware 2B configurations, the mean area under the receiver operating characteristic curve (AUROC) ranges from 0.596 to 0.629, and the mean area under the precision-recall curve (AUPRC) ranges from 0.541 to 0.575, compared with 0.804 and 0.790, respectively, for the Baseline. However, the reduction in membership distinguishability does not hold uniformly across data sources. Moreover, the relationship between the privacy ratio and harmlessness preference accuracy varies by model setting, whereas helpfulness preference accuracy remains broadly stable. These findings suggest that P3M should be viewed as a lightweight empirical protocol for examining privacy-utility-safety trade-offs rather than as a formal privacy guarantee or a defense against extraction attacks. --- ### Verification-Aware Training for Speculative Decoding Authors: Geonmo Gu, Byeongho Heo, HeeJae Jun, Yoohoon Kang, Sangmin Lee, Sangdoo Yun, Dongyoon Han Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30135v1 Speculative decoding accelerates large language model inference by using a draft model to generate candidate tokens, which are verified by the target model in a single forward pass. Verification proceeds sequentially and discards every position from the first rejection onward, yet existing draft training relies on token-level imitation of the target with a fixed per-position weighting that reflects neither property. We introduce Verification-Aware Training (VAT), a plug-in framework that simulates verification at every training step and turns the resulting accept and reject patterns into supervision. VAT consists of two components: (i) a verification head, a lightweight jointly trained binary classifier that supervises the draft model on whether each position survives sequential verification; (ii) verification-adaptive weighting, which replaces the fixed weighting schedule by keeping full weight up to each sample's first rejection point and re-anchoring the decay to start there. VAT modifies only the training objective, so it can be layered on top of existing methods without changing the draft architecture, the target model, or the inference procedure. Applied to EAGLE-3 and DFlash on Qwen3-4B, Qwen3-8B, and LLaMA-3.1-8B, VAT improves average acceptance length by up to 11.4% and wall-clock speedup by up to 8.7%, with consistent gains across math, code, and chat benchmarks. Code will be available at https://github.com/naver-ai/vat --- ### E-SENS: Exclusion-Sensitive Penalization for Negative-Constraint Retrieval Authors: Yerang Kim, Jiyoon Myung, Joohyung Han Published: 2026-08-31 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2608.30130v3 Retrieval-augmented language models can fail to respect negative constraints when the retriever supplies evidence about concepts the user explicitly excluded. Beyond explicit negation, queries may ask for answers that include one concept while excluding another, or for entities that belong to a category but differ from a closely related instance. Because the excluded concept still appears in the query text, dense retrievers may assign high similarity to documents about that concept even when the user asks to avoid it. We introduce E-SENS, a training-free reranking method for negation-sensitive retrieval. E-SENS extracts a compact trap query for the excluded side and subtracts trap-query similarity from the original-query retrieval score. On ExcluIR, E-SENS shows a clear recall-violation trade-off across four embedding models and reduces trap retrieval at recall-preserving settings. --- ### Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention Authors: Bingde Liu, Wu Ran, Jinglei Zhang, Huanhuan Yuan, Chao Ma Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30129v1 This work presents $\textbf{Lapis}$, a $\textbf{l}$inear-$\textbf{a}$ttention-based $\textbf{pi}$xel-$\textbf{s}$pace generative framework that achieves efficient and high-fidelity depth estimation with one-step diffusion. While generative frameworks have significantly advanced monocular depth estimation with superior detail fidelity, the $\mathcal{O}(N^2)$ complexity of standard attention and the multi-step denoising process introduce prohibitive computational costs when scaling them to high-resolution image applications. Although linear attention and one-step prediction are intuitively viable, directly applying them leads to poor structural consistency, detail loss, and noise. Lapis rectifies these limitations through a coarse-to-fine hierarchy. Specifically, a Patch-level Consistency Module restores structural coherence by integrating semantic and spatial priors. Subsequently, a Pixel-level Refinement Module recovers sharp geometric boundaries via skip-connection-based pixel correspondence. Furthermore, to mitigate sampling noise inherent in one-step diffusion, we leverage the manifold assumption and adopt a direct $\mathbf{x}$-prediction strategy to target the clean data manifold. Extensive evaluations on multiple benchmarks demonstrate that Lapis consistently achieves state-of-the-art (SOTA) accuracy and boundary sharpness across various resolutions, reducing inference latency by up to 7.6$\times$ at 1080P and 10.9$\times$ at 1440P resolution compared to previous SOTA generative models. --- ### VIBE: Video Instruction-aligned Background music gEneration Authors: Aryan Vijay Bhosale, Vaibhavi Lokegaonkar, Vishnu Raj, Gouthaman KV, Sreyan Ghosh, Ramani Duraiswami, Lie Lu, Dinesh Manocha Published: 2026-08-31 Categories: cs.SD, cs.AI, cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.30125v1 Current video-to-music (V2M) models lack semantic control and fail to penalize instruction violations, largely due to their reliance on reconstruction objectives and the representational bottleneck of static cross-modal conditioning in Diffusion Autoregressive (DAR) architectures. To resolve this, we introduce VIBE, a novel text-and-video-to-music (T+V2M) generation model that leverages: (1) Conditioning Connection, a depth-wise cross-layer conditioning mechanism that dynamically bridges the planning and diffusion refinement heads and (2) a comprehensive reward modeling taxonomy, optimizing for both hard, verifiable constraints (e.g., tempo, key) and soft, subjective qualities (e.g., musicality, multimodal alignment) with a structured 5-stage training curriculum. Upon evaluation using audio-visual alignment, instruction following, and audio quality metrics, along with a subjective human evaluation study, we observe that VIBE demonstrates enhanced controllability and instruction adherence while performing comparably to most evaluated baselines on generation fidelity and multimodal alignment. --- ### TPR-Attention for Combinatorial Generalization Authors: Melisa Civelekoğlu, Isabeau Prémont-Schwarz Published: 2026-08-31 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2608.30124v1 Systematic generalization remains a significant challenge in deep learning. In particular, combinatorial generalization - generalizing to new configurations of known factors of variation - is effortless for humans but difficult for standard neural architectures that rely on statistical correlations rather than explicit structural representations. We introduce a new architectural component that embeds structured inductive bias into deep learning: an attention mechanism operating over tensor-product representations (TPRs). Through controlled experiments on compositional tasks, we show that this TPR-attention mechanism outperforms existing architectural components in combinatorial generalization. These results highlight the value of integrating explicit compositional structure into neural attention and point toward a promising path for models capable of systematic generalization. --- ### Aligning Multi-Trajectory Supervision with Policy Optimization for VLA Driving Authors: Tian Zhang, Zhuo Huang, Hongrui Ye, Yu Wu, Zengmao Wang, Kaixuan Zhou Published: 2026-08-31 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.30122v1 Vision-language-action (VLA) driving methods increasingly combine multi-trajectory imitation learning with group-relative policy optimization (GRPO), making trajectory selection critical to final performance. However, some high-scoring trajectories that improve imitation can degrade subsequent GRPO by inducing advantage estimates misaligned with the current policy's feasible behavior distribution, driving updates away from safe and compliant behaviors. To address this, we propose a novel framework that aligns multi-trajectory supervision with policy optimization. To address the policy gradient bias induced by infeasible noisy trajectories outside the feasible region, augmented trajectories are constrained to a neighboring manifold of the ground-truth feasible region, and a Pareto-optimality criterion is adopted in place of the conventional aggregate score, retaining only non-dominated candidates and thereby filtering out conflicting samples at the source. To ensure that expanded trajectory supervision is effectively absorbed during policy optimization, we introduce two complementary mechanisms: feasibility-first advantage assignment and dynamic distillation. The former adapts Pareto credit to the feasibility composition of each rollout group and guides fully infeasible groups toward safe references. The latter updates teacher trajectories across refinement rounds to continually transfer useful supervision. Together, they progressively translate the benefits of expanded supervision into policy improvement. On NAVSIM v1 and v2, our method achieves 91.4 PDMS and 89.1 EPDMS, respectively, under single-trajectory inference, and recovers 440 of 658 initially failed scenes, 11.1\% higher than the original GRPO baseline. --- ### Manacá-1B: An Open, Reproducible Brazilian-Portuguese Language Model and a Tokenizer-Aware, Paired Evaluation Authors: Bruno Leonardo Santos Menezes, Carlos Leonardo Souza Cardoso, Fabio Andre Machado Porto Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30114v1 Brazilian Portuguese remains under-served by open language models, and the few that exist are difficult to reproduce and are often compared without measures of uncertainty. We release Manacá-1B, an open decoder-only model of 1.72 billion parameters trained from scratch for Brazilian Portuguese with a fully containerized, reproducible pipeline. The pretraining is stable, with zero skipped or NaN steps and self-recovering loss spikes, and we release its full log and dynamics. We evaluate the model against nine open baselines on four Portuguese benchmarks under a single harness. Every comparison reports a standard error and a paired significance test, and the harness is validated against previously published numbers. On last-word prediction Manacá-1B is the strongest model below the 7B scale, exceeding both Tucano-1b1 and Tucano-2b4 on LAMBADA-PT with large paired margins; it is competitive on commonsense completion and near chance on multiple-choice reasoning, as are all small base models. Along the way we document a concrete evaluation pitfall: converting a SentencePiece tokenizer with case-folding normalization to the HuggingFace fast format silently drops the normalizer, routing every capitalized token to byte-fallback and depressing scores in a way that is invisible in aggregate metrics. The uncorrected tokenizer lowered LAMBADA-PT accuracy from 45.3 to 25.0; we quantify the effect and provide a one-line fix that reproduces the training tokenizer exactly. Code, raw training and evaluation logs, per-example prediction vectors, the model weights, and the corrected tokenizer are released so that every number in this paper can be recomputed. --- ### Supraglacial Lake Fate Is Knowable Long Before the Season Ends Authors: Emam Hossain, Md Osman Gani Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30113v1 A supraglacial lake on the Greenland Ice Sheet ends its melt season in one of four ways: it drains rapidly through a hydrofracture, drains slowly across the surface, refreezes in place, or is buried by late-season snowfall. Which one occurs decides whether the meltwater reaches the ice bed. Satellite classifiers recover the outcome accurately but only after the season closes, and how much of a season each outcome actually requires has never been measured. We measure it directly: holding the representation and the classifier fixed, we truncate the input at $14$ cutoffs from 1 May to 31 December, retrain at each, and record the earliest cutoff at which each outcome's per-class $F_1$ reaches a fixed target. The outcomes resolve in a consistent order, two of them months early: rapid drainage by 15 July and slow drainage by 1 August, $92$ and $75$ days ahead of the earliest date a full-season pipeline can be computed at all, with buried and refreeze following at $44$ and $30$ days. Five further learners, from a majority-class floor and $54$ summary statistics to a trigger-based early classifier, leave the ordering intact: every learner that produces a per-class trajectory reproduces it despite end-of-season accuracies differing by up to $18$ percentage points, and it survives leave-one-basin-out evaluation, though not the substitution of machine labels for expert ones in an unseen season. Every feature we compute at day $t$ reads only days up to $t$, at a cost of at most $1.3$ percentage points. A monitoring system should therefore not have one release date: rapid drainage can be flagged on 15 July, three months before a full-season pipeline can be computed at all. --- ### Can LLMs Take the Pulse of the Economy? A Real-Time Evaluation of LLM Nowcasts on Macroeconomic Indicators Authors: Xinyue Zhao, Ruiyi Zhang, Liqin Ye, Rui Cao, Pengtao Xie, Sudheer Chava Published: 2026-08-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.30110v1 Nowcasting headline macroeconomic indicators, i.e., estimating an indicator's value for the current reference period before its official release, is critical for monetary policy and financial markets, and central banks devote dedicated teams of expert economists to producing such estimates. Large language model (LLM) agents are a promising candidate for this task, combining broad world knowledge with real-time web search and supporting queries at higher frequency than institutional nowcasts. Evaluating their nowcasting capability is, however, challenging: headline indicators such as GDP and CPI are widely reported and likely memorized during pretraining, so any evaluation on historical releases is vulnerable to data contamination. To address this, we introduce LiveMacroEval, a live, contamination-resistant benchmark in which LLM agents produce hourly nowcasts for sixteen major U.S. macroeconomic indicators over a pre-release window closing at each official release. Nowcast quality is assessed through a LiveMacro Score against announcement-window equity returns and a LiveBetting Score from simulated Polymarket-style trading, with Federal Reserve regional-bank nowcasts, the Bloomberg ECOS professional consensus, and an auto-ARIMA baseline as comparators. Over six months with four state-of-the-art LLM agents configured with web search, aggregate nowcast accuracy is broadly comparable to the institutional and professional benchmarks, with performance varying widely across individual indicators. This highlights LLM agents' potential as real-time estimators of macroeconomic conditions. --- ### COGTRL: Training LLMs for Scientific Discovery Assistance using Cognitive Traces via Reinforcement Learning Authors: Shrinidhi Kumbhar, Santosh Mashetty, Divij Handa, Kevin Coutinho, Siddharth Sambhaji Ghule, Chitta Baral Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30109v2 Large Language Models (LLMs) trained on extensive scientific research are increasingly integrated as assistants for scientific discovery. However, most research papers omit the fine-grained cognitive process of examining constraints, failed alternatives, and iterative decisions required to achieve the desired goal. Such cognitive processes are vital for real-world scientists working toward specific goals under constraints. In this paper, we show that LLMs, when trained to produce such cognitive traces, perform better as scientific discovery assistants than when trained solely on scientific literature. We propose COGTRL, a trajectory-level reinforcement learning framework that trains LLMs to emulate cognitively grounded reasoning by jointly optimizing cognitive traces and the scientific steps produced in an interleaved manner. Across two 3B-parameter models and two scientific domains (AI and Materials Science), COGTRL improves method quality by an average of 7.85 points over comparable 3B model baselines and achieves competitive performance relative to 70B parameter models. Moreover, analysis by domain experts shows a preference for methods generated by COGTRL over the baselines. --- ### AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP Authors: Joan Nwatu, Tsedeniya Solomon Amare, Longju Bai, Bontu Fufa Balcha, Zayd Bashir, Angana Borah, Zara Burzo, Yubin Choi, Naihao Deng, Samika Gupta, Michel Faloughi, Claude Kwizera et al. Published: 2026-08-31 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.30107v2 Understanding which countries are represented in NLP datasets is essential for identifying gaps, targeting data collection, measuring progress, and informing AI policy. However, geographic metadata is very rarely available, and country-level representation is often hidden behind broad language-level claims. We introduce AtlasNLP, a country-aware atlas of over 13,000 NLP dataset records across normalized NLP task categories, tracking both the populations represented and where datasets are produced. AtlasNLP includes AtlasNLP-Gold, a human-curated reference set, and AtlasNLP-Core, an ACL-derived large-scale collection. Using this resource, we show that (1) dataset coverage is highly uneven across countries and tasks; (2) dataset production and representation are geographically asymmetric; and (3) language coverage does not imply geographic representation. These findings reveal blind spots in current dataset documentation practices and motivate more explicit geographic metadata for country-aware NLP evaluation. --- ### A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets Authors: Jimmy Gammell, Kaushik Roy Published: 2026-08-31 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.30105v1 Deep learning-based side-channel analysis has historically focused on single-byte targets and manually cropped traces, which risks discarding exploitable leakage. While recent work has proposed specialized architectures and resampling techniques to address this gap, the literature lacks a simple transformer baseline for simultaneous full-key attacks on uncropped traces. We present an open-source transformer implementation for uncropped full-key attacks which uses the standard transformer encoder backbone, adapting only the input and output layers to the side-channel setting. We release our implementation, training recipes, and pretrained weights for uncropped ASCADv1f, ASCADv1r, and CHES-CTF-2018 which achieve performance competitive with previously-reported results, while using less than 10GB of VRAM and requiring at most 3.34 hours of training on a single NVIDIA A6000. ---