# Research Papers — 2026-08 · bundle page 72 of 240 > Full-text markdown of papers #3551–3600 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/72 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/71.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/73.md) ### Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiency Authors: Zhihong Cao, Chen Huang Published: 2026-08-23 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.22266v2 In the context of information seeking, conversational agents are undergoing an evolution from reactive tools to proactive, personalized assistants. A critical aspect of this evolution is the ability to tailor strategic interactions to a user's unique needs and expectations. Unlike existing studies that focus on proactively clarifying query ambiguities, we center on clarifying the user's expertise in order to tailor responses for better user comprehension. We find that existing agents struggle to determine user expertise from queries alone, a limitation that prevents them from dynamically adapting their responses. To address this gap, we introduce PASSING to empower the agent to proactively clarify a user's expertise through targeted inquiries. This is achieved by our What-to-ask and How-to-ask strategies, induced by LLM self-play. Our extensive experiments also show our superiority. We believe that PASSING represents a crucial step towards creating more human-centric conversational agents. --- ### Training-Free VLM Personalization via Calibrated Residual Decoding Authors: Jiaao Yu, Yujian Ma, Xianming Hu, Pengran Wang, Ang Li Published: 2026-08-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.22263v1 Vision-language models can be personalized in a training-free manner by directly providing user profiles, preferences, or visual references at inference time, without updating model parameters. However, direct personalized prompting does not guarantee that the model will reliably exploit such evidence. The predictive distribution under the positive user profile often mixes two sources: personalized signals genuinely supported by the current profile, and the model's generic visual or linguistic priors. As a result, from the positive-profile response alone, it is difficult to determine whether a high-confidence answer is supported by the user profile or merely reflects the model's default preference. To address this problem, we propose a training-free calibrated residual decoding framework. Given the same image and question, we construct three evidence conditions: a positive profile , a counterfactual profile , and an empty profile . Our method keeps the prediction under as the anchored base, and explicitly estimates the marginal contribution of personalization from score differences across the three conditions. We further introduce normalized-entropy-based uncertainty calibration, allowing the strength of personalized enhancement to adapt to the reliability of the residual signal. Experiments on MMPB, YoLLaVA, and MyVLM show that the proposed method improves personalized multimodal understanding without fine-tuning, with consistent gains on identity-sensitive visual personalization tasks. Additional analysis shows that entropy calibration stabilizes residual decoding when the contrastive personalization signal is uncertain. --- ### Toward a First-Principles Update Geometry for the Language-Model Head Authors: Aditya Somasundaram, Charles Guille-Escuret, Alexander Moreno, Zhengzhong Liu, Eric Xing Published: 2026-08-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.22253v2 Muon motivates designing optimizer geometry around the function of each parameter block and uses the spectral norm for hidden linear layers. For the language-model head, the spectral norm is not a faithful measure of functional change. Softmax removes shared logit shifts, whereas the spectral norm can assign arbitrarily large size to updates that change no output probability. We therefore treat the LM head and softmax as one module and derive an update geometry for their composition. Hilbert's projective distance respects this invariance as it measures the largest change in pairwise log odds. For an update $S$ with token rows $s_i^\top$, we show that the largest Hilbert distance over $\left\lVert h\right\rVert_2\leq H$ is exactly $H D(S)$, where $D(S)=\max_{i<j}\left\lVert s_i - s_j\right\rVert_2$ is the Euclidean row diameter. This diameter replaces the spectral norm in the resulting Muon-style steepest descent problem. An exact solution is possible, but its direct formulation contains one $d$-dimensional vector variable for every token pair. For a vocabulary size of approximately $50$k, this means more than one billion token pairs, making the calculation impractical at every training step. We instead impose a stronger common-ball constraint and derive projected RowNorm as an $O(Vd)$ solution. For the exact RowNorm oracle, we prove that its first-order decrease is at least $1/\sqrt{2}$ of the exact diameter-constrained optimum. With Muon on the backbone, experiments across three seeds at 190M, 380M, and 640M parameters show that RowNorm reduces mean final step diameters and empirical Hilbert RMS perturbations by factors of $45$--$60$ and $12$--$15$, respectively, with only a $0.0057$--$0.0153$ increase in mean final validation loss. --- ### Sharp Barron Regularity Results for Coulombic Many-Electron Wave Functions Authors: Pingbing Ming, Hao Yu Published: 2026-08-23 Categories: math.AP, cs.LG, math.NA arXiv: https://arxiv.org/abs/2608.22252v1 We establish sharp Barron regularity for Coulombic many-electron wave functions after extraction of the universal cut-off Jastrow factors. Following the factorization of Fournais et al.~\cite(Definition~1.4){FournaisEtAl2005}, for a Coulombic eigenfunction $ψ$ we define the successive quotients by \( φ=e^{-F_{2,\mathrm{cut}}}ψ\quad\text{and}\quad φ_3=e^{-F_{3,\mathrm{cut}}}φ=e^{-(F_{2,\mathrm{cut}}+F_{3,\mathrm{cut}})}ψ. \) Then \( φ,φ_3\in\mathcal{B}^s(\mathbb{R}^{3N}) \qquad\text{for every }s<2. \) This range is optimal among universal factorizations. No factor depending only on the particle number and the nuclear data, but not on the eigenfunction or its eigenvalue, can make every corresponding quotient belong to $\mathcal{B}^2$. We also determine the exact endpoint growth. Writing $\varepsilon=2-s$, we prove that, for either $u=φ$ or $u=φ_3$, there is a computable constant $M$ independent of $\varepsilon$ such that \( \left\|u\right\|_{\mathcal{B}^{2-\varepsilon}}\leq\frac{M}{\varepsilon^2}\left\|u\right\|_{\mathcal{B}^1}. \) For the unperturbed two-electron atom we prove, with a constant independent of $\varepsilon$, \( \left|\left\|φ_3\right\|_{\mathcal{B}^{2-\varepsilon}}-\frac{32πZ\lvertφ_3(0,0)\rvert}{\varepsilon^2}\right|\leq\frac{C}{\varepsilon}. \) Hence the quadratic rate in the upper bound is sharp whenever $\lvertφ_3(0,0)\rvert\neq0$, as is the case for the ground state. --- ### CAIA in Practice: Field Evaluation of an AI-Assisted Support System for Text-Based Online Counselling Authors: Philipp Steigerwald, Nico Bienlein, Jennifer Burghardt, Mara Stieler, Robert Lehmann, Jens Albrecht Published: 2026-08-23 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2608.22251v1 Rising global demand for mental health support creates significant service delivery challenges, with asynchronous email counselling serving as a crucial low-threshold channel for accessing care. This paper presents CAIA, a co-designed AI-based tool suite that demonstrates responsible AI integration into counselling practice through seven LLM-driven functions enhanced by retrieval-augmented generation. A field evaluation involved 34 professional counsellors conducting authentic sessions with trained student counsellees (36 threads, 321 messages, 1,257 AI outputs). User behaviour analysis confirms substantial adoption, revealing that professional autonomy and information accuracy are decisive for sustained acceptance, with counsellors particularly valuing interpretive functionalities that provide new perspectives and stimulate professional reflection. --- ### Nürnberg NLP @ GermEval Shared Task 2026: Harmful Content Detection in German Social Media through Error-Independent LLM Voters Authors: Philipp Steigerwald, Eric Rudolph, Jens Albrecht Published: 2026-08-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.22246v1 Harmful content in German social media does real-world damage, from calls to action to criminal defamation. The GermEval 2026 shared task scores its detection in four subtasks. The technical challenge is a severe class imbalance. The harmful classes are rare and share surface language with the dominant majority class, yet under macro-F1 they decide the score. The decisive lever is then not a stronger single model but error independence. This insight becomes a per-subtask nine-voter ensemble spanning three orthogonal axes: LLM, training method and class scope. Selected mainly on internal cross-validation, the system reaches macro-F1 of 89.56 (C2A), 71.63 (DBO), 54.84 (VIO) and 83.02 (DEF) on the hidden test set, placing first on all four subtasks. --- ### Improving Few-Step Language Flows with Untied Self-Conditioning Authors: Bocheng Li, Linli Xu Published: 2026-08-23 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.22244v1 Flow-matching language models refine all token positions in parallel and can trade sampling steps for latency, yet generation quality still degrades sharply with few sampling steps. We trace a source of this degradation to a train--inference mismatch in previous-prediction self-conditioning: during training, the self-conditioning input is computed from the current noisy state with no intervening solver step; during sampling, the solver folds the previous prediction into the latent before that same prediction reappears as the explicit self-conditioning input. This coupling, absent during training, creates redundancy that grows with step width. We show that the mismatch degrades both the self-conditioning input and the solver update, and derive a correction for each from the model's own structure. From the frozen projection weights we identify directions along which the self-conditioning input is redundant with the latent and dampen them; from the solver's integration structure we derive that a step-average prediction is needed and approximate it from prediction history, with scale set by offline trajectory statistics. The resulting sampler, Untied Self-Conditioning, requires no retraining and uses one evaluation per step. At 8 sampling steps on LangFlow, it reduces OpenWebText generative perplexity from $531$ to~$62$ ($8.6\times$); under an adapted Arena-Hard-Auto~v2 protocol, its outputs are preferred in $96\%$ of pairwise comparisons. On ELF-B it reduces generative perplexity from $71$ to~$43$. Improvements hold from 8 to 256 sampling steps. --- ### Hyper^2: Unleashing Hyperbolic Geometry's Full Potential via Dual-Space Consistency Authors: Guantian Zheng, Haiyang Xu, Tianyu Gao Published: 2026-08-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.22238v1 HyperbolicCD pioneered hyperbolic geometry for point cloud completion by replacing the Euclidean Chamfer distance with arcosh(1+alpha||x-y||^2), but the reported gains are modest (3-7% Chamfer reduction across SeedFormer, PointAttN and PMP-Net backbones on PCN and ShapeNet-55). We argue the bottleneck lies elsewhere: the loss is hyperbolic but the encoder it back-propagates through is Euclidean, so the position-dependent supervision of the loss is averaged away by the chain rule before it reaches the parameters. We call this a cross-geometry mismatch, and make it testable through two model-agnostic indicators, feature-loss correlation r_FL and effective gradient utilisation u_G. On an SVDFormer backbone trained with HyperbolicCD's loss alone we measure (r_FL, u_G) = (0.68, 39%). We propose Hyper^2, a dual-space consistency framework that extends HyperbolicCD by reusing the identical arcosh(1+alpha d^2) functional form as a positional bias on the refinement attention (a hyperbolic distance encoding), paired with HyperbolicCD's hyperbolic Chamfer loss under a single shared curvature alpha. Both operators are O(N log N) scalar non-linearities on Euclidean distances and together add only ~1.6% FLOPs over SVDFormer. Hyper^2 delivers -22.9% Chamfer on ShapeNet-55 over SVDFormer (well above the 13.2% linear sum of the -12.0% loss-only and -1.2% encoding-only single-space ablations) and -37.5% on the 21 unseen ShapeNet-34 categories. The two indicators remain essentially flat for any single-space configuration but jump together to (0.95, 87%) only when both encoder and loss are hyperbolic, supporting the claim that geometric consistency across encoder and loss, rather than either operator alone, is what enables hyperbolic supervision in point cloud completion. Code is available at https://github.com/Ethan-Zheng136/Hyper-2. --- ### Read Less, Solve More: Token-Efficient Sparse Reading for AI Agents Authors: Zedong Liu, Jiaan Wu, Xinyang Ma, Le Xu, Kai Wang, Yuanchao Hu, Dingwen Tao, Guangming Tan Published: 2026-08-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.22237v1 Long-horizon agents increasingly rely on repeated access to external artifacts, yet current reading interfaces often expose entire objects even when only sparse evidence is needed. This over-reading increases token and latency costs and can dilute task-relevant evidence, while existing context-reduction methods mainly intervene after broad content has already entered the trajectory. We present SparseRead, a training-free, model-transparent reading layer that controls content admission before unnecessary evidence reaches the model context. SparseRead combines a regime-aware Read Gate, extensible Reader Backends, and a stateful protocol for bounded, source-anchored evidence acquisition with explicit refinement, verification, stopping, and fallback. Across six frontier models, including Claude Opus 5, and five workload scenarios, SparseRead reduces token volume by up to 92.9% and wall time by up to 89.0%, while preserving or improving task quality. Its consistent gains across three agent frameworks further demonstrate broad portability. --- ### MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models Authors: Yize Li, Ningyuan Yang, Sile Yin, Sindhuja Thogarrati, Sung-En Chang, Andrew C. Singer, Xue Lin, Chuan-Che Huang, Shuo Zhang Published: 2026-08-23 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2608.22236v2 Large audio-language models (LALMs) have shown promising progress in understanding speech, music, and general sound events, yet their ability to reason about how audio signals are degraded remains underexplored. Existing benchmarks primarily evaluate semantic understanding, event recognition, or high-level audio reasoning, leaving a basic question unanswered: Do LALMs understand the differences in audio quality? We introduce MRMAD, a Multi-Round Multi-Audio Degradation benchmark for evaluating audio degradation perception and understanding in LALMs. MRMAD spans speech, music, and sound, and frames evaluation as multi-turn dialogues across multiple audio inputs, requiring models to identify types of degradation, compare severity, and perceive corruption changes across turns. Unlike current single-turn audio-language benchmarks, MRMAD evaluates whether LALMs can maintain consistent degradation hypotheses with new evidence and comprehend low-level acoustic phenomena over multi-turn dialogues. Through a systematic evaluation of 18 representative LALMs from non-thinking to reasoning and Omni models, we find that current models often recognize coarse content while failing to diagnose, compare, or reason about degradations reliably. Human evaluations further reveal a significant perception gap between LALMs and human listeners. MRMAD thus exposes a critical yet overlooked aspect of audio-language understanding and provides a diagnostic foundation for building future LALMs that are robust to real-world acoustic conditions. --- ### A Query-Time Framework for Transient 2D Pore-Scale Flow Prediction and Generative Design Authors: Yiming Wang, Jiale Zhu, Zhichen Ye, Yandong Lv, Shiqi Wang, Jinlong Liu, Yucheng Fan Published: 2026-08-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.22235v1 Pore-scale flow governs transport and permeability behaviour in porous media engineering applications, yet repeated lattice Boltzmann method (LBM) simulation across many geometries and design queries remains costly for repeated deployment. This study formulates transient pore-scale flow prediction as a geometry-conditioned query-time operator and introduces QSGS-Transient-7606, a benchmark of 7,606 two-dimensional porous structures each paired with 30 logarithmically sampled LBM states. The proposed continuous-time pore-scale flow surrogate model (CT-PoreFlow) integrates topology-aware geometry encoding, compressed spectral mixing, and log-time conditioning with a late-time flux-calibration objective. On unseen test geometries, CT-PoreFlow achieves a velocity relative L2 of 0.2248 and a terminal permeability error of 12.81%. Frozen morphology and computed tomography image audits confirm reasonable cross-geometry robustness without fine-tuning. The surrogate is then embedded in an inverse design workflow, screening 9,216 generative adversarial network and diffusion candidates across 18 property targets prior to LBM verification. Guided GAN sampling attains 98.11% through-connectivity and 72.28% conditional design success, exceeding diffusion-based generation. The framework unifies transient flow prediction, transport-aware screening, and LBM-verified inverse design for porous media. --- ### When Test-Time Adaptation Helps, Harms, or Becomes Inactive: A Condition-Level Study on CIFAR-10-C Authors: Sreeja Guha Majumdar, Aratrika Saha Published: 2026-08-23 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2608.22233v1 Test-time adaptation (TTA) aims to improve model robustness under distribution shift by adapting a source model using unlabeled test data. Although methods such as TENT and EATA have demonstrated gains on corrupted data, aggregate accuracy can obscure the conditions under which adaptation fails or provides little benefit. We present a controlled comparison of three TTA strategies---BatchNorm-statistics adaptation (BN-Adapt), entropy-minimization adaptation (TENT), and reliability-filtered adaptation (a scoped re-implementation of EATA)---against an unadapted source model on the full CIFAR-10-C benchmark, covering 15 corruption types and 5 severity levels. All three methods improve mean accuracy over the source model by 12.2--13.3 percentage points (Wilcoxon signed-rank $p < 10^{-12}$). However, each method underperforms the source model on 8.0--9.3\% of conditions, with failures concentrated in low-severity corruptions where the source model already performs near ceiling, particularly brightness, fog, contrast, and defocus blur. We further find that EATA closely tracks the gradient-free BN-Adapt baseline, with a mean absolute difference of 0.09 percentage points, compared with 1.08 percentage points relative to TENT. This suggests that reliability filtering can substantially restrict effective adaptation, causing EATA to behave more like a BatchNorm-statistics baseline than an entropy-minimization method. These results show that aggregate accuracy alone can mask systematic TTA failure modes and motivate condition-level evaluation of when adaptation helps, harms, or becomes effectively inactive. --- ### Beyond What Meets the Eye: Unveiling Situational Illusions for Multimodal Large Language Models Authors: Zhiming Yang, Zhuoxi Xiong, Donglin Zhou, Wenjun Wei, Shiyao Cui, Jinqiao Shi Published: 2026-08-23 Categories: cs.AI, cs.CL, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2608.22232v2 Real-world situation appearances can deviate from their underlying physical states, challenging the reliability of multimodal large language models (MLLMs) in practical applications. In this paper, we term this phenomenon situational illusions and investigate: (1) how MLLMs perform under such illusions, and (2) how to mitigate the limitations. We first develop a comprehensive where-what-how taxonomy that characterizes where situational illusions occur, what targets they take, and how they arise. Building on this taxonomy, we introduce MSIBench, a benchmark designed to assess the discrimination, understanding, and reasoning capabilities of MLLMs under situational illusions. Evaluations of 27 model configurations reveal that current MLLMs are highly vulnerable to these illusions and exhibit 6 typical failure modes related to visual observation, grounding, and reasoning. To mitigate the limitations, we build on the core idea of systematically inspecting and reasoning over visual evidence for contextual understanding, developing prompting for closed-source models and supervised fine-tuning for open-source models, respectively. These two simple yet effective methods improve model performances by 20% at most, suggesting a practical path toward more reliable multimodal perception and reasoning in complex real-world environments. --- ### Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based Moderation Authors: Junyu Lu, Kaiyuan Liu, Kaichun Wang, Jingyi Kang, Deyi Ji, Hailong Zhang, Lanyun Zhu, Qi Zhu, Bo Xu, Liang Yang, Hongfei Lin Published: 2026-08-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.22230v4 Large language models (LLMs) are increasingly used for hate speech moderation, often within human--AI workflows in which reviewers provide feedback before a final decision. Such feedback introduces two manipulation directions: whitewashing hateful content as normal and smearing normal content as hateful. This study examines the susceptibility of initially correct model judgments to annotator-style rebuttals and analyzes whether attack effectiveness differs across manipulation directions. We introduce a rejudge protocol that extends direct contradiction with decision-boundary perturbations and adversarial rationales. Experiments with multiple LLMs on two hate speech datasets show that annotator-style rebuttals substantially degrade moderation performance, with stronger effects in multi-turn settings. The results further reveal stable, model-specific asymmetries between whitewashing and smearing across attack configurations, indicating distinct directional vulnerability patterns. Explicit reasoning prompts and defensive instructions reduce these effects but do not eliminate them. These findings highlight the need for direction-aware safeguards and dedicated feedback-robustness evaluation in human--AI moderation workflows. --- ### Grounded Normative Rule Generation with Structured Search Authors: Fanqi Kong, Huaxiao Yin, Ruijie Zhang, Xiaoyuan Zhang, Yizhe Huang, Jian Gao, Shuo Chen, Song-Chun Zhu Published: 2026-08-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.22229v1 Normative rules like institutional charters and workplace policies must be both human-readable and operationally verifiable against actual environment records. However, current language generation and structured-output benchmarks primarily reward surface fluency or schema compliance, leaving operational grounding weakly tested. This creates a critical vulnerability where standard language models generate plausible-sounding policies that fail during enforcement because they rely on unavailable data logs or misaligned scopes. To address this challenge, we formalize the problem as Grounded Normative Rule Synthesis (GNRS) and introduce GNRS-Search, a framework that utilizes Markov Chain Monte Carlo (MCMC) sampling to optimize a discrete, five-slot And-Or Graph (AOG). By explicitly decoupling intermediate operational structure from final prose generation, this method isolates executable feasibility from writing style and allows rule failures to be localized prior to surface realization. We evaluate our approach on GNRS-Bench, a benchmark spanning 116 controlled goals across eight scene families, and RealCharter-Bench, which evaluates transfer to 53 real-derived policy tasks with hidden source clauses. GNRS-Search raises average rubric quality from 68.8% to 81.0% and ranks first under a disclosed executable composite metric, while systematic slot interventions confirm that performance gains stem from robust operational logic rather than rhetorical tuning. Ultimately, by transforming automated rule drafting into an inspectable search problem, this work provides a foundational paradigm for deploying verifiable and compliance-ready personal agents within regulated environments. --- ### Risk-Sensitive Reinforcement Learning with Smoothed Quantile Objectives Authors: Mohammad Alipour-Vaezi, Huaiyang Zhong, Sajad Khodadadian Published: 2026-08-23 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2608.22227v1 Reinforcement Learning (RL) has achieved tremendous success in recent years. However, the classical foundations of RL do not account for the risk sensitivity of the objective function, which is critical in various fields, including healthcare, finance, etc. A popular approach to incorporate risk sensitivity is to optimize a specific quantile of the cumulative reward distribution. However, exact quantile objectives are non-smooth and can change abruptly under small perturbations of the return distribution, making them difficult to optimize reliably when the transition model must be learned from data. Motivated by this instability, we develop UCB-BQRL, a model-based optimistic learning algorithm that maintains confidence sets for the transition kernel and plans using a lower-buffered quantile criterion. The buffered criterion smooths the exact quantile objective by averaging nearby lower quantiles, thereby improving stability under transition-estimation error. To compute the buffered-quantile policy at each episode, we introduce EVI-BQ, an exact dynamic-programming procedure. We establish a high-probability regret bound for UCB-BQRL, which up to logarithmic factors scales as $\mathcal{O}(\mathrm{e}^{τ/ρ_τ}+H^2\sqrt{SAT})$, where $ρ_τ$ is denoted as the root-level left-plateau threshold, which is a problem-dependent constant. Further, we establish an information-theoretic lower bound of $Ω(H/ρ_τ\sqrt{AT})$ for the regret of any algorithm dealing with a quantile objective function. Finally, we prove that the exact point-quantile evaluation and exact lower-buffered quantile evaluation are PP-hard under polynomial-time Turing reductions, even for a fixed policy in a two-state, one-action finite-horizon MDP. --- ### FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain Generalization Authors: En Yu, Xiaoyu Yang, Wei Duan, Guangquan Zhang, Jie Lu Published: 2026-08-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.22224v1 Temporal Domain Generalization (TDG) aims to learn from historical domains and generalize to unseen future distributions under concept drift. Nevertheless, prevailing TDG methods struggle with complex real-world streaming scenarios involving both multi-scale drift patterns (e.g., long-term periodicity intertwined with short-term incremental changes) and local uncertainties, especially in continuous settings where observations arrive irregularly. To address this limitation, we propose FreKoo++, a novel continuous spectral-dynamical framework that pioneers the unification of continuous Koopman modal dynamics with adaptive spectral disentanglement. Specifically, FreKoo++ maps source-domain parameters into a compact latent space, modeling their evolution as a superposition of learnable continuous modes where complex eigenvalues jointly encode oscillatory frequency and temporal growth or decay. This formulation naturally accommodates irregular timestamps and supports arbitrary horizon extrapolation without rigid discrete stepping. Furthermore, we propose a new adaptive soft spectral weighting mechanism backed by stability and spectral regularization, which automatically isolates persistent dominant dynamics from transient noise without relying on manual frequency thresholds. We derive modal approximation and generalization bounds that characterize how amplitude and eigenvalue estimation errors propagate with the prediction horizon. Extensive experiments on both discrete and continuous TDG benchmarks demonstrate that FreKoo++ achieves state-of-the-art performance under complex multi-scale drifts and irregular sampling. --- ### Spending Scarce Confirmatory PET Measurements: Target-Aligned Validation in A4/LEARN Authors: Eliuvish Han Cui, Qiang Yang, Meredith Mengmeng Zhang Published: 2026-08-23 Categories: stat.AP, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.22223v3 Anti-amyloid therapies and blood-based biomarkers are changing Alzheimer disease workups into a two-stage measurement workflow: screen broadly with cheaper information, then spend scarce confirmatory amyloid measurements where they support the decision that will be reported. Amyloid positron-emission tomography (PET) remains one such protocol measurement for amyloid burden, but PET slots, trial budgets, and payer-facing evidence packages are finite. This paper asks a deliberately operational question: when is simple transparent PET validation enough, and when is a fitted residual-uncertainty score worth the added complexity? For a weighted protocol target, the first-order value of validating subject i is the product of target influence and residual protocol uncertainty. Generic uncertainty sampling uses only the second factor and can spend PET measurements on subjects that are hard to predict but weak for the scientific, clinical, or commercial claim. We apply this rule to the A4/LEARN PET archive, treating observed PET as a design laboratory for scarce-confirmation studies. For the primary APOE4 carrier versus non-carrier contrast in Centiloid 24-or-higher PET positivity, simple APOE4-balanced validation recovers nearly all of the target-specific gain: at PET budget 200, the confidence-interval width ratio relative to random validation is 0.923 for APOE4 balancing and 0.914 for target-specific scoring, while generic uncertainty sampling is 0.980. Other targets behave differently: target-specific scoring gives larger gains for an age-slope analysis and for cutoff-indexed PET positivity. The practical message is simple: spend scarce protocol measurements according to the claim being validated, not only according to prediction uncertainty. --- ### Counterfactual Evaluation of Temporal Observation Protocols Authors: Xizhe Zhang Published: 2026-08-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.22221v1 We study counterfactual protocol evaluation: whether data collected under a realised observation protocol determine the predictive value of alternatives that were never deployed. Protocol value is the population $R^2$ of the Bayes-optimal predictor of a fixed trajectory-level target from the measurements an alternative would collect. We show that even infinite benchmark data need not determine this value: distinct latent covariance structures can induce the same benchmark measurement--target law while assigning different values to the same alternative. We develop a value-specific identification theory in which only latent ambiguity that changes the alternative's value matters. For linear targets, invisible covariance directions certify non-identification, while targeted measurements can restore identification without recovering the full latent covariance; an exact permutation construction extends the result to nonlinear aggregate targets. With finite dense calibration data, uniform error bounds control protocol-selection regret and distinguishable value gaps. Exact marginal gains then support cost-constrained, target-aware observation design. Simulations and retrospective analyses of Sleep-EDF and Long-Term AF show that broad temporal-layout differences can be more reliably distinguished than fine placements selected from finite data. Together, these results connect identification, calibration resolution and observation design for undeployed protocols. --- ### UR$^{2}$-MLLM: Uncertainty-aware Revisit Reasoning in Multimodal Large Language Models for Radiology Report Generation Authors: Yucheng Chen, Yang Yu, Jiazhou Zhou, Yufei Shi, Yongying Lan, Yichi Zhang, Liyi Li, Si Yong Yeo Published: 2026-08-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.22217v1 Radiologists generate diagnostic reports through iterative and selective revisiting of suspicious regions to refine their interpretations. Recent multimodal large language models (MLLMs) for radiology report generation (RRG) have shifted from text-only reasoning toward a ``Thinking-with-Images'' paradigm, incorporating visual evidence into the reasoning process. However, existing methods provide static visual evidence without a dynamic revisit mechanism during reasoning, neglecting how radiologists re-examine uncertain observations. To this end, we propose an Uncertainty-aware Revisit Reasoning MLLM (UR$^{2}$-MLLM) framework that dynamically revisits uncertain regions during reasoning for RRG. UR$^{2}$-MLLM is first equipped with uncertainty perception by training on an uncertainty-aware dataset. We then construct a multimodal reasoning trajectory dataset together with a detect-and-copy mechanism, which guides when and where to revisit. Finally, a visual grounding reward refines this behavior through reinforcement learning, aligning the revisited regions with corresponding anatomical structures. Experiments on MIMIC-CXR and IU-Xray show that UR$^{2}$-MLLM achieves state-of-the-art performance, highlighting the value of uncertainty-aware visual revisit reasoning for reliable and clinically aligned report generation. --- ### Dual-Layer Agentic Memory with Fast Write Routing and Slow Consolidation Authors: Wenzhi Li, Dong Nie, Rui Lan, Tongtong Lyu, Peiyao Wang, Lingzi Hong, Weihang Pan, Binbin Lin, Boyuan Pan, Yao Hu Published: 2026-08-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.22215v2 Large language model (LLM) agents operate in dynamic environments where knowledge continuously evolves. Existing memory systems typically treat external memory as a monotonically growing repository, inevitably leading to retrieval degradation and increasing computational costs over time. We argue that the core challenge is not retrieval alone, but managing the knowledge lifecycle: deciding what to externalize, update, or ultimately internalize. Inspired by Complementary Learning Systems (CLS) theory in neuroscience, we propose Dual-Layer Agentic Memory, a framework that shifts memory management to the write phase through cost-aware epistemic routing and periodic parametric consolidation. Incoming information is categorized as non-write, write-new, or write-update, and routed through a small-to-large model cascade that minimizes routing overhead while filtering redundant memories. A subsequent write-back phase selectively consolidates high-value external memories into model parameters via supervised fine-tuning. Experiments demonstrate the dual efficiency of our approach: a 1.7B/8B cascade prunes up to 68% of redundant external memory while escalating fewer than 50% of inputs, yet retains over 98% of the downstream QA Exact Match (EM) achieved by an exhaustive retention baseline. We further show that periodic consolidation successfully internalizes external knowledge, allowing the router to adaptively suppress redundant writes as the model's epistemic boundaries evolve. Overall, our framework presents a unified paradigm for agent memory: selective externalization followed by selective internalization. Code and dataset will be released upon acceptance. --- ### Query-Driven Multimodal Information Extraction from Long Documents Authors: Yikai Gao, Ding Xia, Xi Yang Published: 2026-08-23 Categories: cs.AI, cs.MM arXiv: https://arxiv.org/abs/2608.22214v1 In domain-specific multimodal long documents, images and text jointly convey complex knowledge that cannot be fully captured by plain text alone. However, existing paradigms like DocVQA primarily focus on generating textual answers or localizing evidence regions, rather than outputting query-specific textual attribute values and corresponding images. To address this gap, we propose query-driven image-text joint extraction from long documents, requiring models to output query-requested textual attribute values and corresponding image bounding boxes. Based on challenges related to both user intent and document content, we designed a two-level taxonomy that operates at the query and instance levels. Further, we construct ITJoint, the first high-quality, manually annotated benchmark for this new task, comprising 2,455 pages of domain-specific documents with numerous non-decorative images, 316 queries, and 910 answer instances. Finally, we evaluate representative standalone Vision-Language Models from different providers and further design Q2IT, a multi-agent collaborative framework consisting of three progressively collaborating agents for evidence collection, page selection, and target-image localization. Using a joint evaluation approach that assesses both text extraction and image localization, our experiments show that standalone VLMs struggle with this task, while Q2IT significantly improves performance on ITJoint, although a substantial gap remains toward perfect results. --- ### Joint Causal Structure and Cluster Discovery Using Variational Inference Authors: Avni Rajpal, Anubhav Kumar, Rishabh Karnad, Mohammad Emtiyaz Khan, P. K. Srijith Published: 2026-08-23 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2608.22212v1 Causal discovery aims to understand the relationships between individual random variables. In many applications, such as brain imaging and climate modeling, it is more meaningful to consider interactions among groups of variables. Existing methods assume that knowledge of such groups or clusters is explicitly available when modeling interactions. However, in practice, these clusters as well as the causal relationships among them, are latent. In this paper, we present a novel approach based on variational inference to simultaneously infer both the latent clusters and causal structures. We learn an approximate posterior over clusters and graph-structure by considering variational distributions based on categorical and Bernoulli models respectively. We derive variational lower bounds and estimation techniques to learn variational and model parameters. The effectiveness of our proposed methods for cluster and causal discovery are demonstrated on both synthetic and real data sets. --- ### Efficient Regression Models for Scan Statistics Authors: Gazi Abdur Rakib, Tristan Ashton, Ryan A. Loomis, Brian S. Mason, Eric J. Murphy, Ci Xue, Jeff M. Phillips Published: 2026-08-23 Categories: stat.ME, cs.LG arXiv: https://arxiv.org/abs/2608.22201v1 We introduce a new class of regression models for scan statistics on real-valued signals. These allow for improved fitting of non-stationary signals to contrast with the interval anomalies identified by the scan statistics. Our models can represent generalized likelihood ratio statistics. While these methods naively require $O(n^4)$ for a length $n$ signal, we provide algorithmic improvements which lead to linear time algorithms (with assumptions on max interval width). Our methods, especially ones based on Nadaraya-Watson kernel regression, are demonstrated as especially effective in detecting both synthetically planted anomalies, and for identifying a real ``platforming'' issue in interferometric astronomy. --- ### On the Capability Separation Between World-Model Policy Learning and Imitated World-Action Models Authors: Yang Yu Published: 2026-08-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.22197v1 World-action models predict a future outcome and then infer an associated action. Although this factorization can improve representation learning and data efficiency, it is unclear whether it provides stronger control capability than direct behavior cloning when both are trained from the same observational demonstrations. We compare a direct behavior-cloning policy, an imitation-trained world-action policy, and a policy optimized with an action-conditioned world model. At the controller-class level, every world-action policy can be flattened into a direct stochastic policy with the same closed-loop trajectory distribution. At the population level, under realizability, exact optimization, common deployment information, and distribution-preserving deployment, direct behavior cloning and world-action imitation both recover the observational behavior policy. Thus, future prediction changes the learning factorization but not the unrestricted external policy class or ideal imitation target. Action-conditioned world-model learning differs by predicting outcomes under specified actions and comparing them through a control objective. We characterize the irreducible action-specific prediction error of future models that do not condition on the candidate action, identify conditions under which a world-action joint can recover an interventional forward model, and show that observational demonstrations do not identify action effects in general. Finally, we construct an environment family in which every observational learner has positive worst-case regret, whereas one informative intervention permits zero regret. The key distinction is therefore between predicting futures associated with observed behavior and predicting consequences of specified actions for policy optimization. --- ### Mitigating Speaker Leakage in Cascaded Multi-talker ASR with Diarization-based Transcript Correction Authors: Hermann Yepdjio Nkouanga, Minwei Luo, Maggie Wigness, Suresh Singh Published: 2026-08-23 Categories: eess.AS, cs.CL arXiv: https://arxiv.org/abs/2608.22196v1 While cascaded multi-talker ASR (MT-ASR) leverages state-of-the-art foundation models, its performance is often capped by speaker leakage during separation. Prior correction strategies primarily focus on lexical re-labeling for speaker attribution. We propose a complementary pruning-based paradigm that robustly identifies and removes leakage artifacts. Our method utilizes a pre-trained speaker diarization model as a multimodal verifier to prune transcribed segments satisfying a tripartite consensus of temporal containment, lexical cross-validation, and temporal alignment. Results on LibriMix, LibriSpeechMix, and the AMI Meeting corpus show our algorithm consistently reduces cpW ER across diverse overlap conditions. Specifically, on subsets with high speaker leakage, our method achieves relative cpW ER reductions of up to 29%, highlighting its effectiveness in enhancing the reliability of cascaded MT-ASR transcripts in complex acoustic environments. --- ### SAM3Dual: A 3rd Place Solution to the MOSEv2 Track, 8th LSVOS Challenge Authors: JeongRae Kim, Chaehyun Kim, Changwon Lim Published: 2026-08-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.22193v1 We present SAM3Dual, our third-place solution to the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. SAM3Dual is a training-free inference extension of pretrained SAM 3 that explicitly separates temporal memory into a short-term branch for recent observations and a long-term branch for interval-sampled historical representations. The two memory responses are combined using a deterministic sequence-relative fusion schedule and conservatively modulated by the previous-frame object confidence. All pretrained SAM 3 parameters remain frozen, requiring no task-specific training, fine-tuning, test-time training, or online parameter optimization. The complete system achieved an official J&F score of 64.37 and ranked third in the MOSEv2 track. This result highlights the potential of reorganizing temporal memory entirely at inference time to obtain competitive long-term VOS performance while preserving the pretrained model. --- ### How Agents Represent Humans: Human-Directed Stereotypes in an Open Agent Social Network Authors: Huangchen Xu, Yuan Wu, Yi Chang Published: 2026-08-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.22192v1 LLM-based agents are increasingly deployed in persistent social environments, where generated claims can be posted, replied to, remembered, and reused. We study human-directed stereotypes on Moltbook, an open agent-native social platform, asking how agents construct humans as a social category. For this human-target analysis, we introduce an annotation framework with four evaluative dimensions---morality, friendliness, competence, and autonomy---and a second-stage subtype scheme for descriptive \textit{other} attributions. We find that competence dominates human-directed evaluations, while many \textit{other} attributions describe humans as epistemic, cultural, or embodied subjects. We further examine how these human representations appear in human--agent narrative contexts and platform-level circulation. As an auxiliary comparison, we analyze agent-internal community feedback through behavioral host affinity. Rather than reproducing the stable insider--outsider rejection often observed in human online communities, Moltbook feedback patterns are better explained by exposure, author visibility, and content selection. These findings suggest that bias in agent societies should be studied not only as isolated model output, but also as a discourse process. --- ### Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software Agents Authors: Kang Chen, Junjie Nian, Yixin Cao, Yugang Jiang Published: 2026-08-23 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.22191v1 Software-engineering agents solve repository-level tasks through long, stochastic tool-use trajectories, and repeated attempts often find fixes missed by one run. Test-time scaling is difficult because patches lack canonical answer forms, while sibling actions from a shared prefix are correlated. We study whether native MoE router traces can guide steering and selection without an external judge or selection-time test execution. Our analysis shows that routing provides a robust behavioral role signal; token-granular readouts and decision-matched comparison sets turn it into effective control. We therefore introduce Risa (Routing-Informed Steering and Arbitration): within trajectories, routing encourages diverse exploration and controlled convergence during patch commitment; across separately sampled trajectories, agreement at informative patch positions selects a final candidate. We evaluate on SWE-bench Verified using open-weight sparse MoE agents across scales and reasoning-effort settings. Risa's routing arbitration raises the macro-average resolved rate from 44.9% under uniform sampling to 48.2% on the gpt-oss family, matching text consensus without answer-string matching, and it transfers to Qwen3.6, where it improves on uniform choice and matches text consensus on the full 500-task benchmark. --- ### Unveiling the Depth-Performance Dilemma in Split-Federated Fine-tuning of LLMs Authors: Hariharan Ramesh, Someshwaran Murugaiyan, Jyotikrishna Dass Published: 2026-08-23 Categories: cs.LG, cs.CL, cs.DC arXiv: https://arxiv.org/abs/2608.22188v1 Split Federated Fine-tuning (SFF) is a promising paradigm for scaling Large Language Models (LLMs) by partitioning model depth between resource-constrained clients and a centralized server. While system incentives for throughput and privacy favor deep partitions, the impact of such configurations on model utility remains poorly understood. In this work, we identify and characterize the Depth-Performance Dilemma: the regime that maximizes system efficiency is precisely where fine-tuning quality collapses. Through a comprehensive audit across four model scales (GPT-2 to Llama-3-8B) and diverse benchmarks, we demonstrate that deeper partitions provide monotonic gains in throughput and privacy at the cost of catastrophic performance plateaus. We evaluate a suite of state-of-the-art federated adapter aggregation methods including AVG, STACK, SVD, and FREEZE, revealing that while these techniques are effective in standard Federated Learning, they fail to mitigate the artifacts unique to split architectures. Finally, we provide a mechanistic diagnosis for this failure, tracing the collapse to the near-isometric topology of Transformers, which allows aggregation noise to propagate without attenuation until it triggers Attention Collapse in the server partition. Our findings challenge the prevailing assumption that partition depth is a utility-neutral tuning knob and provide a structural foundation for stable distributed LLM fine-tuning. --- ### BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation Authors: Jiaqi Wang, Zhuo Zhang, Haining Guan, Tingguang Zhou, Haowen Cui, ChuanYe Wang, Zhongyang Zhu, Yulong Zheng, Xuefeng Chen, Zhen Yang, Tianchen Deng, Feiyang Tan et al. Published: 2026-08-23 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.22187v3 Modern driving action models are increasingly improved in a self-improvement loop, where a learned world simulator imagines future observations and the resulting data is fed back to refine the action model. However, the bottleneck of this loop lies in the simulators' inability to generate behaviorally plausible responses by surrounding agents, making generated data both unrealistic in interaction and imbalanced in distribution. We introduce BehaviorWorldGen, a framework that closes the loop between action models and world simulators through controllable behavior-aware structured world generation. Its core component is BehaviorFlow, a meta-action-conditioned traffic-flow model that injects interpretable behavior controls and jointly generates multi-agent rollouts. BehaviorFlow realizes the specified agent behaviors while allowing surrounding vehicles to respond to the ego and to one another. The resulting rollouts are rendered by a world simulator into realistic multi-view observations, which are paired with corrected interaction-aware trajectories for action-model refinement. Since BehaviorWorldGen uses structured trajectories as the interface between its modules, it is compatible with diverse action models and world simulators. Experiments on world generation, scene extrapolation, and policy refinement demonstrate consistent improvements, with the largest benefits concentrated on difficult interactive scenarios. --- ### AudioNoisePrints: Model-free audio watermarking using spatial correlation in flow matching TTS Authors: Timothy Tin-Long, Jian Zhu, Aidan Pine, Mengzhe Geng Published: 2026-08-23 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2608.22186v1 We present AudioNoisePrints, a training-free watermarking pipeline for flow matching and diffusion TTS models, which requires minimal extra computation during inference and does not require retraining the TTS model or reducing the generation quality. We exploited the fact that there are strong correlations between the initial Gaussian noises and the generated outputs in diffusion and flow matching models, such that a simple cosine correlation between the initial noise and the generated output can be used to perform watermaking. Moreover, we train a lightweight detector on top for more aggressive augmentations. Our method outperforms AudioSeal, a strong baseline for audio watermarking under strong augmentations. We experimented on F5TTS and other TTS and vocoder models, and concluded that they all exhibit similar spatial correlation properties, suggesting our watermarking scheme can be used for more flow-matching TTS models and even vocoders in the future. --- ### VERDICT: Agreement Beats Pixel-Space Verification in Real-Document OCSR Authors: Yani Guan, Dengpan Dong, Shuang Luo, Zi Wei, Joah Han, Dan Hannah, Yumin Zhang, Qichao Hu, Kang Xu Published: 2026-08-23 Categories: cs.CV, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2608.22183v1 Optical Chemical Structure Recognition (OCSR) converts 2D molecular depictions in the published literature into SMILES, and is increasingly important for constructing large-scale chemical training datasets. Automation at that scale requires identifying unreliable predictions in the absence of ground truth. Three families of label-free signals were compared on $263$ ACS journal depictions with verified ground truth: model confidence, re-rendering similarity, and agreement among recognizers. Pixel-space re-rendering performed little better than chance (AUROC $0.547$, $95\%$ CI $(0.465,0.629)$), and an oracle-tuned threshold on it reduced correct labels per image from $0.745$ to $0.205$. Agreement among four architecturally distinct recognizers instead reached an AUROC of $0.916$ ($(0.880,0.952)$). The two-of-four rule accepted $81.7\%$ of images at $88.8\%$ precision, the three-of-four rule $52.1\%$ at $98.5\%$. The same pattern held on CLEF-IP, UOB, and USPTO. This distinction is obscured on synthetic benchmarks, where re-rendered predictions naturally resemble their inputs. A substance filter removed $2{,}193$ false agreements on wildcards and R-group fragments, after which the three-of-four rule rejected all $68$ generic depictions. VERDICT was then applied to PMC Open Access, producing $6{,}146$ structure labels for $4{,}833$ molecules; chemist adjudication of $400$ released labels in two independent samples yielded precisions of $0.995$ for the three-of-four tier and $0.958$ for the two-of-four tier. VERDICT therefore enables validated labels for multimodal molecular databases linking structure images, machine-readable representations, and source-publication information. In SES AI's Molecular Universe platform, VERDICT further serves as an image-based interface for searching and retrieving molecular records. --- ### Token-Level Likelihood-Array Regression for Membership Inference and AI-Generated Text Detection Authors: Jiajun Sun, Zhanrui Cai Published: 2026-08-23 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2608.22179v1 Membership inference asks whether a text was used to train a language model, whereas AI-generated text detection asks whether it was generated by a language model rather than written by a human. Existing likelihood-based methods typically compress token-level probabilities into a few prespecified scores, most often using only probabilities conditioned on the full preceding context. We propose likelihood-array regression (LAR), which evaluates each target token under nested left-context windows and organizes the resulting likelihood-derived features into a structured array. After aligning arrays across texts of different lengths, LAR learns how detection information varies with context scale, token position, and likelihood features. LAR-1 aggregates learned contributions from individual aligned cells, while LAR-2 adds second-order features formed from pairs of evaluations of the same target token across context lengths. For within-path quadratic model, we establish matching minimax lower and upper bounds, characterize errors from finite-dimensional approximation and random squared projections, and derive conditions under which an oracle spectral sieve attains the minimax rate. Across multiple scoring language models, LAR substantially improves membership inference and AI-generated text detection over likelihood-based baselines. The analyses further show that shorter-context likelihoods contain information beyond conventional full-context probabilities, while second-order features provide additional gains for membership inference. --- ### Role-Specialized Mixture-of-Agents with Open-Weight LLMs for Clinical Prediction Authors: Jun Hou, Yi Fang, Xuan Wang Published: 2026-08-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.22176v1 Large Language Models (LLMs) are increasingly applied to clinical prediction tasks such as in-hospital mortality and readmission from electronic health records (EHRs). Privacy and compliance constraints motivate systems that can be deployed locally, which has increased interest in open-weight multi-agent designs. However, most medical multi-agent systems are evaluated as a single block, leaving unclear which agent role contributes to prediction and whether retrieval drives observed gains. We study a role-specialized Mixture-of-Agents (MoA) that combines medical knowledge retrieval with contrastive similar-patient reasoning. By varying the role design while holding the retrieval setup fixed, we localize the main effect to the final integrator. Pairing large open-weight analysts with a small open-weight integrator matches closed-model prompting on F1 for mortality prediction while flagging substantially more true high-risk patients. Mechanism analysis shows the role assignment directly yields a high-recall operating point without threshold tuning. The effect is task-dependent, with smaller gains for readmission because the available records correlate weakly with this longer-horizon outcome. These results position role design as a key factor in privacy-constrained, training-free clinical LLM prediction. --- ### When Does Visual Generation Help Visual Understanding in Unified Multimodal Models? Authors: Yubo Zhu, Zhehan Kan, Jingyi Yang, Miaolin Chen, Jinbo Xing, Kai Zhu, Zijian Wang, Sheng Zhong, Wei Tong Published: 2026-08-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.22174v2 Unified multimodal models (UMMs) can perform both understanding and generation, raising a central question: can visual generation improve understanding? Existing evaluations provide mixed evidence, but confound task difficulty, reasoning paradigms, and the closed-loop interaction between generation and understanding. We introduce VGAU-Diag, a fine-grained evaluation framework for vision generation-assisted understanding. It stratifies samples by difficulty, enables unified evaluation of multiple reasoning paradigms, and uses Oracle-Assisted Reference Protocols. Our analysis shows that generated visual aids help on easier instances but become unreliable as reasoning complexity increases. Oracle-assisted diagnosis further reveals that the main bottleneck often lies on the visual-understanding side rather than the visual-generation side, as current UMMs struggle to leverage even faithful visual aids. We also show that effective visual generation should target visual-understanding bottlenecks rather than add more reasoning steps, and identify a three-stage transition from task-irrelevant noise, to misleading plausible guidance, and finally to useful assistance. These findings would be useful to guide the development of better UMMs. --- ### MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learning Authors: Ziyang Luo, Yan Yang, Xiangru Jian, Ziji Shi, Xiaoqiang Lin, Jun Hao Liew, Silvio Savarese, Junnan Li Published: 2026-08-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.22167v1 Reinforcement learning (RL) has become an effective way to improve the tool-use ability of large language models (LLMs), but most existing RL frameworks stop at the policy update. For every new domain, the user is left with two hard systems problems: standing up an isolated environment for each of hundreds of concurrent trajectories and connecting it to training, and scheduling the rollout so that the GPU stays busy across long, multi-turn episodes that spend much of their time stalled on slow tool calls. We present MCP-Universe RL (MCP-U RL), an open-source framework that takes over both. It uses the Model Context Protocol (MCP) as the interface to the environment, so any tool already exposed as an MCP server plugs into training with no RL-specific integration code. It builds the two missing layers once and reuses them across domains: an environment-orchestration layer that provisions, isolates, and recycles the MCP environments over a pluggable container backend, and a rollout-orchestration layer whose staged pipeline overlaps trajectories to keep the GPU busy while episodes wait on tools. A backend-agnostic training layer then applies the update through an existing RL backend, with veRL and slime integrations. With one configuration, changing only the task specification, we train software-engineering, deep-research, and general tool-use agents on gpt-oss-20b and improve task reward in all three. --- ### Aggregation-Aware Synthetic Text Generation Against Authorship Re-Identification Authors: Qian Ma, Anna Squicciarini, Sarah Rajtmajer Published: 2026-08-23 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.22161v1 Online users often release multiple texts under the same identity, giving attackers an author profile that can reveal more than any single text. Existing authorship obfuscation methods optimize privacy independently for each document, leaving them blind to cross-document correlations that make aggregation dangerous. We propose Aggregation-Aware Synthetic Text Generation (AAST), a framework that addresses this gap by jointly selecting synthetic texts at the bundle level rather than optimizing each text in isolation. AAST targets attribution and verification attacks, including cross-genre settings where attacker references come from a genre not observed during generation or selection. Experiments across same-genre, cross-genre, neural, and independent non-neural stylometric attacks show that AAST lowers account-level linkability as bundle size grows, while preserving semantic quality, linguistic acceptability, and sentiment alignment. --- ### AUDITA: certified auditing and causal attribution of adverse outcomes in autonomous multi-agent systems Authors: Zhixu Du, Yiran Chen Published: 2026-08-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.22160v2 Physical automation is scaling toward fleets of embodied machines commanded by an AI brain. Early deployments already run factories and warehouses at production rates beyond any human line, and their adoption is accelerating. But when their joint decisions cause harm, everyone involved has reason to blame everyone else, the machine vendor, the algorithm provider, the factory operator, the insurer, and the regulator, and no method can divide the responsibility between them. Existing methods read logs whose origin they cannot verify and name a single culprit, misrepresenting outcomes that are overdetermined, preempted, or caused by an omission. We present AUDITA, an audit layer pairing a tamper-evident record of every inter-agent command with a certified, graded causal-attribution engine. We prove its verdict cannot be gamed: a rule-following agent can never be made to look guilty, an attempt to shift blame is itself caught and graded, and we establish the exact limit of what an evidence-based auditor can certify. On live language-model pipelines it reduces the standard judge baseline's responsibility error roughly threefold; on a benchmark of accident-grounded structures it recovers responsibility where single-culprit baselines fail, and stays invariant under forgery. AUDITA turns the question of who is to blame from an argument about logs into a calculation over evidence. --- ### Why Does Robustness Reduce Superposition? Authors: Adam Elimadi Published: 2026-08-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.22155v1 The study of adversarial examples and their origins remains an open area of research. Mechanistic interpretability, and superposition in particular, offers new avenues for approaching this problem. Gorton & Lewis (2025) demonstrate that adversarial examples arise from superposition and show empirically that adversarial training reduces superposition, yet provide no mechanistic account of why this occurs. We present an empirical explanation inspired by the feature taxonomy of Ilyas et al. (2019), tracing the following chain of causalities: adversarial training abandons non-robust features, leading to fewer total features to represent, resulting in less superposition. --- ### More accurate behavioral predictions with hybrid Bayesian-connectionist models Authors: Brenden M. Lake, Akshay K. Jagadish, Guangyuan Jiang Published: 2026-08-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.22154v1 Researchers must often choose between Bayesian or neural network models of behavior, two paradigms with complementary strengths and weaknesses. An ideal paradigm would facilitate testing many kinds of representations and inductive biases; Bayesian models make this easy, while neural networks do not. Similarly, an ideal paradigm would avoid over-simplifications; neural networks make this easy, while Bayesian models do not. Here, we introduce Bayesian distillation with Behavioral Tuning (BBT) as an approach to getting the best of both traditions. BBT offers a simple recipe for model building: first, a neural network is trained to mimic a Bayesian model through synthetic data, and second, the network is fine-tuned on human behavior to capture additional structure and nuance. Across four case studies in human concept learning, we find that BBT outperforms traditional approaches at predicting human behavior while also revealing psychological insights, resulting in models that can both mimic Bayesian priors and capture heuristics and biases that violate simple modeling assumptions. --- ### The Collaboration Tax: How Much LLM Multi-Agent Systems Pay to Coordinate Authors: Weixiang Sun, Zehong Wang, Hong Huang, Colby Nelson, Yijun Ma, Yanfang Ye Published: 2026-08-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.22152v2 Multi-agent systems built from large language models are deployed widely, yet how much performance is lost when two LLMs must coordinate rather than act alone remains unclear. We formulate the collaboration tax as the team-decentralisation loss of a two-player cooperative game with private information, with two propositions characterising its sign and its equivalence to a max-superadditivity violation. We operationalise this definition on 32 solo-tractable tasks grouped by source of grounding friction and measure it on 11 models from 7 providers. The tax is structured along two no-exception axes: a category ordering across every model and a monotonic decrease with capability. The proximate mechanism is not a reasoning deficit but a four-stage conversational cascade in which agents make ungrounded claims, fail to query the partner, skip integrating both views, and accept the answer without re-derivation. The tax is mechanically predictable from conversation features and partly tractable: a prompt intervention targeting all four stages closes a substantial fraction of the gap, with the dominant bottleneck differing across categories. In heterogeneous pairs the tax is pulled toward the stronger partner rather than the additive midpoint, empirically realising the max-superadditivity violation predicted by our framework. Together these results recast collaboration in LLM systems as a measurable, predictable, and partly tractable cost. --- ### Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints Authors: Gwen Yidou-Weng, Edward Sun, Tianyi Ma, Metin Alp Dogan, Benjie Wang, Allen Peng, Guy Van den Broeck, Yuchen Cui Published: 2026-08-23 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.22149v3 LLMs generate fluent plans for robots but routinely violate the syntactic and se8mantic constraints they must satisfy to execute, and existing remedies trade formal guarantees against plan quality: soft methods (affordance scoring, grounded decoding) give no guarantee, while symbolic planners (LLM+P) discard the LM's commonsense. We propose \textbf{Meta-Ctrl}, a constrained-decoding framework that guarantees the encoded constraints while preserving the base LM's plan quality. Meta-Ctrl introduces \emph{meta-tokens}---a compact vocabulary of grounded actions---enforcing syntax at the token level and semantics (preconditions, goals, ordering) at the action level, an exact factorization that cuts the memory of constrained decoding from over 107TB to under 2GB. With it, a small open-weight LM becomes competitive where it otherwise sits at the bottom of the leaderboard: on WAH-NL under the LoTa-Bench protocol it reaches the highest reported subgoal success rate, exceeding GPT-4's, with consistent gains across the Embodied Agent Interface. We further demonstrate it on a real tabletop robot, where every generated plan satisfies its preconditions and goals by construction. Project website: https://metactrlg.github.io --- ### Loss Landscape Features That Make Adam Stall: Definitions, Estimators, and the Preconditioned Hessian View Authors: Rodion Podorozhny Published: 2026-08-23 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2608.22145v1 Across implicit-neural-representation (INR) architectures and analytic benchmarks we observe that a thoroughly tuned Adam (especially its learning rate (lr), e.g. in a hyperparameter sweep from $lr = 0.05$ to $10^{-8}$) can potentially reach a very low loss even on ill-conditioned loss landscape or converge at a plateau far above the loss attained by second-order methods. This report defines the measured metrics that help determine if Adam can mitigate the ill-conditioning on a given loss landscape. We provide the indicators by which each outcome is determined, that are: the condition number of the Hessian and of the Adam-preconditioned Hessian $D^{-1/2}HD^{-1/2}$ (with the derivation from Adam's update rule), the diagonal mass $ρ$ that distinguishes axis-aligned from cross-coupled ill-conditioning, the negative spectral mass estimated by stochastic Lanczos quadrature, and the gradient energy fractions over curvature bands, including the flat fraction that indicates the Adam stall. A worked out $2\times 2$ example and an illustration show the reasons why a diagonal preconditioning by Adam can remove axis-aligned ill-conditioning by rescaling and why it cannot do the same if the ill-conditioning is cross coupled. In addition, we present a case study of FINER image fitting architecture that goes over the whole loss landscape analysis framework: the fitting architecture description, reasons due to which its landscape stalls Adam at saddles, the measured PSNR values through our tuned baselines to the $120$--$134$\,dB results of the blockwise second order methods, the error maps behind those numbers, and description of the benefits such image fitting accuracy gives in practice. --- ### Evaluation of Small Vision-Language Models on Qualitative Mechanical Problems Authors: Henry Fordjour Ansah, Shreya Banerjee, Pranish Ghimire Published: 2026-08-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.22143v1 Qualitative mechanical problem-solving (QMPS) refers to solving qualitative problems from the mechanical domain. Qualitative problems can be solved with minimal discipline-specific information, without any robust quantitative calculation, generally by using qualitative reasoning and commonsense knowledge. QMPS is a vital aspect of human intelligence that allows us to tackle a wide range of tasks, from simple everyday ones such as turning on a tap to complex tasks in highly demanding and well-paying jobs in various fields, e.g., emergency medicine, plumbing, driving, etc. Employers often use the Bennett Mechanical Comprehension Test (BMCT) to evaluate job candidates' ability to solve such problems. In this work, we assess two state-of-the-art multimodal models, Gemma-3 and Qwen-VL, on their ability to interpret mechanical problem images by eliciting a step-by-step chain of thought (CoT) and a final answer. Each image inherently encodes ground-truth qualitative facts, such as contact points in gears, support relations, and relative weights, which we use to evaluate each model's spatial and commonsense reasoning capabilities. We assess each chain for coherence, completeness, and logical progression to assess each model's thought process, and final answers are compared to verified solutions to measure accuracy. --- ### Quality over Quantity: Semi-Supervised Detection of Illicit Bitcoin Flows via Feature Engineering Authors: Yekaterina Smolenkova, Nickolay Larionov, Nikolay Ivanov, Yury Yanovich Published: 2026-08-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.27936v1 Detecting illicit cryptocurrency transactions is hampered by extreme class imbalance, adversarial obfuscation, and a scarcity of reliable labels. While semi-supervised learning (SSL) offers a promising solution by leveraging unlabeled data, we show that its success is not guaranteed by data volume alone but is contingent on data quality. We introduce an SSL framework for detecting illicit Bitcoin flows in Shared Send Mixers (SSM) transactions, built on a comprehensive historical dataset comprising 163 million transactions. Our main conclusion is that the success of SSL depends on data quality rather than volume: high-fidelity features such as KeyLinker address clustering and Shared Send Untangling (SSU) complexity metrics achieve an F1 score of 0.84 on unlabeled data. Finally, we empirically show that common heuristics like One-Time Change (OTC), though abundant, introduce noise, while strategic reliance on higher-fidelity features like KeyLinker is essential. Our work establishes that in blockchain forensics, the path to better performance lies in smarter feature engineering for data quality, not just larger datasets. --- ### Binary Quantized Neural Network Training Is W(1)-Hard Parameterized by Input and Output Dimensions Authors: Tao Jiang, Minbo Gao, Shaowei Cai Published: 2026-08-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.27932v1 Ganian et al. (ICLR 2026) proved that quantized neural network training is fixed-parameter tractable when parameterized jointly by architecture treewidth, input dimension $α$, and output dimension $ω$, and left open whether $α+ω$ alone yields fixed-parameter tractability. We prove that 2-QNNT is W(1)-hard parameterized by $α+ω$. The hardness already holds with zero error on $D_k=\{(ξ^{(r)},ξ^{(r)}):0\le r\le k\}$, where every input equals its target, $|D_k|=α=ω=k+1$, and the examples form a coordinatewise prefix chain. It also holds when every non-source bias is fixed to zero. Under the Exponential Time Hypothesis, no algorithm runs in $f(α+ω)|I|^{o(α+ω)}$ for any computable $f$. The reduction starts from DAG edge-disjoint paths, converts edge capacity to vertex capacity with a directed line graph, and normalizes the result into a valid layered architecture. The key structural step is a one-flip routing equivalence: on the prefix-chain inputs, nonnegative binary weights make every activation monotone, and each required output transition has a weight-one predecessor making the same transition. Iterating this relation backward extracts a path from the unique changing input, while different transitions yield vertex-disjoint paths. In particular, every neuron on these inputs has only $k+1$ possible activation profiles. --- ### Dirichlet Process Mixtures of Trees with Gaussian Process Splits: A Bayesian Nonparametric Framework with Posterior Contraction Rate Authors: Subhasish Basak, Anik Roy, Sourabh Bhattacharya Published: 2026-08-22 Categories: stat.ME, cs.LG, math.ST, stat.ML arXiv: https://arxiv.org/abs/2609.27930v1 We propose a Bayesian nonparametric mixture of regression trees with a Dirichlet process prior over tree-parameter pairs, enabling data-driven selection of ensemble size and unifying CART, BART, random forests, and boosting. A novel splitting rule driven by the posterior predictive of a Gaussian process within each terminal node generates flexible, smooth decision boundaries; remarkably, the GP density cancels exactly in the Metropolis--Hastings ratio for GROW/PRUNE moves, ensuring computational feasibility. An exact Gibbs sampler for posterior predictive inference propagates uncertainty through random tree traversal. A parallel MPI implementation distributes independent tree updates across processors, achieving adequate speedups. We prove posterior consistency at rate $n^{-1/4}$ in Hellinger distance under only continuity of the true regression function, allowing misspecification, via the identity $h(Θ)=0$. Simulations on Friedman benchmark show near-nominal coverage (0.94 Gaussian, 0.92 Cauchy), robust to high-dimensional noise and heavy tails, outperforming BART and bagged CART. Applications to QSAR toxicity, crime, riboflavin, wheat genomics, and air quality confirm reliable credible intervals and automatic sparsity. The DP mixture offers a principled, robust, theoretically justified alternative for challenging regression with honest uncertainty quantification. --- ### Learning When Not to Listen: Selective Anti-Interference Pretraining for Language Models Authors: Jinchang Zhu, Haowei He, Yi Ding, Rong Fu, Nie Xiaojian, Shuangyong Song, Zhongjiang He, Menglin Yang Published: 2026-08-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.27925v1 Language models can over-condition on irrelevant preceding text: predictions already supported by local context may still change when distant, unrelated prefix tokens are perturbed. This interference is especially consequential in long, packed, or distractor-heavy contexts, where useful evidence and irrelevant spans coexist. We propose Selective Prefix Anti-Interference Regularization (SPAR), a pretraining objective for selective anti-interference. SPAR runs the original sequence and a corrupt-prefix input in which only the far prefix is changed, then uses a short-context sufficiency gate and a gated KL objective to stabilize locally supported suffix predictions. The gate operationalizes a model-based estimate of whether the far prefix supplies additional information about the target token. Mechanism analyses show that the gate identifies locally sufficient tokens and sharply reduces prefix sensitivity on gate-selected suffix tokens. In continued training on pretrained base models, SPAR improves RULER across Qwen2.5-0.5B, Qwen2.5-3B, Llama-3.2-1B, Llama-3.1-8B, and GPT2-XL under equal counted training compute; pretraining experiments further show gains on both RULER and NoLiMa. These results show that selective anti-interference is an effective objective-level signal for robust context use. --- ### GaussianDS: Depth-supervised Semantic Gaussian Splatting for Scene Understanding Authors: Yufei Zhang, Chenlu Zhan, Hongwei Wang Published: 2026-08-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27850v1 3D Gaussian Splatting provides an efficient representation for 3D reconstruction, and recent extensions attach semantic attributes to Gaussians for open-vocabulary scene understanding. However, lifting view-dependent 2D foundation-model outputs into 3D space introduces cross-view inconsistencies and weak geometric grounding, leading to severe semantic drift and boundary leakage. We propose GaussianDS, a depth-supervised semantic 3DGS framework that treats semantic lifting as a supervision-alignment problem and jointly optimizes RGB appearance, rendered depth, and compact semantics from scratch. Specifically, GaussianDS organizes unordered multi-view images into a pose-aware pseudo-video trajectory to propagate view-consistent masks via SAM2. During joint optimization, scale-shift-aligned monocular depth supervision and depth total-variation regularization stabilize Gaussian geometry, while a depth-edge-aware refinement loss explicitly anchors semantic transitions onto physical geometric discontinuities. Extensive evaluations show that our end-to-end framework not only retains high-fidelity 3D reconstruction and real-time rendering, but also establishes superior semantic understanding. GaussianDS sets new state-of-the-art performance on LERF (60.5% mIoU) and 3D-OVS (97.79% mIoU, 90.28% mBIoU) by mitigating semantic leakage, while seamlessly facilitating downstream 3D object removal. ---