# Research Papers — 2026-08 · bundle page 187 of 240 > Full-text markdown of papers #9301–9350 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/187 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/186.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/188.md) ### Measuring the Cross-Lingual Comprehension Gap: How the language of the evidence shapes what language models understand Authors: Rafael da Silva, Jeff Eicher Published: 2026-08-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.06506v1 Language models are often evaluated as though capabilities demonstrated in English remain equally available when the same content is presented in other languages. Traditional multilingual benchmarks rarely isolate language while holding content, question, reference answer, model, and evaluation unit constant. We define the Cross-Lingual Comprehension Gap (CLCG) as the reduction in response quality when the same content and question are presented in a target language rather than in English. Using ParallelQA-18, a professionally human-translated parallel corpus, we evaluate five models from five laboratories on a stratified sample of 150 articles across 18 languages (English reference; Portuguese high-resource baseline; 16 targets spanning Joshi et al. 2020 classes 0-4). A within-item design varies only passage language. The primary estimator contrasts English versus pooled target-language Token-F1 micro-means on higher-complexity open-ended questions, with article-cluster bootstrap intervals. The primary pooled CLCG is 0.078 (95% CI 0.072-0.084), about a 17% reduction relative to the English score; the equal-language macro summary is 0.077. Net of Portuguese, the macro gap is 0.016 (95% CI 0.013-0.020). Language-level CLCG is negatively associated with Joshi resource class (rho = -0.594, p = 0.015, n = 16). In blinded paired human evaluations, higher-resource responses are preferred in 61.6% of decisive judgments (estimated preference probability 0.655, 95% CI 0.558-0.741). Capabilities shown in English should not be assumed to transfer equally to other languages; English-centered evaluations may overestimate quality for users of low-resource languages. --- ### Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Authors: Guanghui Min, Liang Wu, Mayank Darbari, Chen Chen, Liangjie Hong Published: 2026-08-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.06503v1 Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood. In this preliminary empirical study, we show that compression can weaken the influence of recent interactions, increasing blocked actions, repeated exploration, and instability across runs. Motivated by these observations, we introduce TRACE, a verifier-guided framework that evaluates individual compaction events through paired closed-loop continuations from the same environment state and uses summary preferences to optimize a natural-language compression prompt while keeping all models frozen. Initial results on AppWorld show improvements over existing compression baselines in task performance, multi-run reliability, and context--execution efficiency. These findings provide early evidence for boundary-local evaluation as a promising direction for reliable agent context compression. --- ### Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding Authors: Ming Wang, Yuqing Zhang, Tingna Xie, Xiangju Li, Xiaocui Yang, Daling Wang, Shi Feng, Yifei Zhang Published: 2026-08-06 Categories: cs.AI, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2608.06501v1 Creative capabilities of MLLMs matter in design, communication, education, and human--AI collaboration, yet remain difficult to evaluate because explicit targets and reward signals are scarce compared with accuracy-oriented tasks. Cross-concept understanding is a core cognitive capacity underlying receptive creativity. It enables a perceiver to recover intended meaning from non-obvious but meaningful conceptual relations. We operationalize item construction as cross-concept encoding and model inference as cross-concept decoding. We introduce C4, a cognition-inspired evaluation framework for Chengyu (Chinese idiom)-based Cross-Concept Creativity. Its encoding component maps target slots to imageable substitute concepts along bridge paths in a manually annotated and third-party-reviewed cross-concept network, enabling batch generation with explicit structure, difficulty indexed by bridge count and depth, and exact answers. Using this framework, we instantiate the C4 Evaluation Set (C4-Eval), comprising 184 synthetic items and 37 human-created cross-concept chengyu figures collected from online sources. We manually construct and review cross-concept relations, bridge paths, and reasoning processes for the collected figures. Each C4-Eval item is instantiated in five task settings, yielding 884 primary answer-recovery cases. Across ten evaluated MLLMs, the strongest closed models reach 50.7% and 48.0% primary accuracy, while open-source models remain substantially lower. Candidate constraints improve accuracy sharply, but bridge hints and explanation requests provide only modest gains. These results expose a substantial gap in how current MLLMs decode creatively encoded meaning through cross-concept relations. The code is in the supplementary material. --- ### ConstructCIE: A Dataset for Extracting Causal Information from Construction Accident Narratives Authors: Hung Nguyen, Jaehoon Lee, Namgyun Kim, Kuan-Hao Huang Published: 2026-08-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.06495v4 Construction accident narratives contain rich causal information, but the evidence is often implicit, long-span, and distributed. We introduce ConstructCIE, a manually annotated dataset for Causal Information Extraction from OSHA construction accident reports. The dataset uses a hierarchical schema for accident types, causal factors, sub-causal factors, and supporting evidence spans. We evaluate supervised sequence taggers and instruction-tuned LLMs in an end-to-end hierarchical extraction setting. Results show that most evaluated models achieve strong accident-type prediction and recover broad causal meaning but remain limited in precise span-level extraction. Joint Hierarchical Extraction generally achieves stronger exact and soft matching, while Individual Hierarchical Extraction sometimes achieves higher keyword F1. Error distributions vary by extraction strategy, but evidence-selection and span-boundary errors remain common. These findings show that reliable Causal Information Extraction for construction accidents requires stronger domain grounding and more accurate evidence extraction. The code and data can be found at https://github.com/lab-flair/ConstructCIE . --- ### InsertFuse: A Unified Framework for Multi-Category Reference-Guided Image Insertion Authors: Guangzhao Li, Qingyan Wei, Huayu Zheng, Yige Zheng, Chaoyang Zhang, Jie Yang, Yunan Ding, Yan Tai, Siqi Luo, Xiaohong Liu Published: 2026-08-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06490v1 We present InsertFuse, a unified framework for multi-category reference-guided image insertion. Its key idea is to decouple category-specific expertise learning from cross-category capability consolidation. InsertFuse first trains specialized experts for different insertion categories and then introduces Insertion On-Policy Distillation (IOPD) to consolidate their capabilities into a single student. By querying the matched expert at states visited by the student, IOPD preserves category-specific insertion behavior while mitigating the cross-category interference caused by direct joint training. To improve spatial control, we propose Token-Aligned Geometry Conditioning (TAGC), which maps mask-derived geometric cues to the visual token grid, and Region-Balanced Flow Matching, which separately normalizes prediction errors inside and outside the insertion region to prevent background-dominated and scale-dependent supervision. We further introduce Reference CFG to isolate and strengthen the guidance induced by the visual reference under fixed scene and geometry conditions, with IOPD transferring this enhanced supervision into the unified student. Extensive experiments on the public AnyInsertion benchmark and our multi-category test set demonstrate state-of-the-art performance on most metrics, showing strong reference fidelity and generation quality across diverse insertion categories. --- ### Beyond Attention: Signed Integrated Gradients Attribution in a BiomeGPT-Style Microbiome Transformer Authors: Oren Nelson Published: 2026-08-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.06486v1 In a feature-tokenized transformer (arXiv:2106.11959) such as BiomeGPT (doi:10.64898/2026.01.05.697599), each input token is built by fusing a fixed identity with a sample-specific measurement: a fixed species and a variable abundance, T = S + A. To interpret downstream classification in such models, prior work inspects the attention weights of the special (CLS) token (arXiv:2106.11959, arXiv:1810.04805, BiomeGPT) to rank sample tokens by importance. These weights have two critical limitations: they are nonnegative, so they cannot separate disease-supporting from health-supporting evidence (arXiv:2201.12114), and they act after token fusion, obscuring how the input sources S and A each affect the output. To address this we use Integrated Gradients (arXiv:1703.01365), a signed, fusion-aware attribution method, and propose a source-derived baseline T' = S + A_0 for feature-tokenized models such as BiomeGPT, which preserves species identity as a fixed biological coordinate while isolating the effect of abundance variation. Applied to a disease-versus-health decision margin, it yields polarity that explicitly separates pathogenic from protective microbial signals. We show that this gradient-based approach uncovers species-abundance directional relationships and sensitivity diagnostics entirely obscured by unsigned (CLS) attention weights. We further recommend second-order Integrated Hessians (arXiv:2002.04138) to expose microbiome community interaction rules: how a perturbation in one member alters the model's sensitivity to another, and which other species drive ambiguous cases toward disease or health at a given abundance level. This provides a principled approach to explainability in BiomeGPT that generalizes to other smooth and differentiable feature-tokenized transformers. Code is available at https://github.com/nohren/token-source-attribution --- ### Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events Authors: Ming Wang, Peidong Wang, Xiaocui Yang, Daling Wang, Shi Feng, Fiona Fui-Hoon Nah, Ee-Peng Lim Published: 2026-08-06 Categories: cs.CL, cs.AI, cs.SI arXiv: https://arxiv.org/abs/2608.06485v1 Personality-conditioned LLM agents (PC-Agents) are increasingly used in emotional support, social simulation, and role-playing, motivating the development of lifelong agents that remain coherent over extended interactions. A key component of such coherence is personality evolution: agents should undergo plausible, psychology-grounded changes as they experience life events in different contexts. Although prior work shows that LLM personalities can shift under contextual perturbations, how these shifts vary across traits, events, personas, and models remains poorly understood. We study event-induced personality change after 11 major life events, using the Big Five traits as a psychometric anchor and interpreting the resulting trajectories against longitudinal evidence from human personality psychology. Across four diagnostic axes, PC-Agents exhibit measurable trait shifts at similar rates for event-trait pairs with and without documented human change directions. Even when shifts follow the expected direction, their magnitudes usually fall below human effect-size ranges. Gender and cultural-region prompts show little moderating effect, while persona-level dispersion is compressed three- to four-fold relative to human samples. To enable systematic comparison, we introduce BFI-Adapt, a reusable benchmark for scoring the directional fidelity of event-induced personality change, and use it to rank 14 models. A validation suite shows that the measured shifts exceed no-event retest noise, remain stable under independently paraphrased prompts, exhibit limited and model-dependent convergence with scenario-based behavioral choices, and persist across intervening unrelated dialogue. Together, these checks establish the measured trajectories as robust event-conditioned response patterns. Our results suggest that current PC-Agents simulate the mean of human personality dynamics, but not its shape. --- ### LyEvO: Lyapunov-Guided Evolutionary Optimization for Safe and Robust Sim-to-Real Policy Learning Authors: Riccardo Curcio, Hongpeng Cao, Marco Caccamo Published: 2026-08-06 Categories: cs.RO, cs.AI, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2608.06481v1 Training controllers that are safe and robust in simulation, and systematically assessing their readiness for real-world deployment, remain key challenges in sim-to-real transfer. To address this, we propose LyEvO, a physics-grounded framework that combines constrained Evolutionary Optimization and Statistical Model Checking (SMC)-based verification with Lyapunov-based stability analysis. Leveraging prior knowledge of the system dynamics, LyEvO uses Lyapunov analysis to compute an initial candidate stability region. An iterative loop then uses operational scenarios drawn from this region to jointly optimize and statistically verify a policy, and subsequently expands the region's boundaries based on the verification outcome. This integrated procedure provides a practical criterion for assessing deployment readiness. We evaluate LyEvO on Cartpole and 3D Quadrotor benchmarks through extensive simulations and targeted real-world experiments, demonstrating safe and robust sim-to-real transfer. --- ### StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt Injection Authors: Zhuoxin Zhan, Akbar Rafiey, Avery Ma, Leila Pishdad, Layla El Asri Published: 2026-08-06 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.06477v1 Computer-use agents (CUAs) face a growing threat from indirect prompt injection, where adversarial instructions are planted in the environment such as web pages. In this paper, we introduce multi-step indirect prompt injection, a new attack class against CUAs in which the adversarial goal is decomposed into multiple innocuous-looking sub-steps and distributed across a chain of pages referenced along the agent's navigation path. We develop a pipeline to automatically decompose an adversarial goal under the constraint that the execution of the decomposed sub-steps must achieve the original goal while optimizing the innocuousness of each decomposed sub-step. With this pipeline, we build StepJack, a CUA safety benchmark with 480 test examples. On this benchmark, we evaluate six state-of-the-art CUAs and find that at a fixed decomposition depth, multi-step attacks raise attack success rate (ASR) on three of six CUAs, by up to 31.2 points (e.g., GPT-5.4-mini: 41.7% at single-step to 72.9% at three-step); averaged over the five CUAs that can reliably follow the reference chain (all but EvoCUA-32B), ASR rises from 31.3% at single-step to 36.9% at three-step. Dataset and code are available at https://github.com/BorealisAI/StepJack. --- ### WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader Authors: Boshui Chen, Huiping Liu, Shaolei Zhang Published: 2026-08-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.06474v1 Large language models increasingly generate complete websites from natural-language descriptions, and reinforcement learning has become a central approach to closing their remaining functional gap. This training regime is bottlenecked by reward design. Hand-authored browser scripts are executable yet costly to write for open-ended requirements, while VLM and GUI-agent graders scale but may issue verdicts before observing the decisive state. We propose WebGrader, a self-evolving programmatic grader that autonomously derives the required interaction flows from each website request, represents each flow as an executable Flow Contract, and uses its execution outcome as an RL reward. WebGrader materializes the generated project in a live browser, grounds target actions against the source code and live DOM, and collects visual, DOM, response, and persistent-state evidence along the same browser trajectory. A residual-driven offline loop then discovers reusable verifier skills, screens them on disjoint validation pages, and freezes the promoted skill graph before policy training. By separating test planning, action grounding, evidence collection, and semantic judgment, WebGrader issues a Pass verdict only after observing the requested transition. On WebGen-Bench, WebGrader trains an 8B policy to a 52.01% functional success rate, outperforming a matched appearance-plus-script reward by 7.88 points and surpassing o4-mini and DeepSeek-v4-flash. On WG-core-250, the policy reaches a Full Score of 44.953 and surpasses Qwen3-Coder-480B. --- ### CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training Authors: Amine Lbath, Manan Suri, Aurelien Delaitre, Vadim Okun, Massih-Reza Amini, Ram D. Sriram, Dinesh Manocha Published: 2026-08-06 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.06471v1 Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world software. Generally available agents can already aid attackers, who only need to find one exploitable weakness, while defenders must continuously identify and patch all vulnerabilities across fast-growing codebases. Stronger defensive agents would help close this gap, yet the scarcity of security training data with reproducible build and execution environments remains a bottleneck. We present CyberForge, a framework that synthesizes executable, repository-level security training data by injecting vulnerabilities into real C/C++ projects. It validates each instance dynamically: the injected build must pass the project's unit tests, and generated proof-of-vulnerability (PoV) must trigger on the injected build and not on the clean one. CyberForge is not limited by the availability of disclosed vulnerabilities, therefore it can scale in comparison to data augmentation techniques which rely on historic CVE data. The resulting corpus holds 1034 validated vulnerabilities across 80 projects and 63 weakness categories, with edit locality similar to real CVE patches under a real-versus-real noise floor. Fine-tuning on trajectories collected over this corpus improves SEC-bench patch repair by +3.3 to +14.7 points, in all six configurations of three model scales and two teachers, with the 31B student reaching its GPT-5.4-mini teacher, 72.7% against 74.0%. These gains generalize out of distribution to PatchEval, a corpus containing other programming languages, where every configuration also improves and the 31B student passes its teacher. --- ### Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning Authors: Devharsh Trivedi, Nesrine Kaaniche, Nikos Triandopoulos, Maryline Laurent, Jackson Walters Published: 2026-08-06 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.06469v1 Collaborative machine learning among financial institutions must be both group-fair and robust against deliberate adversarial manipulation. Existing fairness-aware aggregation methods remain formally vulnerable to fairness poisoning: a malicious client maximizing group disparity while preserving accuracy evades accuracy-based Byzantine defenses, and in our threat model FairFed's gap-based weighting can be gamed by an adversary who observes the global fairness score. We present Fairis, a server-side reweighting scheme in which each client's update receives the normalized weight $ω_k = \bar{w}_k / \sum_j \bar{w}_j$ built from the unnormalized score $\bar{w}_k = η- \mathcal{F}_k$, with $\mathcal{F}_k \in (0,1)$ the local Equal Opportunity Difference and $η> 1$ a security parameter. We prove three properties, Monotone Weight Reduction (MWR), Demographic Participation, and Non-Gamesmanship, extend MWR to colluding minority coalitions, and show that combining MWR with server-side norm clipping bounds the adversary's displacement of the global model by $ω_0 C$, strictly decreasing in its own reported disparity. Assuming honest score reporting, an assumption this paper does not discharge, Fairis is the only rule evaluated that guarantees every client strictly positive weight while provably reducing an adversary's weight monotonically in its bias; clipped FairFed can reach a lower weight but guarantees nothing and zeroes a client outright on Taiwan Credit. Against an adversary stealthy enough to evade accuracy-based defenses, within 0.04 accuracy of benign, Fairis cuts its weight by 41 to 54% below a size-blind control on Taiwan. On routine non-IID partitions no rule dominates, and a uniform-weighting ablation shows that containment tracks how far the adversary's score separates from the honest mean, providing none when the honest population is already unfair. --- ### Test-Time Adaptation with Online Personalized Energy-Based Cache for Fine-Grained Video Expression Recognition Authors: Masoumeh Sharafi, Muhammad Osama Zeeshan, Soufiane Belharbi, Alessandro Lameiras Koerich, Marco Pedersoli, Eric Granger Published: 2026-08-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06467v1 Facial expression recognition (FER) in videos is challenging because models must identify subtle, temporally evolving affective states that vary across individuals. Although vision-language models provide transferable visual-semantic representations, models trained on subject-independent data often degrade under subject-specific distribution shifts at inference time. Existing test-time adaptation (TTA) methods commonly update model parameters during inference, increasing computational cost and latency. Cache-based methods avoid parameter updates, but they usually require enough target samples to form reliable class prototypes, which is difficult early in adaptation and for rarely observed classes. We introduce Energy-Based Cache Personalization (EB-CaP), a subject-based online TTA method for video FER that generates class-specific prototypes personalized to each target video. EB-CaP uses a lightweight energy-based model to sample prototypes from the current unlabeled video and populate a personalized cache online, without accumulating large amounts of target data or storing diverse source prototypes. Its energy function relies only on pretrained CLIP: similarities between the target video embedding and class text embeddings guide prototype sampling. In parallel, positive and negative caches store reliable and uncertain target embeddings. An adaptive entropy gate controls cache updates according to the evolving confidence distribution, while a diversity gate limits redundant samples. Final predictions combine cache-derived scores with the current CLIP scores. Experiments on BioVid, StressID, and BAH show that EB-CaP outperforms state-of-the-art TTA methods while maintaining low computational and memory overhead. Code is available at https://github.com/MasoumehSharafi/EB-CaP. --- ### ED-CSP: Crystal Structure Prediction from Electron Diffraction Authors: Germain Poloudenny, Arnaud Demortière, Yaël Frégier Published: 2026-08-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.06448v3 Recovering a periodic 3D crystal structure from sparse, unindexed electron diffraction (ED) observations is a challenging generative inverse problem. Existing ED-based learning methods mainly predict crystallographic labels, reconstruct structures from indexed reflections, or retrieve candidates from finite structure libraries. Here, we introduce ED-CSP, a machine learning framework that predicts crystal structures from chemical composition, atom count, and multiple detector-plane ED spot sets. ED-CSP combines a relational set encoder, permutation-invariant multi-view aggregation, and a periodic flow generator to jointly predict lattice parameters and fractional atomic coordinates. To train the model, we construct ED-CS, a dataset of 4.85 million simulated multi-view ED crystal structures, deduplicated across seven materials repositories and filtered to exclude CHILI-100K overlaps. On 2,075 held-out CHILI-100K materials, ED-CSP trained only on CHILI achieves a structural match rate of 57.49% MR@5, outperforming PXRDGen (52.92%), a state-of-the-art crystal structure prediction model conditioned on powder X-ray diffraction. Scaling training data further improves performance: initializing from a one-million-structure precursor raises MR@5 to 66.27%. On 1,024 compositions absent from the training retrieval library, the model still achieves 53.52% MR@5, demonstrating true generative capability beyond exact-formula retrieval. Replacing target ED observations with diffraction from non-isomorphic structures of identical composition decreases MR@5 by 22.09 percentage points, confirming that predictions depend on the input diffraction patterns rather than composition alone. ED-CSP and ED-CS establish a benchmark for generative crystal structure prediction from sparse ED observations and provide a foundation for future transfer to experimental data. --- ### FedTransKD-IDS: Robust Federated Transfer Learning with Knowledge Distillation for Intrusion Detection in IoT Authors: Mohammad Hosssein Gholamrezazadeh, Ahmadreza MontazerolghaemAhmadreza Montazerolghaem Published: 2026-08-06 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2608.06447v1 In modern distributed network environments, particularly in Internet of Things infrastructures and 5G networks, stringent privacy preservation and scalability requirements have created significant challenges for intrusion detection systems. Although federated learning preserves privacy by preventing data centralization, its efficiency and stability is considerably degraded under severe statistical heterogeneity and resource constraints of edge nodes. To address these limitations, this study introduces the FedTransKD-IDS framework, which enhances both system stability and efficiency by integrating robust aggregation based on the geometric mean, federated transfer learning, and knowledge distillation. Within this framework, the collaboratively trained global teacher model transfers its feature extraction component to lightweight student models. Experimental evaluation on heterogeneous datasets demonstrates a peak detection performance, achieving an accuracy of 99. 18% and a recall of 99. 99%, thereby indicating the effectiveness of structured knowledge transfer in federated environments. --- ### Game-Theoretic Inverse Reinforcement Learning for Modeling Competitive Human Driving: A Cut-in Prediction Study Authors: Yu Song Published: 2026-08-06 Categories: physics.soc-ph, cs.LG arXiv: https://arxiv.org/abs/2608.06445v1 Capturing the strategic decision-making inherent in competitive human driving is critical for autonomous vehicle safety and traffic simulation. This study demonstrates that game-theoretic Inverse Reinforcement Learning (IRL) provides a robust framework for this challenge. We present a comprehensive analysis comparing data-driven IRL models against an established physics-based game-theoretic approach for predicting aggressive, safety-critical cut-in lane changes. Using the high-fidelity highD dataset, we systematically develop and evaluate a series of IRL models with increasing feature complexity. Our results reveal significant advantages: the best-performing IRL models achieve an overall prediction accuracy exceeding 75 percent while maintaining a Cut-In precision up to 51 percent and recall up to 49 percent. This represents a significant improvement over the established physics-based benchmark, which achieved only 4.4 percent precision in these high-stakes scenarios. The analysis reveals a clear trade-off: incorporating granular, instantaneous features yields higher precision, while adding temporal consistency features maximizes recall. These findings suggest that IRL-based models can effectively bridge the gap between microscopic driver intent and macroscopic safety outcomes, providing a more reliable foundation for modeling interactions in mixed-autonomy environments. --- ### SNI-GNN: SmartNIC-Assisted Full-Graph GNN Training with In-Network Embedding Prediction Authors: Guofan Yu, Sitian Chen, Zhenheng Tang, Xiaowen Chu, Amelie Chi Zhou Published: 2026-08-06 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2608.06441v1 Full-graph GNN training delivers high accuracy but scales poorly on multi-server clusters due to heavy, irregular inter-node embedding exchanges. We present SNI-GNN, a SmartNIC-assisted full-graph training system that reduces communication while preserving accuracy by predicting remote embeddings in-network. SNI-GNN deploys a lightweight linear-trend predictor on SmartNICs to refine cached historical embeddings, coupled with an importance-based boundary-node sampling policy and an asynchronous DPU--GPU data pipeline with intermediate-result reuse. We provide error and convergence bounds showing that predictor bias remains controlled under bounded second-order dynamics and yields standard non-convex convergence with inexact gradients. Implemented on NVIDIA BlueField-3, SNI-GNN integrates with state-of-the-art full-graph systems, cuts communication by 21--45\%, achieves 1.3--3.6$\times$ end-to-end speedups over BNS-GCN and up to 1.29$\times$ over baseline SANCUS, with accuracy loss $\leq 0.01$, and scales efficiently to 16 GPUs on graphs with up to tens of millions of edges. These results indicate SmartNIC-based in-network prediction is a practical complement to partitioning and compression techniques for communication-efficient full-graph GNN training at scale. --- ### Fast and Accurate: An Adaptive VLA Inference Framework through Environment-aware Model Selection Authors: Yuewei Sun, Lang Qin, Zechuan Tian, Jingwen Li, Guiqin Wang, Shengzeng Huo, Wenxin Ren, Tao Fang, Xiaochen Zhang, Guanqing Deng, Xiang Wang, Xiaowen Dong et al. Published: 2026-08-06 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2608.06434v1 Embodied intelligence demands both long-horizon reasoning and real-time closed-loop responsiveness. Recent dual-system Vision-Language-Action (VLA) architectures combine fast reactive control with slow deliberative reasoning to balance inference speed and task success rate. However, existing dual-process VLAs tightly couple the fast module to intermediate representations of the slow module, necessitating end-to-end joint training and limiting modularity, extensibility and flexible system switching. In this paper, we propose Environment-aware Model Selection (EMS), an adaptive VLA inference framework that switches between two fully decoupled systems of different scales through environment-aware model selection. The large-scale deliberative system provides globally consistent trajectory planning to ensure task success, while a lightweight reactive system enables high-frequency closed-loop control. A reinforcement-learning-based switching policy dynamically selects which system to invoke based on real-time feedback, enabling sparse use of the slow system and thereby balancing pretrained knowledge utilisation with runtime efficiency. Our design offers three key advantages over prior hierarchical VLA frameworks: (1) a fully decoupled and modular dual-system architecture that supports plug-and-play model replacement; (2) an adaptive, environment-aware switching strategy; (3) high-frequency inference for responsive closed-loop control. We extensively evaluate EMS in both simulation and real-world environments. On the LIBERO benchmark, EMS achieves success rates comparable to the large-scale baseline while increasing the effective action frequency to 93.4 Hz. The framework further demonstrates strong extensibility in real-world dual-arm manipulation tasks, where it accelerates task completion while maintaining robust performance. --- ### Learning When to Trust via Selective Context Preference Optimization Authors: Xian Sun, Wei Chow, Yingshuo Wang, Junhao Liu, Wei Gao, Qing Wu, Lingdong Kong Published: 2026-08-06 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.06377v1 Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, training models to resist such signals, hides a failure mode: a model that ignores all context looks robust yet is useless when the context is worth trusting. We recast the problem as selective trust and introduce MIST, a human-annotated benchmark that renders each reasoning item under four matched conditions (clean, misleading, correct-context, and irrelevant-context), together with SC2W, a paired metric counting how often a misleading signal flips a clean-correct answer to wrong. Across a comprehensive benchmark study, we observe that such a susceptibility is universal. We then propose SCOPE, which mines clean-correct/misleading-wrong failures and optimizes a standard Direct Preference Optimization (DPO) objective over matched preference pairs balanced equally across all four conditions, rather than over misleading items alone. Our approach substantially reduces SC2W on popular open-sourced models while preserving accuracy when the added context is clean, correct, or irrelevant. With this work, we argue that models should be judged on selective trust, not on resistance alone. --- ### The Bitter Lesson of Tool Calling Authors: Ishan Patel, Sahil Sen, Elias Lumer, Vamse Kumar Subbiah Published: 2026-08-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.06370v1 Tool use transforms LLMs into agents that act beyond their training data, and for code-capable models, programmatic tool calling extends this further by replacing rigid JSON calls with scripts that chain and parallelize naturally. However, a systematic evaluation of tools as code on an established benchmark across current and prior model generations under real-world task conditions has not been conducted. In this work, we empirically compare programmatic tool calling (PTC) to native JSON tool calling across 14 language models on BFCL v4. In the programmatic tool calling paradigm, tools are exposed as typed Python stubs that the model invokes through code, with execution and results handled in a single agent turn. Programmatic tool calling matches or exceeds native JSON tool calling in 11 of 14 models on BFCL v4, with the GPT-5.6 family achieving a 10.6% improvement over the JSON tool calling baseline. Further, it matches or outperforms baseline in 13 of 14 models under parallel fan-out, and holds stable under context rot conditions where baseline degrades 2.3% on average. Our results demonstrate that programmatic tool calling is a viable and robust alternative to JSON tool calling, with performance tracking model capability across release generations. --- ### Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering Authors: Soorya Ram Shimgekar, Michelle Hu, Dorisa Shehi, Daniel Kang, Roy Ka-Wei Lee, Koustuv Saha, Christian Poellabauer, Christopher Lee, Sajeev Singh, Piyum Zonooz, Navin Kumar, Zeeshan Ahmed et al. Published: 2026-08-06 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.06366v1 Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists' workload. This is especially pronounced in heart failure, which affects an estimated 6.7 million U.S. adults and requires integrating fragmented EHR data with disease-specific, guideline-based clinical reasoning. Existing rule-based and large language model (LLM)-based approaches offer only partial automation with limited maintainability and evidence traceability. We developed the Nimblemind Multi-Agent System (nMAS), an evidence-linked, rubric-grounded pipeline for automated heart-failure feature engineering, and evaluated it on 500 dummy patient records from nine EHR source tables. nMAS generated 132 structured and 70 rubric-scored aggregated features, verified for structural integrity, rubric compliance, and provenance, and audited by a restricted LLM. Adding the aggregated features improved held-out AUROC from 0.895 to 0.963 for HFrEF and 0.870 to 0.910 for HFpEF phenotyping, and an independent LLM-based rubric assessment of evidence support and methodological soundness scored the features at 81.5% of maximum points. These results demonstrate the feasibility of automated, auditable feature engineering for complex cardiovascular EHR data, though evaluation was limited to a single-institution cohort and external validation is needed. --- ### Investigating Artificial Intelligence Digital Sovereignty in Mobile Shopping Apps: A Case Study of Nigeria Authors: George Grispos, Sajda Qureshi Published: 2026-08-06 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.06364v1 The use of e-commerce mobile applications is expanding in Nigeria, creating both opportunities and risks, including fraud and reduced user control over digital technologies, raising concerns about digital sovereignty. This research examines how Artificial Intelligence (AI) in Nigerian mobile applications affects digital sovereignty, examined through platform transparency as a key indicator of user awareness and control. Using an interpretive approach, the research combines the forensic analysis of selected Android applications with contextual document analysis to identify AI features and evaluate disclosure practices. The findings show that AI is widely implemented in the applications, yet transparency about its use remains limited. A socio-economic analysis of Nigeria further shows an increasing dependence on consumer digital platforms, moderate AI awareness, and uneven patterns of interaction. By providing empirical evidence on AI transparency and platform practices, this study advances understanding of individual digital sovereignty and highlights challenges for protecting user control in AI-driven digital environments. --- ### An Optimal Agnostic PAC Algorithm Authors: Markus Engelund Mathiasen, Jian Qian, Nikita Zhivotovskiy Published: 2026-08-06 Categories: cs.LG, cs.AI, cs.DS, math.ST arXiv: https://arxiv.org/abs/2608.06363v1 Let $H\subseteq\{-1,+1\}^X$ be a class of finite VC dimension $d\ge1$. Writing $L$ for the binary risk and $L^*=\min_{h\in H}L(h)$, we construct a learner achieving the statistically optimal risk bound: from an i.i.d.\ sample of size $n$, for every $0<δ\le 1/2$, with probability at least $1-δ$, \( L(\widehat h) \le L^*+ 7\cdot10^8\left( \sqrt{\frac{L^*(d+\log(1/δ))}{n}} +\frac{d+\log(1/δ)}{n} \right). \) This settles the sample complexity of agnostic PAC learning up to universal constants at every fixed $L^*$, matching the lower bounds of Devroye, Györfi, and Lugosi (A Probabilistic Theory of Pattern Recognition, Springer, 1996). --- ### AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information Games Authors: Boning Li, Yu Chen, Longbo Huang Published: 2026-08-06 Categories: cs.GT, cs.AI, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.06362v1 Deciding which of two agents is stronger means playing games until skill outweighs luck, and every game costs money, model inference, or expert time. Since the number of games needed is unknown, fixed-budget evaluations either keep paying after the result is settled or stop before the agents can be told apart, while naive optional stopping with an ordinary confidence interval invalidates the stated level. We make such an evaluation stop as soon as its evidence suffices, with the guarantee intact. The Action-Informed Value Assessment Tool (AIVAT) reduces variance in imperfect-information games through conditional mean-zero corrections, by a median $54\times$ across 15 LLM agent configurations spanning 71,439 paired Heads-Up No-Limit Hold'em (HUNL) hands, but does not say when to stop. We combine AIVAT with continuously monitored Confidence Sequences (CSs) into anytime-valid AIVAT (AV-AIVAT), whose online value model learns only from past games so that no game scores its own correction. At the nominal 95\% level and a target precision of $\pm1$ Big Blind, raw outcomes need a median $74\times$ as many hands as AIVAT-corrected outcomes to stop under the Asymptotic CS (AsympCS). Exact finite-sample certification uses the Empirical-Bernstein CS (EB-CS), which needs an independently justified bound on corrected payoffs. We establish such a bound structurally for Leduc hold'em and characterize a width floor set by the CS's bet cap and that bound, which governs how much of a variance gain becomes earlier stopping; the descriptive HUNL EB-CS runs show a median $1.37\times$ stopping-time ratio. AV-AIVAT turns variance reduction into efficient, auditable early stopping while separating asymptotic screening from exact certification, so an evaluation can stop the moment its evidence suffices and hand a third party everything needed to recheck the verdict at that very stopping time. --- ### The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping Authors: Sarvesh Baskar, Zikui Cai, Shayan Shabihi, Anirudh Satheesh, Muhammad R. Islam, Udari Madhushani Sehwag, Tom Goldstein, Furong Huang Published: 2026-08-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.06361v1 Real-world video benchmarks provide broad coverage, but their fixed clips entangle event count, rate, duration, and visual complexity, making failure modes hard to isolate. While existing programmatic benchmarks offer better control, they score only the final answer rather than auditing reported events against executable ground truth. To bridge this gap, we introduce trace-grounded parametric profiling for event counting in three controlled video tasks: bouncing-ball wall contacts, visual blinks, and categorical state transitions. Across 2,190 videos, we vary event count N and frequency F while holding rendering fixed. Each video includes an executable event trace for capability-surface estimation and timestamp-level evaluation. Our results reveal a staged temporal failure. At an 80% reliability threshold, Gemini 3.6 Flash reliably counts persistent state transitions up to 12 events at 0.5 and 1.0 Hz, yet demonstrates no reliable positive-count region for transient blinking events. Thus, event representation dictates whether a model initially accesses evidence -- a limitation that compounds as count and frequency increase. In the high-count, high-frequency regime, only 0.2% of final counts are correct and the model recovers just 18.1% of true events. To test if visual access is the primary bottleneck, we increase sampling rate. Although this boosts Bounce Ball accuracy from 19.6% to 29.3%, the reported sequence agrees with ground truth only 3.7% of the time. Extra frames can therefore inflate final scores without producing faithful event recovery. Different prompting strategies yield similarly limited gains, and real-world video evaluations show the same concentration of success at low event counts. Ultimately, trace-grounded profiling shifts video evaluation from aggregate accuracy metrics to a detailed diagnostic of where temporal reasoning fails. --- ### Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents Authors: Praphul Chandra, Sujit Gujar, Ganesh Ghalme Published: 2026-08-06 Categories: cs.GT, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.06353v1 We give a formal mechanism design model for the continuous participatory governance of a deployed AI agent. The mechanism is built on the principle that governance should control an AI agent through resource allocation so as to make authorization self enforcing via compute budgets. The mechanism seeks to establish the Safe AI paradigm that compute is an effective governance lever. We situate our work as a compliance or commons overlay on a deployer. One governance period is an extensive form game in which verified human stakeholders arrive sequentially and contribute, on a provision or a rejection market, in a governance currency that is deliberately distinct from the agents compute. A funding aggregator turns raw contributions into breadth weighted effective supports - a two threshold gate with hysteresis converts net support into a binary authorization that, through a coupling map bounded by an exogenously certified safety ceiling, releases a metered compute budget - realized in hardware as a signed compute license so that the decision is self-enforcing. We characterize the class of agents the mechanism can govern and isolate manipulation of the governing electorate by the governed agent as the central open problem. We also introduce several challenges addressing manipulation of governing electorate by the governed agents. --- ### CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks Authors: Fanzhe Meng, Guoxin Chen, Jiale Zhao, Shuang Sun, Zhiyu Lin, Wayne Xin Zhao, Ruihua Song, Ji-Rong Wen, Kai Jia Published: 2026-08-06 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.06352v1 Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task behaves relative to a given solver setting. In this paper, we present CalibForge, an autonomous terminal-task synthesis system that uses verified solver behavior to revise candidate tasks through adversarial solver calibration. Multi-solver calibration targets disagreement within a heterogeneous solver pool, whereas contrastive solver calibration targets a designated strong-pass/weak-fail relation; both operationalize a solver-relative learnable zone anchored in demonstrated solvability. Using CalibForge, we construct 5,431 calibrated terminal tasks. Our ablations show that both strategies yield more effective supervision than authoring and validation alone or ordinary single-solver feedback. Models trained on the full collection achieve 32.58% and 47.57% on Terminal-Bench 2.0. The largest improvements over the corresponding base model reach 24.71 percentage points on Terminal-Bench 2.0, 27.68 points on SWE-bench Pro, and 30.04 points on Doc2Repo. Together, these results support solver-relative learnability as a practical target for constructing effective and transferable agent training data. --- ### Challenges in Evaluating Explanation Methods for Static and Evolving Data Authors: Jerzy Stefanowski Published: 2026-08-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.06351v1 This paper addresses the limitations of Explainable Artificial Intelligence (XAI) with respect to insufficient evaluation. They are illustrated through the DetoxAI image recognition system for bias detection and concept unlearning. Then, an example of a human-grounded evaluation of methods for explaining image classification is presented. The paper further explores methods for adapting explanations to evolving data streams with concept drift. Experiences with adapting counterfactuals for this problem are discussed. Finally it is related to the challenges of tracking the co-evolution of data, models, and explanations.\footnote{This paper has been accepted for a publication in J.Nalepa (ed) Explainable AI in Space. Proceedings of EASi 2026 Workshop at IJCAI-ECAI 2026 Bremen, Springer CCIS vol 3107 (2016).} --- ### RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer Authors: Xinye Wang, Junxiao Liu, Shujian Huang Published: 2026-08-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.06347v1 Multilingual reasoning transfer is crucial for extending reasoning capabilities of large language models (LLMs) beyond high-resource languages. On-policy self-distillation (OPSD) and its variants have emerged as a promising paradigm, providing dense token-level supervision on student-generated rollouts, yet their objectives do not explicitly prioritize reasoning signals most critical to cross-lingual transfer. We characterize that target-language reasoning comprises the generation of both surface text and reasoning pivots, which are decisions that advance or redirect the reasoning process and shape subsequent inference. This motivates concentrating privileged distillation around such pivots. We therefore propose RP-OPSD, Reasoning-Pivot-guided On-Policy Self-Distillation, using the distributional shift between matched teacher views with and without an English reference solution as an operational proxy to guide privileged distillation and reference anchoring. Experiments on mathematical reasoning benchmarks covering 17 languages and multiple difficulty levels show that our method outperforms strong multilingual reasoning baselines and OPSD variants. Further analysis reveals that RP-OPSD concentrates privileged distillation on reasoning-control and problem-condistioned state-update tokens, while downweighting it for tokens that mainly support surface realization. Our code is available at https://github.com/NJUNLP/RP-OPSD. --- ### TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories Authors: Yunjia Qi, Zehua Yin, Xintong Shi, Hao Peng, Songyuanyi Lu, Yixian Liu, Richeng Xuan, Yuhong Liu, Zhichao Hu, Xiaozhi Wang, Lei Hou, Bin Xu et al. Published: 2026-08-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.06346v1 LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging. Critical error detection aims to locate the earliest error step in a failed trajectory that is responsible for the final failure. However, progress faces two main challenges. First, long trajectories make it difficult to identify individual errors, since the evidence for judging a step may be scattered across distant instructions, observations, and prior context. Second, failed trajectories often contain multiple local errors with different downstream effects, only some of which remain responsible for the final failure. In this work, we propose TrajDebug, an error-lifecycle tracing framework that addresses long-trajectory error discovery with multi-granularity history compression and evidence-based error identification, and supports critical attribution by tracing each error's resolution status and terminal impact. We further construct TrajErrBench, a benchmark of 486 manually annotated failed trajectories from Tau2Bench and SWE-Bench Pro, covering realistic tool-use and coding scenarios. Experiments across diverse agent benchmarks show that TrajDebug achieves the best overall performance over existing baselines, and application studies further demonstrate that its diagnoses provide actionable feedback for improving downstream agent success. We will release the codes and data to facilitate further research. --- ### Scalable estimation of VARMA models Authors: Daniel Paulin, Victor Elvira Published: 2026-08-06 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2608.06340v1 Vector autoregressive moving-average (VARMA) models have long been considered impractical beyond moderate dimensions: the likelihood is non-convex, the parametrization is identified only up to equivalence, and every evaluation costs a pass over the entire series. Yet their moving-average term captures with a few parameters what a pure autoregression matches only with many lags. We introduce an estimation framework that removes this computational barrier: each optimization iteration is independent of the series length $T$. The framework combines a partial-autocorrelation reparametrization that guarantees stationarity and invertibility by construction, Gaussian priors on the reparametrized coefficients with separate scales for diagonal and off-diagonal entries, and losses that depend on the data only through fixed-size sufficient statistics, evaluated by a Parseval (Fourier) identity at near-linear cost in the truncation length. This yields two point estimators: a regularized least-squares fit and a covariance-marginalized maximum-a-posteriori estimator. We prove that both recover the infinite-autoregressive representation of the true process at a near-parametric rate in fixed dimension, so the truncation introduces no asymptotic bias. The same machinery extends, at the same leading cost, to seasonal dynamics, exogenous regressors (VARMAX), and rolling-window refits. Empirically, the estimators stay close to the oracle forecast error from $d=10$ to $d=40$ (where classical conditional MLE returns non-invertible fits whose forecasts diverge) and match or beat VAR, Bayesian-VAR, component-wise ARMA, and sparse-VARMA baselines on retail-demand, meteorological, and air-quality data. This brings likelihood-based VARMA estimation, at a per-iteration cost independent of the series length, to the problem sizes where practitioners have so far relied on VAR models. --- ### Optimal Rates for Learning with Monotone Adversaries Authors: Anay Mehrotra Published: 2026-08-06 Categories: stat.ML, cs.DS, cs.LG, math.ST arXiv: https://arxiv.org/abs/2608.06337v1 A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice, every one of them labeled correctly by the target hypothesis. The learner sees a uniform shuffle of the combined sample and is scored on the original distribution. Every example is correctly labeled, but the insertions depend on the clean sample, so the combined sample is not exchangeable. Larsen, Pabbaraju, and Shetty, who introduced this model, showed that empirical risk minimization attains expected error $O((d/n)\log(n/d))$ for classes of VC dimension $d$, and that every known optimal learner can be pushed away from the $Θ(d/n)$ rate, optimal for PAC learning. They asked whether the extra logarithm is an artifact of those particular algorithms or an inherent consequence of the lack of exchangeability. We show that this additional cost is inherent beyond VC dimension one. In the worst case over classes of VC dimension $d$ and over known finite insertion budgets, the minimax expected error is $Θ(1/n)$ at $d=1$ and $Θ((d/n)\log(n/d))$ for $d\geq 2$. The same rates hold with Littlestone dimension $d_{\mathrm L}$ in place of $d$, so the clean online-to-batch rate $O(d_{\mathrm L}/n)$ is unattainable as well. Thus, somewhat counterintuitively, adding correctly labeled examples can make learning harder by a logarithmic factor, even for classes that admit finite mistake bounds in online learning. The dimension-one upper bound is achieved by a simple improper learner whose analysis adapts the leave-one-out argument underlying the one-inclusion graph. All of our lower bounds are elementary and come from a single construction: an explicit class and prior on which two target hypothesis, which differ a point of nonnegligible mass, produce the same sample. --- ### Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data Authors: Donna Hooshmand, Shubham Shahi, Cameron Barrie, Abhratanu Dutta, Marko Sterbentz, Harper Pack, Kristian J. Hammond Published: 2026-08-06 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2608.06331v1 From natural-language query interfaces to automated report generation, data analysis tools need a description of the data: the real-world entities it contains, which columns function as measures or identifiers, and how tables connect into units of analysis. Today, this semantic layer is usually written by hand. This is a knowledge-acquisition bottleneck that limits the scalability of analytic systems, keeps non-technical users dependent on experts, and is itself error-prone. We present TYTAN, a system for automatically constructing an analytic semantic schema from a relational database and, when available, a short user-provided description. TYTAN combines symbolic analysis of the database with LLM-based semantic inference for entity proposal, role assignment, and naming. When the evidence leaves a decision ambiguous, TYTAN asks the user a targeted natural-language question. We evaluate TYTAN on eight databases spanning real-world and benchmark domains along the three axes that define a schema's functional utility: (i) coverage, are all important entities and features captured?; (ii) retrieval correctness, do the schema's instructions actually reach the data; and (iii) characterization accuracy, are semantic types correct? Across the seven reference domains, TYTAN reaches every entity, attribute, and aggregable feature of the expert-corrected reference schemas (100% coverage). Additionally, 100% of its retrieval instructions execute correctly (1,678 of 1,678 self-generated claims), and semantic roles agree with the reference on 92-100% of matched attributes. Checking the underlying data showed the small disagreement is in the reference, not in TYTAN. On a held-out blind test (a live, ten-table database with no declared keys), TYTAN recovers the full entity structure with verified keys and satisfies 100% of the satisfiable expectations of five independent blind annotators. --- ### Benchmarking the Benchmarks: Evaluating Benchmarks for Conversational Agents Authors: Noam Koren, Roy Bar-Haim, Abigail Goldsteen Published: 2026-08-06 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.06329v1 Task-oriented conversational agents are evaluated using curated or automatically generated benchmarks, yet benchmark quality is rarely assessed. Poor benchmarks may contain inconsistent tasks, simplistic scenarios, or limited policy coverage, leading to unreliable evaluations. We introduce a reference-free framework that uses LLM judges to assess benchmark consistency, complexity, and policy coverage, while providing actionable diagnostics of weaknesses. We validate the framework by demonstrating agreement with independent human annotations and by evaluating benchmarks generated by LLMs of varying capabilities, as well as benchmarks subjected to controlled quality-degrading perturbations. Across domains and judge models, the proposed metrics consistently distinguish between benchmark quality levels. We further demonstrate the framework's applicability to manually curated benchmarks. Our framework offers a practical approach for evaluating synthetic and manually curated conversational-agent benchmarks. --- ### Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents Authors: Tao Wang, Qihao Yang, Rongjiao Liang, Lianghong Lin, Haitao Wang, Xinyu Cao, Tianyong Hao Published: 2026-08-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.06312v1 Large language models (LLMs) increasingly support complex professional tasks, yet their capabilities in rule-intensive document review remain insufficiently evaluated. National standard documents, such as China GB/T standards, offer a representative testbed: they are lengthy, highly structured, and governed by explicit rules for scope, terminology, normative wording, and cross-section consistency. Existing benchmarks focus on domain knowledge and question answering, largely overlooking intrinsic quality review for professional documents. Such reviews rely heavily on human experts, making them costly and difficult to scale. To bridge this gap, we introduce GB/T-Bench, the first benchmark for the structured review of national standard documents. Its GB/T Review Taxonomy is a hierarchical schema covering document structure, scope alignment, normative modality, terminology consistency, and normative references, with 25 diagnosable error types. A controllable counterexample generation mechanism combines deterministic rules and constrained LLM rewriting to process 488 documents into 7,306 traceable review error instances for evaluation. We also develop a diagnosis-oriented evaluation protocol requiring exact matches on error location, review dimension, and error type, plus document-level coverage metrics. We further propose GB/T-Reviewer, a multi-agent framework that converts review knowledge into specialized skills and coordinates global inspection, targeted diagnosis, rule scanning, and result verification. Experiments with 14 mainstream LLMs reveal a substantial human-LLM gap: the strongest model achieves only 0.3280 CMCS versus 0.6640 for experts. GB/T-Reviewer raises the best CMCS to 0.5094, showing the value of structured skill coordination for rule-intensive document review. This work paves the way for trustworthy AI in standardization and other high-stakes document domains. --- ### Does FLAIR super-resolution erase or hallucinate small white-matter lesions? Authors: Zahra Khodakarami, Yue Li, Pulkit Khandelwal, John Detre, Sandhitsu Das, Christopher Brown, David Wolk, Paul Yushkevich Published: 2026-08-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.06311v1 White matter hyperintensities (WMH), bright regions on Fluid-attenuated Inversion Recovery (FLAIR) scans are associated with cerebrovascular pathology and neurodegeneration. FLAIR is usually acquired with thick slices in clinical settings, giving it poor through-plane resolution. Super-resolution (SR) is a widely used method for recovering an isotropic volume from an anisotropic scan. Yet whether applying it prior to WMH segmentation preserves lesion content remains unknown: a model may erase small real lesions or hallucinate absent ones. We used 1-mm isotropic high-resolution (HR) FLAIR scans from 29 individuals in the ADNI cohort, each manually segmented for WMH by an expert. Then, we degraded each to simulated 3 and 5 mm through-plane acquisitions. Multi-contrast implicit neural representation (INR), a single-contrast self-supervised model (ECLARE), and cubic interpolation were used to upsample them onto the HR grid. WMH segmentation from a simulated thick slice and the original HR FLAIR set the floor and ceiling, respectively, for the per-lesion analysis. Of four WMH segmentation methods (WMH-SynthSeg, segcsvd, MARS-WMH, TrUE-Net), we ran the analysis under the most sensitive one to small lesions on HR (MARS-WMH) with the evaluation metrics of detection sensitivity, erasure rate (HR-detected lesions lost after reconstruction), and hallucination rate (predicted components absent from both the manual and HR segmentation). The dominant effect of SR was erasure of small real lesions, not hallucination, and it increased with slice thickness, though every reconstruction still improved lesion detection over the raw thick slice. ECLARE recovered small lesion signal best at both thicknesses, while the INR was no better than cubic interpolation. --- ### RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction Authors: Chenglong Wang, Ziming Zhu, Yifu Huo, Bei Li, Qiaozhi He, Yan Ding, Xiaoyang Hao, Yuxin Gao, Tianhua Zhou, Xiaojia Chang, Tongran Liu, Jingbo Zhu Published: 2026-08-06 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.06310v1 Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong capabilities in response ranking, generative reward models have not realized their potential in reinforcement learning (RL). Our analysis reveals that this limitation arises from a mismatch between the comparative nature of generative reward modeling and the scalar scoring paradigm adopted by existing RL algorithms. To bridge this gap, we propose a Ranking-based Reward Construction (RRC) approach, which enables generative reward models to provide more effective RL learning signals by deriving rewards from relative preference rankings. RRC introduces two complementary strategies: self-competitive ranking, which exploits comparisons among sampled responses, and anchor-guided ranking, which enables scalable ranking-based reward construction with a small set of reference responses. Experiments across open-ended chat and reasoning benchmarks demonstrate that RRC substantially improves RL training with generative reward models, achieving consistent gains over existing reward construction approaches. Our code can be found at https://github.com/wangclnlp/RRC. --- ### UQ-Loc: Uncertainty-Aware LiDAR Scene Coordinate Regression Authors: Jacek Komorowski Published: 2026-08-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06307v1 LiDAR-based Scene Coordinate Regression (SCR) maps point clouds directly to 3D scene coordinates, enabling precise 6-DoF localisation without explicit map retrieval. However, existing methods produce deterministic predictions, discarding aleatoric uncertainty that could improve robustness and downstream decision-making. We present UQ-Loc, which extends the LightLoc architecture with an anisotropic Gaussian covariance head that predicts a full 3x3 positive-definite covariance matrix per voxel. Training uses a Negative Log-Likelihood (NLL) loss augmented with a kNN-based spatial smoothness regulariser, while inference employs a modified SC2-PCR solver with uncertainty-weighted seed scoring and a Mahalanobis-distance inlier test. We adopt Expected Calibration Error (ECE) as a principled metric for evaluating the quality of the predicted uncertainty. Experiments demonstrate that UQ-Loc achieves consistent improvement in 6-DoF localization accuracy while producing well-calibrated covariances. --- ### Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations Authors: Sagar Tamang, Ayush Vyas, Tabarakul Hazarika Published: 2026-08-06 Categories: cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2608.06305v2 Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents -- financial statements, audit reports, regulatory returns -- this design is structurally unsound, and we make the argument measurable. On a 780-page government financial report, 86.8% of content lines are table rows, thousands of near-identical figures compete in one embedding space, and a figure inherits its unit from a header a median of 13 lines above it -- so a chunk boundary routinely separates a number from whether it is in lakh or crore, an error of two orders of magnitude. A table-aware chunker built as a steelman fixes the unit problem but leaves 27-30% of numeric chunks with no fiscal-year header at every chunk size we tried. We propose READ (Reliable Embedding-free Agentic Document-search), in which an agent reads the raw document through three deterministic operations -- normalized lexical search, structural navigation, and bounded span reads -- exposed over the Model Context Protocol, so a trajectory is a replayable audit trail, not an opaque similarity score. On 51 verified questions READ answers 58.8% against dense retrieval's 15.7% (p_Holm = 2 x 10^-5) -- or 35.3% tuned, which READ still leads by 23.5 points (p_Holm = 0.017). An agent given the same loop but a top-k tool reaches only 27.5%, locating the gain in the interface rather than in iteration. We also report what the evidence does not support: BM25 is statistically indistinguishable from READ, so our result separates embedding-based from embedding-free retrieval, not agentic from lexical search. --- ### Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations Authors: Sagar Tamang, Ayush Vyas, Tabarakul Hazarika Published: 2026-08-06 Categories: cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2608.06305v1 Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents -- financial statements, audit reports, regulatory returns -- this design is structurally unsound, and we make the argument measurable. On a 780-page government financial report, 86.8% of content lines are table rows, thousands of near-identical figures compete in one embedding space, and a figure inherits its unit from a header a median of 13 lines above it -- so a chunk boundary routinely separates a number from whether it is in lakh or crore, an error of two orders of magnitude. A table-aware chunker built as a steelman fixes the unit problem but leaves 27-30% of numeric chunks with no fiscal-year header at every chunk size we tried. We propose READ (Reliable Embedding-free Agentic Document-search), in which an agent reads the raw document through three deterministic operations -- normalized lexical search, structural navigation, and bounded span reads -- exposed over the Model Context Protocol, so a trajectory is a replayable audit trail, not an opaque similarity score. On 51 verified questions READ answers 58.8% against dense retrieval's 15.7% (p_Holm = 2 x 10^-5) -- or 35.3% tuned, which READ still leads by 23.5 points (p_Holm = 0.017). An agent given the same loop but a top-k tool reaches only 27.5%, locating the gain in the interface rather than in iteration. We also report what the evidence does not support: BM25 is statistically indistinguishable from READ, so our result separates embedding-based from embedding-free retrieval, not agentic from lexical search. --- ### HarnessOpt-Bench: Evaluating LLMs at Harness Optimization Authors: Varun Ursekar, Apaar Shanker, Yash Maurya, Shehab Yasser, Vijay S. Kalmath, Veronica Chatrath, Yuan Xue Published: 2026-08-06 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.06301v1 As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts, tools, control flow, memory, and orchestration code surrounding them. This makes automated harness optimization -- the iterative and evaluation-guided improvement of a harness by an AI system -- both an important route to improving AI systems and a demanding capability for AI systems themselves. Yet the community lacks a common protocol for measuring how well frontier LLMs perform at this task. We introduce HarnessOpt-Bench, a benchmark for end-to-end harness optimization under expensive and stochastic evaluation. An optimizer, an LLM paired with a coding harness, receives a target agent's seed harness, graded evaluation feedback, and a fixed target-evaluation budget. It edits the harness and nominates a final candidate, which is scored by its normalized gain over the seed on a held-out test partition that remains inaccessible throughout search. A trusted execution environment enforces the evaluation boundary, meters target-agent resource use, and preserves candidate versions for audit. We evaluate 5 frontier LLMs as optimizers both under a shared coding harness and under their native harnesses across 4 downstream tasks, over 111 scored runs. Experiment results show that optimizer models separate more than the coding harnesses they act through, native harnesses are not consistently superior, and gains vary substantially across tasks and seed regimes. These results establish harness optimization as a measurable and discriminative capability with large space for improvement. --- ### Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors Authors: Arya Labroo, Mengjie Qian, Kate Knill Published: 2026-08-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.06300v1 Automatic speaking assessment systems are increasingly deployed in high-stakes settings to mark second language (L2) learners' speaking tests, making it critical to show that their scores depend on speaking proficiency rather than irrelevant speaker attributes such as first language (L1) or age. Transformer-based foundation models have improved the accuracy of these L2 speaking graders, but their black-box representations make fairness and interpretability analysis more difficult. Building on prior work that used Concept Activation Vectors (CAVs) to detect bias towards unwanted attributes (`concepts') in feature-based graders, we extend CAV-based analysis to two neural speaking assessment systems: a text-based BERT grader and a speech-and-text multimodal grader based on Whisper. CAVs represent human-interpretable concepts as directions in a model's activation space, allowing us to distinguish between whether a concept is encoded in a model's internal representations and whether it influences the predicted score, the latter quantified using a gradient-based sensitivity metric. Since CAVs rely on linear separability, which is less likely in complex neural embedding spaces, we also investigate whether sparse autoencoders (SAEs) provide cleaner concept directions by learning CAVs in a sparse latent space and mapping them back to activation space. Our analysis shows that concept recoverability depends strongly on the representation and architecture being probed, rather than on the concept alone. Sensitivity to concepts is also architecture-dependent. SAEs make concepts more linearly recoverable, but attenuate the original activation-space sensitivity, especially in low-dimensional layers. These findings highlight the need to distinguish concept recoverability from concept influence when auditing bias in speaking assessment systems. --- ### On-Policy Self-Distillation without Any Supervision Authors: Yijiang Li, Bingyang Wang, Yijun Liang, Yunjie Tian, Di Fu, Nuno Vasconcelos Published: 2026-08-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.06296v2 On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs). However, existing methods still rely heavily on external supervision, including ground-truth signals, environmental feedback, or guidance from larger models, and therefore fall short of genuine "self"-distillation. In this study, we show that on-policy self-distillation can be achieved using only a model's own generations via internal consistency. We propose unsupervised on-policy self-distillation (U-OPSD). U-OPSD first samples multiple rollouts and constructs a pseudo solution by majority vote under a self-consistency threshold. It then conditions the model's distribution on the pseudo-solution and distills itself on the disagreeing completions, allowing the model to correct itself precisely where it is confidently wrong. Across diverse benchmarks, base models, and training settings, U-OPSD consistently improves over the base models and matches or surpasses supervised methods with ground truth (GT) such as OPSD and GRPO. On five mathematical reasoning benchmarks, i.e., AIME24, AIME25, HMMT25, MATH500, and AMC23, U-OPSD improves over the base model by 8.5% and 10.7% on Qwen3 non-thinking mode at 4B and 8B scales, and outperforms OPSD by 3.2% and 2.3% on average, respectively. In thinking mode, U-OPSD stays on par with OPSD, ahead by 0.9% at 4B and level at 8B and surpassing GRPO by 0.7% and 1.1%, respectively. Code is available at (https://github.com/williamium3000/u-opsd)(https://github.com/williamium3000/u-opsd). --- ### On-Policy Self-Distillation without Any Supervision Authors: Yijiang Li, Bingyang Wang, Yijun Liang, Yunjie Tian, Di Fu, Nuno Vasconcelos Published: 2026-08-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.06296v1 On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs). However, existing methods still rely heavily on external supervision, including ground-truth signals, environmental feedback, or guidance from larger models, and therefore fall short of genuine "self"-distillation. In this study, we show that on-policy self-distillation can be achieved using only a model's own generations via internal consistency. We propose Unsupervised On-Policy Self-Distillation (U-OPSD). U-OPSD first samples multiple rollouts and constructs a pseudo-solution by majority vote under a self-consistency threshold. It then conditions a teacher distribution on the shortest pseudo-solution and distills it into prefixes of the model's longest incorrect completion, allowing the model to correct itself precisely where it is confidently wrong. Across diverse benchmarks, base models, and training settings, U-OPSD consistently improves over the base models and matches or surpasses supervised methods with ground truth (GT), such as OPSD and GRPO. On AIME24, AIME25, HMMT25, MATH500, and AMC23, U-OPSD improves over the base model by 8.5% and 10.7% on Qwen3 non-thinking mode at the 4B and 8B scales, respectively, and outperforms OPSD by an average of 3.2% and 2.3%. In thinking mode, U-OPSD remains on par with OPSD, outperforming it by 0.9% at 4B and matching it at 8B, while surpassing GRPO by 0.7% and 1.1%, respectively. --- ### QuanTiMedAI: Quantum-Enhanced Time-Series Model guided by Agentic AI for Cardiac Arrest Mortality Prediction Authors: Mutasim Fuad Sarker, Adiba Rahman Namira, Wafa Binte Alam, Md Adnan Arefeen, Mahzabeen Emu, Sumaiya Tabassum Nimi Published: 2026-08-06 Categories: cs.AI, cs.ET arXiv: https://arxiv.org/abs/2608.06294v1 Cardiac arrest remains one of the most lethal conditions encountered in intensive care units. Despite the growing availability of electronic health record data, existing mortality prediction studies in this population largely depend on static summaries derived from early admission. Such approaches ignore the temporal progression of physiological deterioration and recovery that unfolds throughout a patient's ICU stay. To address this limitation, we introduce QuanTiMedAI, a quantum-agentic framework developed for cardiac arrest mortality prediction using agentic AI guided quantum enhancement time series model. The proposed system combines an agentic large language model (LLM) for clinically informed feature discovery with a compact quantum recurrent network for temporality aware mortality prediction. Our findings demonstrate that agentic LLM-guided feature selection consistently outperforms conventional feature selection approaches, and the proposed quantum architecture achieves competitive predictive performance through nonlinear feature enhancement while keeping the number of parameters very low. Through extensive experimentation on a MIMIC-IV cohort of cardiac arrest patients, QuanTiMedAI's quantum-enhanced architecture attains an AUROC of 0.852 using only 605 parameters, an improvement of approximately 2.9\% over a current state-of-the-art baseline for this task. A structured ablation study systematically validates the contribution of each architectural design choice. These results show that quantum-enhanced sequential modeling can exceed classical recurrent networks while using substantially fewer parameters. --- ### NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering Authors: Jonas Gann, Michael Gertz Published: 2026-08-06 Categories: cs.CL, cs.SC arXiv: https://arxiv.org/abs/2608.06292v1 Retrieval-augmented generation (RAG) improves question answering by grounding large language models (LLMs) in external knowledge such as text corpora. However, its reasoning process remains largely opaque: intermediate reasoning steps are difficult to verify and cannot be reliably attributed to specific evidence. Moreover, missing user-specific context is rarely detected systematically, often leading to incomplete or incorrect output. We propose NeSy-RAG, a modular neuro-symbolic RAG framework that synthesizes attributable Prolog modules from retrieved text chunks. For each chunk, the system generates semantically meaningful predicates that encode Boolean claims, which may depend on user facts. Using joint natural language-code embeddings, predicates are retrieved and composed into Prolog queries. To address incomplete user context, we introduce a symbolic knowledge-gap detection mechanism that identifies missing user facts whose truth values affect the query outcome and automatically triggers follow-up interactions. Executing the resulting Prolog queries yields deterministic answers together with transparent execution traces that link each reasoning step to its originating source. On the ShARC benchmark, without domain-specific training, NeSy-RAG achieves 61.1% accuracy, outperforming a same-model RAG baseline that achieves 42.8% accuracy. --- ### FastKron: Efficient Quantization with Kronecker-Factored Hessians Authors: Johann Birnick, Rayan Saab Published: 2026-08-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.06291v2 We accelerate a family of algorithms for neural network quantization which utilize a two-sided version of the GPTQ/LDLQ algorithm. Standard GPTQ-style adaptive rounding uses one-sided correlation information derived from input activations. A natural two-sided extension can additionally capture correlations across output channels. It utilizes a general Kronecker-factored approximation of the weight matrix curvature. This approach has been used in BoA and YAQA. But making a concrete algorithmic implementation of this two-sided GPTQ variant is nontrivial. BoA uses a large number of sequential steps, while YAQA improves over the sequential depth but still has quartic total cost. We introduce FastKron, an efficient algorithmic implementation that combines anti-diagonal parallelism with a recursive divide-and-conquer construction. For an $m\times n$ weight matrix, FastKron uses $O(m+n)$ sequential steps while reducing the total work from $O(m^2n^2)$ to $O(mn(m+n))$. Thus, it matches the cubic scaling of GPTQ while exploiting richer curvature information. Moreover, FastKron is modular with respect to both the base quantizer and the Hessian estimator. We also provide practical benchmarks, consider a range of Hessian approximations that FastKron can be used with, and provide an efficient technique to compute these Hessians. --- ### BaKron: Efficient Quantization with Kronecker-Factored Hessians Authors: Johann Birnick, Rayan Saab Published: 2026-08-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.06291v1 We accelerate a family of algorithms for neural network quantization whose geometry is informed by any Kronecker-factored approximation of the Hessian. GPTQ-style adaptive rounding typically uses one-sided information derived from input activations. Two-sided Kronecker-factored Hessian approximations can additionally capture correlations across output coordinates, but applying GPTQ directly in the vectorized weight domain is computationally expensive. Building on the two-sided adaptive-rounding formulation used by BoA and YAQA, we introduce BaKron, an efficient solver that combines anti-diagonal parallelism with a recursive divide-and-conquer construction. For an $m\times n$ weight matrix, BaKron uses $O(m+n)$ sequential steps while reducing the total work from $O(m^2n^2)$ to $O(mn(m+n))$. Thus, it matches the cubic scaling of GPTQ while exploiting richer curvature information. Moreover, BaKron is modular with respect to both the base quantizer and the Hessian estimator. We also provide practical benchmarks, consider a range of Hessians that BaKron can be called with, find an efficient technique to compute these Hessians, and evaluate the algorithm experimentally. --- ### Learning Latent Memory States from Longitudinal Athlete Monitoring Data Authors: Dae-Jin Lee Published: 2026-08-06 Categories: stat.CO, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2608.06290v1 We propose a new unit of analysis for longitudinal data: the Latent Memory Table. The scientific contribution is not the encoder. It is that table, treated as a reusable statistical object on the same footing as a matrix of principal-component scores, a table of estimated random effects, or a table of predicted probabilities. We estimate a statistical table that summarizes recent longitudinal history and is intended to be stored, queried, analysed and reused throughout the statistical workflow. A memory operator maps each masked windowed history to a finite-dimensional state; collecting those states with uncertainty yields the Latent Memory Table. Validation is organized around six properties---recoverability, personalization, temporal coherence, interpretability, stability and reusability---summarized by a composite quality index \(Q\); the Transformer, the SoccerMon case study and the simulations exist to argue that this table deserves that status. Classical exponentially weighted moving averages and related short- and long-horizon scalar summaries arise as restricted, typically univariate special cases of the same operator class. A simulation study with known memory mechanisms shows that \(Q\) and rotation-invariant recovery scores discriminate genuine multivariate or personalized memory from negative controls and from misspecified windows, whereas regime classification accuracy alone does not. SoccerMon serves as an empirical case study: a constructed Latent Memory Table attains \(Q\approx 0.73\) versus about \(0.40\) for classical and lagged principal-component baselines, with incremental held-out value for some wellness targets and Procrustes ensembles for row-wise reliability. --- ### Surv-IPTB: An Attention-Based Model for Estimating Individual Probability of Treatment Benefit with Survival Data Authors: Lev V. Utkin, Stanislav K. Kogan, Andrei V. Konstantinov Published: 2026-08-06 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.06288v1 This work presents a novel attention-based framework for estimating the Individual Probability of Treatment Benefit (IPTB) in survival analysis contexts. The proposed model, called Surv-IPTB, directly quantifies the probability that a specific patient will experience extended survival time under treatment versus control. We reformulate IPTB estimation as a binary classification problem, leveraging pairwise patient comparisons across treatment and control cohorts. The framework incorporates a principled handling of right-censored observations through imprecise probability representations, where uncertain treatment effects are characterized by interval-valued probabilities. An attention mechanism with learnable query-key transformations enables flexible, data-driven aggregation of pairwise comparisons, while simultaneously learning soft class probabilities for censored cases. Through extensive experiments on synthetic datasets with complex nonlinear structures, including spiral, bell-shaped, and circular feature spaces, we demonstrate that our approach maintains robust performance across varying censoring rates and treatment effect strengths. The model consistently outperforms meta-learner baselines (T-learner and S-learner) equipped with random survival forests, Cox proportional hazards, and Beran estimators, particularly in challenging nonlinear scenarios where conventional methods exhibit significant degradation. The results establish the proposed attention-based framework as a scalable and statistically principled solution for personalized treatment benefit assessment in survival settings. The code implementing the model is publicly available. ---