# Research Papers — 2026-08 · bundle page 211 of 240 > Full-text markdown of papers #10501–10550 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/211 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/210.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/212.md) ### Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations Authors: Chunlei Meng, Jacqueline J. Pang, Pengbin Feng, Zhenyu Yu, Chun Ouyang, Zhongxue Gan Published: 2026-08-04 Categories: cs.AI, cs.MM arXiv: https://arxiv.org/abs/2608.03611v2 Multimodal Sentiment Analysis (MSA) integrates text, audio, and vision to infer human affect, yet real-world multimodal observations are often incomplete. Existing methods for incomplete-observation MSA mainly follow two paradigms. Reconstruction-based methods recover missing information from observed modalities, while joint-representation methods learn directly from incomplete inputs. Although effective, these methods usually treat modality reliability only implicitly within representation learning or fusion design rather than modeling it explicitly. We argue that modality reliability is a central variable in incomplete-observation settings. Failure to model it explicitly gives rise to two related issues. The first is reliability mismatch, in which the affective evidence retained by each modality varies across samples and missing rates. The second is reliability propagation bias, in which messages from degraded modalities may adversely affect cross-modal interaction and predictive performance. To address these issues, we propose MRCF, a Modality Reliability-Calibrated Framework for MSA with incomplete observations. MRCF contains a Reliability-Aware Branch that estimates sample-specific modality reliability from intramodal quality cues and cross-modal semantic consistency, a Reliability-Guided Interaction Branch that uses the estimated scores to modulate cross-modal information flow, and a Reliability-Calibrated Fusion Module that integrates reliability and semantic cues for final prediction. Experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS show that MRCF achieves strong performance under standard incomplete-observation protocols. Further analyses provide evidence that explicit reliability modeling helps mitigate reliability mismatch and reliability propagation bias during interaction and fusion. --- ### Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations Authors: Chunlei Meng, Jacqueline J. Pang, Pengbin Feng, Zhenyu Yu, Chun Ouyang, Zhongxue Gan Published: 2026-08-04 Categories: cs.AI, cs.MM arXiv: https://arxiv.org/abs/2608.03611v1 Multimodal Sentiment Analysis (MSA) integrates text, audio, and vision to infer human affect, yet real-world multimodal observations are often incomplete. Existing methods for incomplete-observation MSA mainly follow two paradigms. Reconstruction-based methods recover missing information from observed modalities, while joint-representation methods learn directly from incomplete inputs. Although effective, these methods usually treat modality reliability only implicitly within representation learning or fusion design rather than modeling it explicitly. We argue that modality reliability is a central variable in incomplete-observation settings. Failure to model it explicitly gives rise to two related issues. The first is reliability mismatch, in which the affective evidence retained by each modality varies across samples and missing rates. The second is reliability propagation bias, in which messages from degraded modalities may adversely affect cross-modal interaction and predictive performance. To address these issues, we propose MRCF, a Modality Reliability-Calibrated Framework for MSA with incomplete observations. MRCF contains a Reliability-Aware Branch that estimates sample-specific modality reliability from intramodal quality cues and cross-modal semantic consistency, a Reliability-Guided Interaction Branch that uses the estimated scores to modulate cross-modal information flow, and a Reliability-Calibrated Fusion Module that integrates reliability and semantic cues for final prediction. Experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS show that MRCF achieves strong performance under standard incomplete-observation protocols. Further analyses provide evidence that explicit reliability modeling helps mitigate reliability mismatch and reliability propagation bias during interaction and fusion. --- ### Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR Authors: Yuan Xie, Jiaqi Song, Xianliang Wang, Ming Lei, Jie Gao, Jie Wu Published: 2026-08-04 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2608.03610v2 Modern LLM-based ASR systems have established multilingual capability as a standard feature, leveraging large-scale multilingual corpora and LLMs' cross-lingual knowledge to achieve competitive performance across multilingual benchmarks. However, jointly modeling languages with heterogeneous acoustic, phonological, and lexical characteristics inevitably introduces optimization conflicts, undermining language-wise specialization. To address this challenge, we propose Language-Specialized Multi-Teacher On-Policy Distillation (LS-MOPD), which decouples language-specific knowledge acquisition from multilingual capability integration: language-specialized teachers are independently optimized via reinforcement learning (RL), with their expertise then integrated into a generalist multilingual student through language routing and token-level multi-teacher distillation, thereby reducing direct cross-lingual optimization conflicts. We further explore static and dynamic acoustic-prefix configurations to examine how teacher-student prefix consistency influences the efficacy of on-policy distillation. Experiments on benchmarks covering Mandarin, Mandarin subdialects, Cantonese, and English demonstrate that LS-MOPD substantially outperforms RL baselines and surpasses the empirical performance envelope defined by the best-performing RL teachers on nearly all benchmarks, revealing its potential to generalize beyond all teachers in multilingual ASR. --- ### Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR Authors: Yuan Xie, Jiaqi Song, Xianliang Wang, Ming Lei, Jie Gao, Jie Wu Published: 2026-08-04 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2608.03610v1 Modern LLM-based ASR systems have established multilingual capability as a standard feature, leveraging large-scale multilingual corpora and LLMs' cross-lingual knowledge to achieve competitive performance across multilingual benchmarks. However, joint modeling of languages with heterogeneous acoustic, phonological, and lexical characteristics inevitably introduces optimization conflicts, undermining language-wise specialization. To address this challenge, we propose Language-Specialized Multi-Teacher On-Policy Distillation (LS-MOPD), which decouples language-specific knowledge acquisition from multilingual capability integration: language-specialized teachers are independently optimized via reinforcement learning (RL), after which their expertise is integrated into a generalist multilingual student through language routing and token-level multi-teacher distillation, thereby reducing direct cross-lingual optimization conflicts. We further explore two acoustic-prefix configurations, static and dynamic, to examine how teacher--student prefix consistency influences the efficacy of on-policy distillation. Experiments on benchmarks covering Mandarin, Mandarin subdialects, Cantonese, and English demonstrate that LS-MOPD substantially outperforms RL baselines and consistently surpasses the empirical performance envelope defined by best-performing RL teachers, revealing its potential to generalize beyond all teachers in multilingual ASR. --- ### Formal Verification of Agentic Systems over Operational Data Authors: Alejandro J. Mercado, Alessio Lomuscio Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03609v1 Agentic systems driven by large language models (LLMs) are increasingly deployed in real-world workflows where they act on persistent operational data. Before deployment, these systems need to be verified against business requirements that govern workflow execution and data evolution. However, existing approaches do not provide such system-level guarantees, as they mainly constrain or analyse behaviour at the agent's interface level. We study here the verification of agentic systems comprising a single LLM and a tool orchestration harness over relational operational data. We formalise them as Stateful Tool-Enabled Agentic Deployments (STEADs), give their semantics, define the problem of verifying them against First-Order Computation Tree Logic (FO-CTL) specifications, and show that it is undecidable. We identify sufficient conditions for exact preservation of FO-CTL specifications under a finite-domain restriction, over which verification is PSPACE-complete. The key requirement is that renaming opaque identifiers in the data must correspondingly rename the selected tool calls. We show that LLM-driven agents can violate this condition and introduce a canonical deployment wrapper that guarantees it for arbitrary base agents while preserving already-equivariant behaviour. We prove that computing canonical representations required by this construction is graph-isomorphism-hard. Finally, we illustrate our framework on an LLM agent orchestrating a case-management workflow. --- ### Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents Authors: William Bolton, Philip Torr Published: 2026-08-04 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.03606v1 Clinical development is sequential decision-making under uncertainty, where a sponsor must plan a portfolio of experiments from heterogeneous evidence. We study this setting by framing oncology clinical development as an offline decision-making problem in which an agent predicts the next six-month trial portfolio of an oncology drug program from information available at the decision date. To support this, we construct a temporal dataset that combines 31.7k heterogeneous public data records, including trial registries, regulatory reviews, sponsor filings, utilization data, and epidemiology, into 881 offline decision episodes across 45 historical programs. We compare four offline objectives: behavioral cloning, reward-weighted behavioral cloning, learned-reward training, and value-based implicit Q-learning against four frontier LLM agents that share a common date-gated retrieval scaffold across held-out drug, sponsor, drug-class, and temporal splits. Models trained offline outperform the non-fine-tuned baselines, particularly in the post-August 2025 contamination-clean holdout. Reward-weighted behavioral cloning performs the best, obtaining 46.2% indication F1 and 14.2% strict F1 against 25.0% and 2.1%, respectively, for the best-performing tool agent on each metric. These results suggest that structured offline learning can teach agents to plan clinical experiments. --- ### FraQ: Efficient Coordinate-Space Recompression for Federated Low-Rank Adaptation Authors: Shenghui Li, Thiemo Voigt Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03605v1 Federated fine-tuning with Low-Rank Adaptation (LoRA) enables efficient collaborative adaptation of Large Language Models (LLMs) without centralizing private data. However, LoRA's two-factor parameterization creates an aggregation mismatch across clients: naively averaging the factors does not recover the average of their induced updates. This mismatch can be avoided by forming the exact aggregate in the full weight space and then recompressing it, but decomposing the resulting dense matrix is computationally expensive and memory-intensive. We propose FraQ, an efficient coordinate-space recompression method for federated LoRA. Starting from stacked factors that exactly represent the aggregate, FraQ factorizes it into an orthonormal basis and a compact coordinate matrix. It then recovers the singular spectrum from a small Gram matrix, selects the smallest rank satisfying a prescribed energy threshold, and maps the selected coordinate subspace back through the basis to construct the global adapter. Experiments on text classification and commonsense reasoning benchmarks show that FraQ achieves accuracy close to uncompressed baselines while substantially reducing downlink communication with low server-side recompression overhead. --- ### Large language models for partial differential equation workflows Authors: Han Wan, Rui Zhang, Hao Sun Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03600v2 Numerical methods and deep learning have advanced the modelling and simulation of systems governed by partial differential equations (PDEs), while formulating equations, configuring solvers, and translating simulations into design and control decisions continue to demand substantial domain expertise and computational resources. Large language models (LLMs) offer opportunities to automate and coordinate these tasks by combining scientific knowledge, mathematical reasoning, code generation, and tool use. Here we review LLM-assisted PDE research across three stages, including discovery, solving, and optimization. We examine how LLMs interact with physical knowledge, numerical methods, and computational feedback to formulate models, implement solution procedures, and guide design and control. We also review existing benchmarks and evaluation practices for assessing scientific validity, computational performance, and workflow reliability. Finally, we discuss three interconnected challenges and opportunities: developing mathematical and physical reasoning tailored to specific PDE problems; building transferable domain expertise through domain-specific and multimodal post-training; and integrating active experimental design with scientific validation for open-ended problems. These directions outline a path towards a more substantive role for LLMs in developing and testing scientific ideas and computational methods across PDE research. --- ### Large language models for partial differential equation workflows Authors: Han Wan, Rui Zhang, Hao Sun Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03600v1 Partial differential equations (PDEs) become actionable in science and engineering not as isolated formulae, but as executable workflows that connect modelling assumptions, governing equations, numerical solvers, diagnostics, and decisions. Large language models (LLMs) are beginning to support such workflows by linking natural language, symbolic mathematics, code, solver outputs, and feedback. Here we examine recent advances in LLM-assisted PDE research across three stages: the discovery and formulation of governing models, the generation and revision of executable numerical solvers, and the use of simulation feedback to support control, design, and optimization. Across these stages, current systems act primarily as workflow-level interfaces. Despite this progress, the field remains limited by the scarcity of high-quality datasets and benchmarks, especially for knowledge discovery and real-world applications, where expert annotation, executable problem construction, and task-level feedback require substantial domain effort. A further challenge is the persistent gap between simulation-based results and real-world scientific and engineering systems, which limits the direct transfer of numerical simulations, control policies, and optimized designs to practical settings. These challenges make LLM-assisted PDE workflows a critical testbed for developing scientific AI systems that can connect language, computation, physical constraints, and real-world decision-making. --- ### Disentangling Language Modeling and Boundaries Authors: Mykola Haltiuk Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.03599v1 Byte-level language models are usually argued for on the grounds of robustness, multilingual fairness, and character-level skills. We point to a different, structural advantage: because they read and write bytes, any two of them share an output space, so knowledge transfer between them is exact and independent of how either was originally tokenized. We hypothesize that the two distributions a byte-level model produces, one over the next byte, one over where its patch boundaries fall, can be disentangled and changed almost independently. A model could absorb a teacher's capability while keeping its own boundaries, or change how it places those boundaries while keeping its capabilities. We lay out the two experiments that would settle the hypothesis, alongside preliminary measurements of the properties they rest on. We argue that the community should move toward a byte-level interface as a shared standard: if the hypothesis holds, then once byte-level models are the norm, transferring capabilities and reshaping boundaries between them become cheap and routine, free of the per-model tokenizer that blocks them today. --- ### FOUND-AF: Benchmarking ECG Foundation Models for Atrial Fibrillation Detection Authors: Amirhossein Taleshinosrati, Yangyang Wang, Atitaya Phoemsuk, Vahid Abolghasemi, Naser Hossein Motlagh, Sadasivan Puthusserypady, Daniel Teichmann, Abdolrahman Peimankar Published: 2026-08-04 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.03597v1 Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia and is associated with increased risks of stroke, heart failure, and mortality. Recent ECG foundation models offer transferable representations for automated AF detection. However, their relative effectiveness remains unclear because existing studies use different datasets, preprocessing procedures, classifiers, and validation protocols. This study presents FOUND-AF, a unified, leakage-controlled, and deployment-oriented benchmarking framework that evaluates the quality of pretrained ECG representations under identical experimental conditions. Nine publicly available foundation models from five families, including HuBERT-ECG, CLEF, ST-MEM, ECG-JEPA, and ECGFounder, were evaluated across four heterogeneous ECG datasets, namely AFDB, CinC2017, CPSC2021, and LTAFDB. All models were used as frozen feature extractors with standardized preprocessing, model-native resampling, a fixed XGBoost classifier, and recording-level grouped cross-validation. The evaluation included classification metrics, receiver operating characteristic analysis, paired recording-level bootstrap comparisons with Holm correction, embedding-space visualization, and computational efficiency profiling. The ECGFounder model consistently achieved the strongest overall performance across datasets while offering a favorable trade-off between accuracy, model size, inference time, and memory usage. FOUND-AF therefore provides a reproducible framework for selecting ECG foundation models and demonstrates that compact, clinically pretrained encoders can support robust and computationally efficient AF detection across heterogeneous acquisition settings. --- ### DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack Chain Reconstruction Authors: Xuyang Liu, Yibin Han, Zhenwei Zhang, Kai Chang, Zhiwei Xu, Tian Qiu, Weixian Deng, Jiabao Gao, Xiaolin Peng, Hai Wan, Xibin Zhao Published: 2026-08-04 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.03591v1 Large Language Model (LLM) agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to infer ordered attacker actions. However, existing benchmarks mainly evaluate final outputs or aggregate accuracy, providing limited insight into how errors arise and propagate across intermediate reasoning stages. We present DiagChain, a diagnostic benchmark for evidence-grounded attack chain reconstruction that enables stage-wise evaluation of LLM agents. DiagChain includes MAIN-69, a suite of 69 scenarios spanning multiple operating systems, evidence noise levels, and chain lengths. It further introduces Evidence-Centric Retrieval-Augmented Generation (ECRAG), which couples evidence retrieval with an evolving structured representation of the reconstructed chain. Five complementary metrics are introduced to assess distinct stages of the reconstruction process and support systematic failure diagnosis. Based on evaluations using 6 LLMs, DiagChain reveals that even the strongest configuration succeeds on only 39.6% of the 849 reference steps in MAIN-69. Our analysis further shows that smaller models struggle with the more basic task of incorporating retrieved evidence into their outputs, whereas larger models can proceed to later steps, where correctly ordering that evidence becomes the main bottleneck. These results validate the importance of diagnostic evaluation beyond end-to-end accuracy and provide actionable insights for improving evidence-grounded cybersecurity agents. --- ### Design-Time Optimization of Deep Neural Networks for Intermittent Learning on Microcontrollers Authors: Jakob Schubert, Maximilian Kasper, Maximilian Linke, Benedict Herzog, Mark Deutel, Axel Plinge, Dominik Seuss, Christopher Mutschler Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.03589v1 We present a method for designing deep neural networks (DNNs) for intermittent, energy-autonomous, on-device learning on microcontroller units (MCUs). In mobile applications where the energy can run out, e.g., when solar-powered, executing artificial intelligence (AI) faces a technical issue as learning can be interrupted at any time. Our approach combines a hardware-aware energy prediction model with multi-objective optimization (MOO), enabling offline DNN optimization at the design stage without repeated deployment and online testing on the target MCU. Our proposed energy predictor estimates per-layer energy consumption for both DNN inference and training, including the intermittent checkpointing overhead, based on implementation-specific compute and memory features extracted from the DNN model. We validate our approach using autoencoders for anomaly detection on a Cortex-M4 MCU, where our predictor achieves a weighted absolute percentage error of 16.6%, which is sufficient for reliable architecture selection under intermittency constraints. As a result, this work bridges the gap between MOO, automated DNN design, deployment on energy-harvesting systems, and intermittent learning, truly enabling autonomous AI at the edge. --- ### GenOS: Compositional Certificates for Semantic Robustness in AI Code Generation Authors: Corrado Priami Published: 2026-08-04 Categories: cs.PL, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.03588v1 AI coding agents are stochastic workflows: prompts are interpreted, artifacts are sampled, validators produce observations, and orchestrators commit or repair. Small prompt or specification changes can therefore alter program-behavior distributions even when the texts appear synonymous. Existing systems evaluate correctness, but lack a compositional criterion for safely replacing a prompt, contract, generator, or program inside a complete agentic workflow. We introduce GenOS, a probabilistic operational semantics for this replacement problem. Each layer is modeled as a Markov kernel, and each interface carries an observer-relative equivalence. We prove that equivalence-compatible kernels descend to quotient classes and that quotienting commutes with distributional extension and sequential composition. Hence, equivalent prompts induce equal probabilities for all downstream equivalence-closed events, including verified commit. We also establish workflow bisimulation, guarded-commit safety under sound validation, total-variation non-expansiveness, and an additive robustness bound that attributes approximation error to individual pipeline layers. An executable insertion-sort audit instantiates the theory with natural-language paraphrases, a formal contract, six programs, two observers, and exhaustive execution on 121 inputs. Equivalent prompts yield identical code-class and commit distributions; a prompt assigning 5% probability to an in-place contract is distinguished by a mutation observer, while downstream distances remain within the predicted bound. Across 20,000 randomized finite-kernel trials, no exact or approximate law is violated. GenOS is model-parametric: compatibility is a measurable property to test, not an assumption about language-model behavior. --- ### From Social Coding to Agentic Coding: Productivity and Relational Reconfiguration in Open-Source Communities Authors: Mengying Zhou, Yongjie Yin, Yang Chen Published: 2026-08-04 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.03585v1 Open-source software communities are a form of digital public infrastructure that not only produces code, but also generates public knowledge and interpersonal relationships through visible collaboration. Generative coding agents (CAs) are an advanced tool to improve development efficiency while shifting part of activities from public human interaction to private human-agent loops. We study this shift using an LLM-based multi-agent simulation initialized with real GitHub data from 1,084 active developers and their repository relationships. After a warm-up with historical commits, we branch the same community state into parallel No-CA and CA conditions for 4-week simulations. CA introduction increases planned and completed tasks by 34.0% and 39.0%, respectively, and reduces median completion time from 45 to 20 minutes. However, adoption reaches only 26.0%, and the gains concentrate among developers who are already more active and well connected. CAs also restructure task execution pathways. Direct human-human interaction declines from 32.4% to 11.6%, while CA-involved modes increase to 57.3%, including 40.3% completed through CA-assisted self-loops. Public knowledge generated under CA condition also provides less support for later tasks. On a standardized retrieval benchmark, the CA corpus achieves 22.3% knowledge coverage, far below the 81.1% achieved by the real-human corpus, and requires more retrieval steps with a lower success rate. These results reveal a productivity-public knowledge tension: coding agents increase technical production, but more work shifts to agent-mediated or private loops, leaving public records less useful to future contributors. --- ### Policy Fragmentation or Institutional Alignment? Institutional Governance of AI in Universities and Business Schools Authors: Lydia Manikonda, Dominique Outlaw Published: 2026-08-04 Categories: cs.AI, cs.CE, cs.ET arXiv: https://arxiv.org/abs/2608.03584v1 Artificial intelligence (AI) is rapidly transforming high-skilled domains, requiring higher education institutions (HEI) to balance the teaching of foundational principles with the integration of emerging tools to ensure workforce readiness. While HEI are increasingly adopting AI, many continue to grapple with how it should be incorporated into curricula and governed through policy, especially when such policies are set at different levels of an institution. This research analyzes AI policies across HEI from 34 states in the United States to investigate what these policies entail and how policies set across institutions as well as within different levels at an institution differ. Using natural language processing (NLP) to analyze institutional AI policies, we find a clear divergence: university-level policies emphasize data security and risk mitigation whereas school-level policies, when present, focus on pedagogical applications and tool usage. When focusing on business school specific policies, relatively few business schools maintain AI policies distinct from university frameworks, creating misalignment with discipline-specific learning objectives. This gap poses challenges particularly for faculty and students as well as for accreditation purposes. Our insights suggest that guidelines should be aligned with broader institutional policies while addressing discipline-specific learning objectives and evolving workforce demands. --- ### AI-Assisted Peer Review Across Research Communities: From Reviewer AI Policies to LLM Review Quality Authors: Alexander M. Fichtl, Lukas Ellinger, Josefin Kelber, Kryštof Olík, Georg Groh Published: 2026-08-04 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.03581v1 AI-assisted peer review is increasingly discussed and adopted as a tool to support the scientific publishing process, yet there is little systematic understanding of how publication venues regulate its use or of how capable current AI review systems are. We address these questions by first surveying reviewer-facing AI policies across 111 leading AI/NLP conferences and medical journals, revealing substantial regulation differences between the two communities. Second, we evaluate AI-generated peer reviews at ICLR 2026 and Nature Communications using a novel dataset comprising original manuscript submissions and several hundred human- and machine-generated reviews. We compare reviews produced by open-source and proprietary models using complementary evaluation metrics, including LLM-as-a-Judge, score alignment, granularity, and overlap with human reviewers' concerns. Our results show that current LLMs can generate detailed and fluent reviews but exhibit systematic weaknesses, such as overly positive recommendations, generic criticism, and uneven evidence grounding. We demonstrate that aggregate quality scores alone can overestimate review quality and argue for multi-dimensional evaluation of AI-generated peer reviews. --- ### SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models Authors: Yaozhi Wen, Jialong Guo, Zhenliang Ni, Han Shu, Xinghao Chen Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03580v1 While Vision-Language Models (VLMs) have demonstrated remarkable performance in processing and understanding both text and images, their large parameter sizes lead to significant computational overhead, limiting their deployment on resource-constrained devices. While pruning has been effective for compressing Large Language Models (LLMs), directly applying it to VLMs leads to significant performance drops, largely due to redundant visual tokens interfering with importance estimation. To this end, we propose SlimVLM, a structured pruning framework designed to compress VLMs while preserving their task performance. We introduce an adaptive visual token selection strategy for VLMs that leverages average text-to-visual attention scores to assess the importance of visual tokens, removing redundant ones during pruning based on a set threshold, thereby optimizing the importance calculation. Recognizing the varying tolerance to sparsity across different modules, we also propose a Sensitivity-aware dynamic pruning mechanism that determines the appropriate pruning ratio for each module by calculating the linear reconstruction error between the outputs of the pruned and unpruned modules, ensuring overall performance stability. Experimental results show that SlimVLM outperforms existing methods across multiple multimodal benchmarks, achieving state-of-the-art performance. --- ### Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving Authors: Xiang Li, Pengcheng Wang, Huazheng Wang, Saurabh Bagchi Published: 2026-08-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.03579v1 Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters. Though powerful, this introduces a critical system dilemma between serving efficiency and task performance: higher-rank adapters generally achieve better downstream task performance, but their GPU VRAM footprint and Host-to-Device PCIe swapping overhead severely constrain scalability. Conversely, ultra-low-rank adapters ($r \le 2$) minimize both VRAM footprint and PCIe transfer overhead, but suffer from downstream task performance degradation. To solve this problem, we propose Subspace-Aligned LoRA Training (SALT), a serving efficiency-aware hierarchical fine-tuning framework. Our solution operates in three phases. First, a provider jointly trains high-capacity domain centroids on public data within the domain using a novel alignment regularizer that coheres in-domain task subspaces into a unified basis. Next, users fine-tune ultra-low-rank task residual adapters on private data atop those frozen centroids. Finally, during inference, the provider pins the centroid in GPU VRAM and dynamically swaps in each user's task residual on demand. Across LLMs of varying scales, SALT recovers high-rank accuracy using $r \le 2$ residuals, achieving up to 18.5% absolute accuracy gains over state-of-the-art compression baselines and reducing per-adapter memory by up to 16x. When integrated into vLLM, SALT improves serving throughput by up to 51% under PCIe bandwidth pressure and 28% under GPU VRAM constraints for Llama-3.2-3B. --- ### Looking under the Wrong Lamppost: On the Limitations of Automated Translation Quality Estimation Authors: Serge Gladkoff, Angelika Vaasa, Sue Ellen Wright, Ingemar Strandvik, Lifeng Han Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.03577v1 Automation of Translation Quality Estimation (QE) has emerged as a widely discussed approach to managing translation quality at scale, and a growing number of tools and technologies have been released in pursuit of this goal. However, the proliferation of new QE systems has not always been accompanied by robust, transparent, and reproducible research and testing. This gap deserves critical scrutiny. This paper examines some fundamental limitations of the QE technology from both theoretical and empirical perspectives, arguing that current QE systems are structurally ill-equipped to serve as reliable standalone tools in real-world translation workflows. The reviewed evidence suggests that QE suffers from a range of interrelated and largely unresolved limitations. Most fundamentally, the evaluation of the quality of translation at the level of isolated segments is problematic because it tends to miss out on cohesion, coherence, and stylistic and rhetorical text features. In addition, empirical research documents several other limitations and flaws, including failure to generalize, systematic biases, overfitting and distribution collapse, performance gaps, error annotation challenges, and data scarcity. These are structural limitations arising from the complexity of human language and translation as a cognitive and communicative act - limitations that more data and better architectures have so far not overcome. Consequently, segment-level QE scores should not be used as a standalone basis for routing, release, or review bypass in production; we argue future work should focus on automating human evaluation grounded in MQM. --- ### SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Authors: Kejian Zhu, Zhuoran Jin, Shangqing Tu, Hongbang Yuan, Yushi Bai, Kang Liu, Juanzi Li, Jun Zhao Published: 2026-08-04 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.03573v2 Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) exhibit fundamentally different behaviors in enhancing multi-task reasoning for large language models (LLMs). Our preliminary experiments revealed a phenomenon: SFT suffers from severe task conflicts under multi-stage training, whereas RL enables stable coexistence across diverse tasks. Empirically, we trace this to the parameter level, observing that RL induces sparse and approximately orthogonal updates across tasks. We provide a theoretical explanation for this mechanism by analyzing multi-task gradient interference. Our results reveal a distinction: interference in SFT is norm-limited, scaling with the absolute gradient magnitude, whereas interference in RL is variance-limited, bounded by the gradient variance induced by advantage normalization and on-policy optimization. This small variance bound yields near-orthogonal optimization directions across tasks. Leveraging this insight, we propose Parallel-RL, a paradigm that decouples multi-task training, significantly improving efficiency and flexibility. --- ### Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning Authors: Kejian Zhu, Zhuoran Jin, Dongqi Huang, Hongbang Yuan, Yupu Hao, Kang Liu, Jun Zhao Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03571v2 Recent works train agents by constructing large-scale multimodal environment pools. However, we find that simply increasing the number of multimodal environments does not always benefit. We further analyze the limitations in current multimodal environment distributions through a series of experiments. Based on these findings, we study how to build more effective training environment distributions from two dimensions: **diversity** and **difficulty structure**. For diversity, we propose **Ability-aware Environment Selection (AES)** to obtain diverse environment sets. For difficulty structure, we propose **Hierarchical Difficulty Curriculum (HDC)**, which organizes curriculum learning through two difficulty levels: harness weakening and state-scale progression. Experiments show that AES and HDC effectively improve multimodal agent training. --- ### Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities Authors: William Bolton, Philip Torr Published: 2026-08-04 Categories: cs.AI, cs.CY, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.03569v1 Benchmarking the ability of AI scientists to generate novel ideas is notoriously difficult. Existing benchmarks in this field have made progress in evaluating scientific reasoning and research replication, but often rely on synthetic tasks or retrospective targets, which may be confounded by prior exposure. We hypothesize that complex, adversarial, fast-moving real-world domains where expert practitioners independently generate observable outputs can provide a practical solution to fill this gap and evaluate the capabilities needed for AI scientists, including reasoning, novelty, and hypothesis formulation. We instantiate this framework in two structurally different domains, Formula 1 (F1), where models ideate around car design concepts for the 2026 season, and real pre-season innovations provide a ground truth, and Magic: The Gathering (MTG), where models propose decks from a recently updated card pool and are evaluated against 19 Pro Tour (PT) decklists. Across both domains, models produce plausible outputs, but few align with real-world expert solutions. In F1, the best model, GPT-5.2 matched 10 of 40 real innovations with 166 ideas proposed across runs. In MTG, the best deck from Gemini 3 Flash recovered 5 of 7 new-set cards from the third-place PT deck, and across all 108 decks, the cards models selected most often were also the cards most widely adopted by PT decks (Spearman $ρ= 0.74$, $p = 0.0003$). These results suggest that a key capability gap for AI scientists is not idea generation, but filtering, prioritization, and coherent novelty. --- ### Divide-and-Conquer: Towards Generalizable Amortized Bayesian Inference for the Drift Diffusion Model Authors: Yufei Wu, Shanqing Gao, Andreas Voss, Francis Tuerlinckx Published: 2026-08-04 Categories: stat.ML, cs.LG, stat.AP, stat.ME arXiv: https://arxiv.org/abs/2608.03566v1 The drift diffusion model (DDM) is a cornerstone of cognitive decision-making research. Although numerous estimation methods exist, researchers continue to seek inference approaches that are both fast and flexible across diverse study designs. Amortized Bayesian inference (ABI) can provide nearly instantaneous inference for complex stochastic models like the DDM, but neural networks trained for one study design cannot generalize to others. In this paper, we propose a divide-and-conquer framework that address this limitation. The core idea is that the DDM's independence assumption allows the full dataset to be decomposed into pairwise shards, each sharing a common structure that a single neural network can learn. Inference is performed on each shard separately and the resulting posteriors are combined via consensus MCMC to approximate the full posterior. Using simulated datasets, we evaluate the accuracy and uncertainty of this method. Our results show that the proposed divide-and-conquer approach achieves accuracy and uncertainty comparable to MCMC while reducing computational cost by several orders of magnitude. This work not only advances DDM estimation but also demonstrates a general strategy for improving the scalability and generalizability of ABI methods across diverse applications. --- ### Enhancing Tabular Learners with Context-Aware Semantic Embeddings Authors: Günther Schindler, Maximilian Schambach, Johannes Höhne Published: 2026-08-04 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.03565v1 While modern tabular learners excel at capturing statistical patterns, they frequently operate in a semantic vacuum, treating textual features as discrete symbols, ignoring the rich semantics inherent in feature names or cell entries. We propose CASE (Context-Aware Semantic Embeddings), a novel framework that bridges the gap between the semantic understanding of Large Language Models (LLMs) and the statistical capabilities of tabular learners. Unlike existing methods that embed rows in isolation, CASE utilizes a contextualization strategy: we pre-fill the KV cache of a custom-trained Gemma 3-based Tabular Language Model with a representative sample of rows to establish a persistent anchor of the dataset's semantics. This ensures that generated row embeddings are dynamically contextualized, resolving semantic ambiguities and anchoring representations in domain-specific context. Our experiments across several benchmarks (CARTE, TextTab, and TabArena) demonstrate that CASE substantially improves the performance of tabular learners on semantically rich datasets, particularly in low-data regimes. --- ### Robust General Utility for Reinforcement Learning Authors: Zixuan Liu, Fangzheng Wu, Brian Summa, Zizhan Zheng Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.03562v1 Reinforcement learning (RL) with general utility extends classic RL by optimizing an arbitrary utility functional of the policy-induced occupancy measure, thereby enabling a broader range of applications. However, previous work on general utility RL typically assumes the evaluation utility is fixed and correctly specified. In practice, the utility used at deployment can deviate from the training one, creating a robustness gap that prior work does not address. Motivated by this, we propose robust general-utility RL, a minimax learning framework that trains policies against utility misspecification within a prescribed uncertainty set. Our framework strictly generalizes standard general-utility RL while also providing a unified view of many existing RL frameworks, including reward-robust RL and constrained RL, through appropriate choices of the utility uncertainty set. We further develop provably convergent stochastic algorithms for two regimes. For concave utilities, we develop a projected stochastic gradient descent-ascent method and establish stationarity guarantees. For the more challenging nonconcave regime, we propose a stochastic prox-extragradient algorithm that mitigates ill-posed behavior induced by nonconcavity, with convergence guarantees to approximate first-order stationarity. Experiments on LLM safety alignment and exploration maximization tasks further corroborate the convergence behavior consistent with our theory. --- ### Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities Authors: Hui Liu, Chen Jia, Fan Shi, Xu Cheng, Mianzhao Wang, Shengyong Chen Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03559v1 In multimodal crack segmentation for industrial facilities, the key challenge is preventing missing modalities from degrading pixel-level performance while maintaining low computational cost. Existing methods struggle to address semantic degradation caused by missing modalities. We propose Compass, a lightweight network for robust crack segmentation under arbitrary missing modalities. Compass comprises Degradation Simulation Distillation (DSD), Needle Block, and Evidential Topology-Preserving Fusion (ETPF). DSD constructs a degradation simulation stream that mimics more severe missing conditions and performs reciprocal distillation with the original stream, decoupling complete perception from degradation adaptation. Within DSD, Feature-Aware Prototype Transmitter (FAPT) performs modality agnostic prototype-guided feature completion to maintain semantic integrity under incomplete modality conditions. As a lightweight backbone, Needle injects crack-direction cues into WKV modulation and combines connectivity-aware gating with anisotropic context probing for structure-aware modeling. ETPF fuses multimodal features via Dempster-Shafer evidential combination with uncertainty-gated decoding, preserving crack topology while suppressing unreliable features. Experiments on three datasets demonstrate state-of-the-art (SOTA) performance under diverse missing modality scenarios. Even with 90\% depth modality missing on CrackDepth, Compass achieves F1 of 0.8216 and mIoU of 0.8434 with only 2.58M parameters. The code is available at https://github.com/Karl1109/Compass. --- ### Test-Time Augmentation for Tabular-to-Image Classifiers under Distribution Shifts Authors: Malena Loza, Felipe Grijalva, Eva Milara, Luis Bote-Curiel, Francisco J. Lara-Abelenda, David Chushig-Muzo Published: 2026-08-04 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.03557v1 Tabular-to-image methods that convert tabular data into visual representations have emerged as a novel paradigm for leveraging the high performance of deep learning models. Despite their advantages, the robustness of these methods under distribution shifts remains under explored. Test-Time Augmentation (TTA) is an effective approach in image classification to improve model generalization and robustness, where predictions over multiple transformed views of each input are aggregated. This work evaluates the impact of TTA techniques on predictive performance under Out-Of-Distribution (OOD) for representations generated by tabular-to-image methods. Six tabular-to-image encoding methods were considered: TINTO, IGTD, DeepInsight, BIE, DistanceMatrix, Fotomics. Twenty-five TTA techniques were used, organized into six types: Geometric, Photometric, Structural, Frequency/Encoding, Mixup, and Composite. We employed two datasets from the TableShift benchmark (HELOC and Voting) that provide in-distribution and OOD test subsets designed to evaluate the effect of distribution shifts on tabular data. The results indicate that TTA improves OOD performance, with composite and photometric strategies providing the best trade-off between robustness and variance. In contrast, frequency-domain transformations that alter the encoder's feature-to-intensity mapping consistently degrade performance. These findings highlight TTA as a promising approach for improving the robustness and generalization of classifiers trained on image representations derived from tabular data, particularly under distribution shifts. --- ### Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Authors: Denys Pushkin, Albert Q. Jiang, Aryo Lotfi, Colin Sandon, Emmanuel Abbé Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03550v1 Chain-of-Thought (CoT) prompting remains the standard baseline for evaluating models' reasoning abilities. Originally, this technique was introduced to elicit step-by-step reasoning from large language models (LLMs), which would otherwise tend to directly output the final answer. However, many modern LLMs produce CoT-style responses \textit{natively} when presented with reasoning tasks, which made us revisit the effectiveness of standard CoT prompting. We evaluate several modern mid-sized language models on a math problem-solving task and find that models specialized for reasoning achieve better performance in a simple zero-shot setting than when using few-shot CoT examples - significantly surpassing officially reported results at no additional cost (e.g., from $\sim$77\% to $\sim$84\% for Mathstral on GSM8K). For the tested general-purpose model, a zero-shot CoT prompt is also sufficient to outperform a few-shot CoT baseline. We attribute this to a `guidance-distraction' tradeoff: standard CoT prompting also demands style adaptation, formatting compliance, and potentially undesired contextualization, which can distract models from the core reasoning task. Our findings suggest that using standard CoT prompting increasingly acts as a source of distraction as models grow stronger. --- ### Hi-TTRL: Regulating Consensus with Hints for Test-Time Reinforcement Learning Authors: Kunbin Xu, Xingzuo Li, Xuefeng Bai, Kehai Chen Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.03545v2 Test-time reinforcement learning (TTRL) improves the reasoning capabilities of large language models without labeled data by updating the policy with pseudo-labels constructed through majority voting. While effective, the reward signal assigned from majority voting is highly sensitive to consensus strength, defined as the frequency of the most common answer within a rollout group. In TTRL, consensus strength plays a dual role: it reflects both the reliability of the pseudo-label and the distribution of advantages. Low consensus can amplify updates from unreliable pseudo-labels through disproportionately large advantages, whereas high consensus reduces reward contrast and ultimately yields vanishing gradients. In this paper, we introduce Hi-TTRL, a test-time reinforcement learning framework that utilizes hints during sampling to regulate rollout consensus strength. Hi-TTRL first estimates consensus strength from a partial rollout group. When the consensus strength falls outside a target interval, it invokes a Markov chain Monte Carlo (MCMC) hint sampler. The sampler targets the power-transformed prefix distribution and uses finite-step approximate sampling to generate rollout prefixes as hints. By tuning the power exponent, Hi-TTRL generates hints with a sharpened or flattened power target, steering rollout consensus strength toward the target interval. Experiments on multiple datasets and backbones show that Hi-TTRL consistently improves over standard TTRL, with ablations and consensus-steering analyses validating the effectiveness of adaptive hint-guided consensus regulation. --- ### S$^3$-Diff: Structural Semantic Synergy Diffusion Model for High Fidelity Super Resolution of Pathological Images Authors: Jiaming Liang, QiHui Han, Guangye Ou, Jiawen Liu, Haolin Chen, Xi Zhong, Jiazhou Chen, Xiaoqi Sheng, Hongmin Cai Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03540v1 Digital pathology relies on high-resolution whole slide images for accurate diagnosis, yet limitations in imaging devices, storage, and transmission often make lower-resolution pathology images more common in clinical workflows. Current super-resolution techniques often tend to smooth diagnostically relevant morphology, leading to over-smoothed textures and semantic drift that compromise downstream clinical interpretation. To this end, we develop the Structural Semantic Synergy Diffusion Model (S3-Diff), a diffusion framework for high-fidelity super-resolution of pathological images. The core of S3-Diff is Specimen-aware Structural Anchoring (SSA), which combines prognosis-aware tissue support extracted by a fixed SAM with LR-HR gradient discrepancies to generate a specimen-specific structural anchor to preserve pathological morphology. Concurrently, we introduce Structure-guided Semantic Fidelity Tuning (SSFT) to adapt DINOv3 representations using SSA-derived structural supervision. SSFT combines the adapted semantic energy with LR-derived edge and grayscale cues. The resulting control guides denoising to suppress stochastic artifacts and maintain structural consistency. Extensive experimental results demonstrate that S3-Diff consistently outperforms state-of-the-art methods in both reconstruction quality and downstream survival analysis performance. The source code will be made public. --- ### IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion Images Authors: Xiaoyan Feng, Zheng Gao, Tong Guan, Rui Bao, Bokang Zeng, Xiaoyu Li, Jiaojiao Jiang Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03539v2 Most in-generation diffusion watermarks embed patterns independent of the image that carries them, and attackers transplant the marks onto images the generator did not produce, resulting in forgery. Binding the mark to visual semantics prevents such transplantation, yet existing bindings anchor to a proxy image rather than the image they mark. Realizing visual-semantic binding inside generation faces two challenges. The mark derives from the image itself yet enters the sampling trajectory before that image exists, and may itself shift the semantics it binds. The binding also meets opposite sensitivity demands, breaking under semantic change while holding through common processing. We present IRIS, a training-free watermarking scheme that embeds an Intrinsic Ring Identifier from Semantics. IRIS reads a content code from the non-watermarked generated image, derives a one-time ring from the code and a secret key, returns to the final low-noise steps of the same trajectory and blends the ring in, after the semantics it binds are settled. To meet the opposite sensitivity demands, the code is read through a canonicalization shared between embedding and detection, holding through common distortions and mild regeneration while flipping under semantic change. Detection recomputes the ring from the query image and the key alone, and the mark therefore fails on a foreign or spliced image, with acceptance tracking semantic displacement. On three prompt datasets IRIS detects reliably and stays close to its same-seed non-watermarked counterpart, a fidelity prior in-generation marks do not reach. While forgeries transfer fixed-pattern marks and regeneration strips post-hoc marks, IRIS alone among the compared marks withstands both. --- ### IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion Images Authors: Xiaoyan Feng, Zheng Gao, Tong Guan, Rui Bao, Bokang Zeng, Xiaoyu Li, Jiaojiao Jiang Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03539v1 Most in-generation diffusion watermarks embed patterns independent of the image that carries them, and attackers transplant the marks onto images the generator did not produce, resulting in forgery. Binding the mark to visual semantics prevents such transplantation, yet existing bindings anchor to a proxy image rather than the image they mark. Realizing visual-semantic binding inside generation faces two challenges. The mark derives from the image itself yet enters the sampling trajectory before that image exists, and may itself shift the semantics it binds. The binding also meets opposite sensitivity demands, breaking under semantic change while holding through common processing. We present IRIS, a training-free watermarking scheme that embeds an Intrinsic Ring Identifier from Semantics. IRIS reads a content code from the non-watermarked generated image, derives a one-time ring from the code and a secret key, returns to the final low-noise steps of the same trajectory and blends the ring in, after the semantics it binds are settled. To meet the opposite sensitivity demands, the code is read through a canonicalization shared between embedding and detection, holding through common distortions and mild regeneration while flipping under semantic change. Detection recomputes the ring from the query image and the key alone, and the mark therefore fails on a foreign or spliced image, with acceptance tracking semantic displacement. On three prompt datasets IRIS detects reliably and stays close to its same-seed non-watermarked counterpart, a fidelity prior in-generation marks do not reach. While forgeries transfer fixed-pattern marks and regeneration strips post-hoc marks, IRIS alone among the compared marks withstands both. --- ### Cross-Lingual Bias in Large Language Models: A Comparative Analysis of English and Swahili Authors: Ruolei Zhang, Teddy Njuguna, Yue Feng Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.03532v1 Large language models are increasingly deployed in multilingual contexts, yet safety alignment and bias evaluation remain overwhelmingly English-centric. We investigate whether social biases generalise across languages by submitting 4,900 symmetric English--Swahili prompt pairs to GPT-5.2 and Gemini 2.5 Flash across nine demographic bias axes, yielding 19,600 completions evaluated for stereotype prevalence, sentiment, refusal behaviour, and cross-lingual semantic similarity. Our findings show that bias transforms rather than transfers: stereotype rates shifted by up to 12 percentage points on specific axes, Gemini's neutral-sentiment rate doubled in Swahili, and GPT-5.2 refused 169 prompts in English and zero in Swahili, consistent with refusal behaviour anchored to English-language surface forms at the behavioural level. Over 55% of prompt pairs produced semantically dissimilar completions across both models. These reinforce the idea that English-only bias audits do not produce adequate coverage for multilingual deployment. --- ### Behaviorally Adaptive Visual Diversion for Inclusive and Resilient Digital Assessment Delivery Authors: Gupta Lovi Raj, kaur Kamalpreet, Dama Sriram, Parali Prajithaa Published: 2026-08-04 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.03531v1 Institutions increasingly rely on browser lockdown, webcam monitoring, and behavioral analytics to secure high-stakes digital assessments, yet these mechanisms are commonly designed and evaluated independently and often overlook learner accessibility. This paper introduces Behaviorally-Adaptive Visual Diversion (BAVD), a theoretical framework in which a synthetic, non-semantic visual field is composited with assessment content and adaptively modulated according to observed candidate behavior. The underlying assessment content is never altered; only its visual presentation is modified to reduce the usefulness of unauthorized screen capture or screen sharing while remaining minimally intrusive for legitimate candidates. The framework further incorporates an accessibility-aware attenuation mechanism that reduces or suppresses diversion intensity for candidates with approved visual-processing accommodations. We formulate the model using a coupled dynamical-systems representation comprising a Diversion Field Generator, Rendering Tensor, Behavior Tensor, Composite Integrity Functional, and Multi-dimensional Entropy Model, and establish theoretical properties for content fidelity, rendering stability, entropy boundedness, integrity tracking, and closed-loop adaptation stability. The framework explicitly states its threat model, identifies deployment assumptions and limitations, and discusses the trade-off between accessibility and capture resistance. This work provides a mathematically grounded foundation for behaviorally adaptive and accessibility-aware assessment delivery and offers a basis for future empirical validation in trusted digital assessment platforms. --- ### Consensus Measures for Unstructured Biomedical Text Annotations Authors: Pascal Wullschleger, Christian Kreis, Martin A. Walter, Jennifer Foster, Marc Pouly Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.03529v2 Biomedical literature is increasingly mined for knowledge beyond the questions it was written to answer. Because the target concepts are not known in advance, annotators prefer open-ended labels, whose agreement is hard to quantify. We study soft inter-rater reliability for annotators providing unstructured texts for biomedical annotation tasks. Synthetic experiments show that soft reliability can be quantified using a variety of semantic equivalence measures, and that the choice of measure affects failure modes of the estimation. Embeddings are scalable, but limited when differentiating similar but distinct concepts. Large language models are promising, but limited by scalability for estimating agreement by chance. Finally, we suggest measures based on natural language inference as a sensible compromise. --- ### Training Documents Reranker with Search Rubrics for Deep Research Agent Authors: Wenhan Liu, Yu Lu, Qiaolin Xia, Hui Xu, Tong Zhao, Jian Xi, Yutao Zhu, Haijin Liang, Haibo Shi, Hao Wang, Zhicheng Dou Published: 2026-08-04 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.03527v1 Retrieval systems help deep research agents generate high-quality answers by providing relevant documents. However, existing retrievers typically select documents through relevance matching, while individually well-matched top-$k$ documents may not form a \textit{set} that satisfies the complex information needs of an agent query (\eg, diverse, concise and authoritative documents). In this paper, we propose search-oriented rubrics that \textit{explicitly} define the requirements that high-quality document sets should satisfy for each agent query. Our search rubrics are organized into a hierarchical structure and synthesized using a powerful LLM. Based on these search rubrics, we further train a document reranker \textbf{RubricRanker} to select a high-quality subset from retrieved documents. We design a two-stage training framework that consists of rubrics-guided supervised fine-tuning and rubric-based reinforcement learning. Extensive experiments demonstrate that RubricRanker outperforms the strongest baseline by 2.6 points on four deep research benchmarks and generalizes well to five RAG benchmarks. --- ### MinerU.Chem: A High-Precision System for Optical Chemical Structure and Reaction Recognition Authors: Haote Yang, Jiang Wu, Jingchao Wang, Xingjian Wei, Lixin Ma, Linye Li, Chen Zhu, Xiaolong Wu, Yuheng Lu, Ziran Zhu, Junyuan Gao, Lingli Ge et al. Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03525v3 In organic chemistry papers and patents, molecular structures, reaction schemes, and experimental conditions are often presented as molecular structure depictions, reaction diagrams, and complex tables or figures. Such information is difficult for general-purpose document parsing systems to directly convert into machine-readable data. This limits data production for organic chemistry knowledge base construction and for AI for Chemistry tasks such as reaction prediction, retrosynthesis, condition recommendation, molecular property prediction, and drug molecule design. This report introduces MinerU-Chem, a document parsing system for organic chemistry literature integrated into the MinerU online platform. Built on top of MinerU's general document parsing pipeline, MinerU-Chem adds five chemistry-specific modules: chemistry relevance filtering, molecular structure detection, molecule identifier extraction, molecular structure recognition, and reaction scheme parsing. Together, these modules convert organic-chemistry-related image regions in documents into a Molecule Summary List and a Reaction Summary List. For molecular structure recognition, MinerU-Chem uses CARBON (Complex Atomic Representation and Bonding Object Notation) as its core representation. CARBON enables recognition results to preserve both the visual layout of the original image and complex chemical semantics, while supporting the export of standard downstream formats such as MolFile and SMILES. On the SMILES-evaluable subset of MolRecBench-Wild (N=2,392), MinerU-Chem's molecular structure recognition module achieves a SMILES exact-match accuracy of 93.02%, outperforming the best evaluated comparison system, GPT-5.6-Sol (74.87%), by 18.15 percentage points. The system has been integrated into the MinerU online platform and is available at https://mineru.net/OpenSourceTools/Extractor . --- ### MinerU.Chem: A High-Precision System for Optical Chemical Structure and Reaction Recognition Authors: Haote Yang, Jiang Wu, Jingchao Wang, Xingjian Wei, Lixin Ma, Linye Li, Chen Zhu, Xiaolong Wu, Yuheng Lu, Ziran Zhu, Junyuan Gao, Lingli Ge et al. Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03525v2 In organic chemistry papers and patents, molecular structures, reaction schemes, and experimental conditions are often presented as molecular structure depictions, reaction diagrams, and complex tables or figures. Such information is difficult for general-purpose document parsing systems to directly convert into machine-readable data. This limits data production for organic chemistry knowledge base construction and for AI for Chemistry tasks such as reaction prediction, retrosynthesis, condition recommendation, molecular property prediction, and drug molecule design. This report introduces MinerU-Chem, a document parsing system for organic chemistry literature integrated into the MinerU online platform. Built on top of MinerU's general document parsing pipeline, MinerU-Chem adds five chemistry-specific modules: chemistry relevance filtering, molecular structure detection, molecule identifier extraction, molecular structure recognition, and reaction scheme parsing. Together, these modules convert organic-chemistry-related image regions in documents into a Molecule Summary List and a Reaction Summary List. For molecular structure recognition, MinerU-Chem uses CARBON (Complex Atomic Representation and Bonding Object Notation) as its core representation. CARBON enables recognition results to preserve both the visual layout of the original image and complex chemical semantics, while supporting the export of standard downstream formats such as MolFile and SMILES. On the SMILES-evaluable subset of MolRecBench-Wild (N=2,392), MinerU-Chem's molecular structure recognition module achieves a SMILES exact-match accuracy of 93.02%, outperforming the best evaluated comparison system, GPT-5.6-Sol (74.87%), by 18.15 percentage points. The system has been integrated into the MinerU online platform and is available at https://mineru.net/OpenSourceTools/Extractor . --- ### Dr. AGENTONOMICS: A Didactic Experiment of AGENTONOMICS Authors: Fengjunjie Pan, Alois Knoll Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03524v1 AGENTONOMICS is a framework that treats AI agents as economic entities that can be designed, managed, and governed through an integrated management architecture. Dr. AGENTONOMICS is its first application: a lecture agent developed in the context of the TUM course on AI agents in business administration. Conceived during the winter semester 2025/26 and first introduced to students in the summer semester 2026, it serves as a didactic experiment in which the agent is both the object that students study and the medium through which they learn and apply the framework. The current prototype is a web-based, retrieval-grounded tutor that explains AGENTONOMICS concepts and supports student questions. This report argues that the same system can grow beyond tutoring into three additional cumulative roles: an avatar lecturer that delivers multimodal instruction, a design consultant that guides students through the AGENTONOMICS Design & Management Reference Framework (ADMRF), and a meta-agent that helps construct the agents students have specified. These roles are cumulative because they share the same interface, intelligence layer, tools, knowledge base, and ecosystem connection, while an orchestrator selects the role-specific algorithm required for each task. We present the architecture of the prototype, outline its development roadmap, and discuss its implications for a polycentric AI economy. This report is intended to invite further discussion on how agents can teach, apply, and eventually reproduce the frameworks by which they are designed. --- ### Pivot-Centric Trajectory Prediction: Bridging Long Horizons via Dynamical Guidance Authors: Xiucong Zhao, Jindong Tian, Hao Miao Published: 2026-08-04 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.03521v1 Forecasting precise future motion of surrounding agents is essential for reliable autonomous vehicles. However, as the demand for longer prediction horizons increases, existing endpoint-completion or iterative-refine methods increasingly struggle with weak guidance and compounding errors. To tackle the long-horizon prediction challenge, we propose Pivot-Centric Trajectory Prediction (PCTP). By introducing ``pivots'' and focusing on predicting pivot points along extended trajectories, we divide the long-term prediction task into short-term sub-tasks at various scales. Specifically, PCTP decouples the long-term trajectory predicting process into two processes: pivot prediction and pivot-based trajectory refinement. The pivot prediction process aims to utilize global map context and agent-to-agent interactions to identify these ``pivot points'', while the pivot-based trajectory refinement process focuses on local map details and refines the short-term trajectory based on predicted ``pivot points''. Compared with existing methods, PCTP provides more intermediate guidance while reducing compounding errors. Moreover, PCTP is a flexible approach that can be integrated into most state-of-the-art trajectory prediction models. Experimental results show that PCTP improves the prediction accuracy of leading models on both Argoverse I and Argoverse II datasets with minimal impact on model size. Specifically, PCTP combined with QCNet outperforms all published ensemble-free methods on the Argoverse II leaderboard at submission. --- ### AI Forensics Across White-, Grey-, and Black-Box Access: A Process Model and Research Agenda for Post-Incident Investigation of AI Systems Authors: Ali Dehghantanha, Sajad Homayoun Published: 2026-08-04 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.03520v1 AI systems are increasingly involved in decisions and actions that may later require investigation. When an AI related incident occurs, investigators need to reconstruct what the system did, why it behaved that way, and which part of the system or supply chain contributed to the outcome. Existing work on AI forensics remains fragmented, often focusing on a specific system type, artifact, or analysis technique. This paper argues that investigator access is a useful starting point for organizing the field. We distinguish white box, grey box, and black box access and show how each access level changes what can be collected, preserved, analyzed, and reported. Based on this distinction, we propose a process model matrix for AI forensics across four phases: collection, preservation, analysis, and reporting. We also introduce an order of volatility for AI systems, covering runtime state, context windows, logs, retrieval stores, model artifacts, and training lineage. From this matrix, we derive an access conditioned examination framework and identify open research problems, including black box preservation, model version attestation, uncertainty quantification for surrogate based analysis, and chain of custody for mutable AI artifacts. --- ### GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression Authors: Ziyue Zeng, Dingjie Peng, Xun Su, Hiroshi Watanabe Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03517v1 Codebook-driven generative compression uses a pretrained image or video generator as a zero-shot visual prior and transmits compact codebook indices to guide reconstruction at ultra-low bitrate. Current codecs tie each finite-rate correction to a fresh prior evaluation, so shortening the sampler also removes correction slots that carry target-dependent information. We propose GVCCTurbo, a BPP-driven scheduler that separates expensive prior refreshes from codebook corrections: after calibrating an atom-count operating point and skip-gap ratio once per protocol, it maps a target codebook-payload bitrate to a trajectory length and refresh period, making BPP a schedule input instead of a fixed consequence of sampler length. The same endpoint-prediction and finite-rate steering interface covers GVCC-style rectified-flow video and DDCM-style diffusion image compression, preserving zero-training deployment and compatibility with future distilled priors. Native 1080p curves position the complete zero-shot codec in the ultra-low-bitrate regime. In a controlled 720p Wan-GVCC study, the scheduler cuts prior evaluations from 20 to 9 for a $\sim\!44\%$ measured decoding-time reduction shared across the whole schedule family, at a small shared LPIPS cost on high-motion content; within that family, uniform refresh thinning (pure-skip) is a boundary point, and the BPP-aware interior point trades $2.9\%$ fewer codebook-payload bits for consistently higher PSNR at comparable LPIPS. These results support BPP-to-compute scheduling as a controllable extension of sampler-length tuning, without requiring the allocated point to dominate every boundary point. --- ### Detecting Pose Estimation Failures via Keypoint Self-Consistency Authors: Robin Chan Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03516v1 One common approach to pose estimation involves predicting object keypoints in an image, followed by using Perspective-n-Point algorithms to compute the object's rotation and translation relative to the camera. While rotations preserve object shapes, this property is often neglected in keypoint-based pose estimation methods, where keypoints are typically predicted independently from each other. As imprecise keypoint predictions negatively affects pose estimation accuracy, it also limits its reliability in downstream tasks. In this work, we explore whether such inaccurate pose estimates can be identified by simply examining spatial locations between 2D keypoints. We propose a set of hand-crafted geometric features that capture the self-consistency of keypoint predictions, including pairwise distances, reprojection consistency, as well as render and mask consistency. Despite its simplicity, a logistic regression classifier trained on these features reliably detects pose estimation failures, outperforming confidence-based approaches like conformal keypoint predictions that rely solely on keypoint uncertainty. --- ### Reversing Arrows in Large Language Models Authors: Sefika Efeoglu, Adrian Paschke Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03512v1 Large language models (LLMs) have achieved strong performance on text-to-knowledge graph generation and related tasks. Nevertheless, it is still unclear whether they accurately model the direction-dependent semantics of inverse relations, in which reversing the order of the arguments alters the meaning of a relation (e.g., \textit{mother} versus \textit{child}). To the best of our knowledge, this work presents the first systematic study of inverse relation directionality in LLMs, using a benchmark consisting of 5,457 instances spanning 27 distinct inverse relation labels. We evaluate five open-source LLMs under a multiple-choice prompting framework and further examine the influence of relation descriptions and entity representations by substituting the original entities with synthetic and masked entities. Our findings reveal systematic asymmetries in inverse relation classification across LLMs, indicate that relation descriptions do not consistently improve performance, and show that model performance can be sensitive to variations in entity representations. --- ### How Many Labels Are Enough? ALDA: Active Learning Deployment Advisor for Medical Image Classification Authors: Julia Machnio, Mads Nielsen, Mostafa Mehdipour Ghazi Published: 2026-08-04 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.03511v1 Active learning (AL) promises to reduce the cost of medical imaging projects by lowering the number of clinical labels required. However, practical deployment requires committing to a sampling strategy before the full annotation budget is spent, and choosing the wrong strategy can increase rather than decrease costs. We propose Active-Learning Deployment Advisor (ALDA), a deployment-oriented framework for AL method selection under clinical performance constraints. Given a short pilot phase, ALDA fits a parametric learning-curve model to each candidate strategy, estimates whether that strategy is expected to reach a required clinical performance target, and predicts the number of expert annotations needed to do so. In addition to absolute annotation cost, ALDA introduces a deployment window that quantifies the sensitivity of this cost estimate to uncertainty in the clinical threshold. The final recommendation follows a risk-aware rule: among strategies with near-optimal predicted cost, ALDA prefers the strategy with the narrowest deployment window, the most robust to threshold revisions. Experiments on four medical imaging classification domains show that ALDA predicts the deployment-optimal method from a pilot of 15-30% of the intended budget and reduces annotation costs by up to 82% compared with a poor strategy choice. Rather than introducing a new sampling heuristic, ALDA provides a practical decision layer that answers a deployment-critical question: how many labels are enough? --- ### From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology Authors: Basit Alawode, Moshira Ali Abdalla, Dwarikanath Mahapatra, Muzammal Naseer, Sajid Javed Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03508v2 Vision Transformers (ViTs) and their hierarchical variants have achieved strong performance in Computational Pathology (CPath). However, most are pre-trained on single-resolution Whole Slide Images (WSIs), limiting their generalization across arbitrary resolutions. Gigapixel WSIs inherently contain diagnostic patterns at multiple scales, including cellular morphologies, tissue architectures, and global context, mirroring how expert pathologists examine WSIs. We introduce Multi-Resolution Pyramid Transformer (MRPT), a model that hierarchically aggregates multi-resolution information from cellular to tissue and WSI levels. MRPT employs a biologically meaningful Consecutive Cross-Resolution Attention (CCRA) mechanism to capture scale-independent interactions and enforces multi-resolution semantic consistency by aligning embeddings across resolutions, yielding robust and generalizable WSI representations. Pre-trained in a multi-resolution self-supervised manner on 624M patches, 2.4M regions, and 36K WSIs, MRPT learns rich coarse-to-fine histopathology features. Extensive experiments on 34 diverse datasets show that MRPT surpasses recent foundation models and Multimodal Large Language Models (MLLMs) in cancer subtype classification, tissue phenotyping, and Visual Question Answering (VQA) for WSI understanding. --- ### From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology Authors: Basit Alawode, Moshira Ali Abdalla, Dwarikanath Mahapatra, Muhammad Muzammal Naseer, Sajid Javed Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03508v1 Vision Transformers (ViTs) and their hierarchical variants have achieved strong performance in Computational Pathology (CPath). However, most are pre-trained on single-resolution Whole Slide Images (WSIs), limiting their generalization across arbitrary resolutions. Gigapixel WSIs inherently contain diagnostic patterns at multiple scales, including cellular morphologies, tissue architectures, and global context, mirroring how expert pathologists examine WSIs. We introduce Multi-Resolution Pyramid Transformer (MRPT), a model that hierarchically aggregates multi-resolution information from cellular to tissue and WSI levels. MRPT employs a biologically meaningful Consecutive Cross-Resolution Attention (CCRA) mechanism to capture scale-independent interactions and enforces multi-resolution semantic consistency by aligning embeddings across resolutions, yielding robust and generalizable WSI representations. Pre-trained in a multi-resolution self-supervised manner on 624M patches, 2.4M regions, and 36K WSIs, MRPT learns rich coarse-to-fine histopathology features. Extensive experiments on 34 diverse datasets show that MRPT surpasses recent foundation models and Multimodal Large Language Models (MLLMs) in cancer subtype classification, tissue phenotyping, and Visual Question Answering (VQA) for WSI understanding. --- ### ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels Authors: Gagan Bhatia, Julian Schlenker, Simone Paolo Ponzetto, Steffen Eger Published: 2026-08-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.03507v1 Historical language change affects morphology, syntax, semantics, and pragmatics, yet computational studies typically examine these levels with incompatible representations and therefore cannot determine whether they evolve together across languages. We address this problem by asking how the magnitude and direction of change vary across linguistic levels, languages, and historical periods within a single analytical space. We introduce ChronoLens, a framework that combines frozen multilingual language models, feature-aligned crosscoders, and post-hoc linguistic interventions, and apply it to 44.98 million documents and approximately 17.2 billion tokens from five parliamentary traditions spanning 1803--2026. The resulting sparse representations agree substantially more strongly with linguistic statistics than dense embeddings or a pooled sparse autoencoder ($ρ=0.72$ versus $0.29$ and $0.28$), and reveal that morphology, syntax, semantics, and pragmatics generally change by comparable amounts within a language, while languages differ markedly in when, how far, and in which direction they change. These findings show that historical language change is a structured, multidimensional process: similar magnitudes can conceal different trajectories, and meaningful cross-linguistic comparison requires measuring both distance and direction. --- ### When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Authors: Omatharv Bharat Vaidya, Connor Thomas Jerzak, Zayne Rea Sprague, Fangcong Yin, Nhat Ho Published: 2026-08-04 Categories: cs.AI, stat.ML arXiv: https://arxiv.org/abs/2608.03506v1 Self-consistency assumes the most frequent answer among sampled reasoning traces is the most reliable, but this can fail in causal reasoning: samples often repeat the same confounding error, and votes fragment across multiple valid answers, letting an invalid answer win despite a valid minority trace. We introduce CALVER (Causal Axiom-Level VERification), a training-free symbolic verifier that scores structured traces against Pearl's causal criteria, including -separation, backdoor adjustment, and intervention, and selects the highest-scoring candidate without consulting a reference answer. On CLEAR find-one-valid queries that admit multiple graph-valid answers, CALVER reaches 42.1% where plurality, a reward model, an LLM judge, and model confidence remain near 30% on identical frozen pools. Scaling the judge to 72B does not close the gap. In an audited clean-core subset, 11 of 21 graph-valid CALVER selections differ from the benchmark's listed answer while still satisfying the requested predicate. The advantage widens with the sampling budget and reproduces across ten published Bayesian networks, a second model family, and settings where the model must build the graph from text. CALVER also improves thresholded average-treatment-effect decisions against exact ground truth, generalizes to logic under a truth-table checker, and scores each candidate in milliseconds on CPU. CALVER needs only a causal structure, supplied outright or built from the text; wherever that holds, selection can aggregate via causal validity. ---