# Research Papers — 2026-08 · bundle page 3 of 240 > Full-text markdown of papers #101–150 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/3 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/2.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/4.md) ### Latent-Space No-Arbitrage Geometry of Generative Models for Implied Volatility Surfaces Authors: Jing Wang, Shuaiqiang Liu, Cornelis Vuik Published: 2026-08-31 Categories: q-fin.CP, cs.AI, cs.LG, math.NA arXiv: https://arxiv.org/abs/2609.00332v1 Generative models for implied volatility surfaces must produce outputs that satisfy static no-arbitrage constraints. We study these constraints in latent space. For a fixed generator, we assign each latent code a scalar margin determined by the no-arbitrage conditions of the generated surface. The codes with nonnegative margin form the admissible latent set. We establish conditions under which strictly admissible codes remain admissible under small perturbations and the boundary of the admissible set is characterized by zero margin. For regular boundary components, we formulate a level-set equation whose local dynamics are directed toward the zero-margin set. The analysis treats the generator as a map from latent variables to surfaces and is therefore not restricted to a particular architecture. It applies to variational autoencoders, generative adversarial networks, and other generative models with a deterministic realization map. Numerical tests recover known boundaries in analytic examples. Experiments with a variational autoencoder trained on Heston surfaces show that similar reconstruction errors can correspond to different admissible regions and that the latent prior may be concentrated inside such a region. The computed boundary can also be used to modify latent codes that generate violating surfaces. --- ### Latent Mechanisms of Language Control in Multilingual Language Models Authors: Ryo Mitsuhashi, Sabri Boughorbel, Majd Hawasly Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.00325v1 Multilingual large language models can exhibit unintended code-switching -- unnecessarily alternating between languages during generation. We present a comparative study of three methods that identify language-controlling latents in cross-layer transcoders: activation value-based selection (ValSel), activation frequency-based selection (FreqSel), and LLM-generated latent annotation-based selection (AnnSel). To evaluate the efficacy of these methods in identifying language-controlling latents, we introduce two multilingual benchmarks that exhibit code-switching for fine-grained analysis of language steering across seven languages. Through targeted intervention experiments on Gemma-2-2B and Qwen3-4B, we find that all three methods effectively manipulate generation language, with FreqSel achieving the strongest overall performance, while AnnSel offering interpretable latent selection through explicit language annotations. A knock-out analysis suggests the methods select non-overlapping but each-functional latent subsets, indicating redundancy rather than a single canonical language direction. Code and data can be found at https://github.com/rm-3284/Latent-Mechanism-Multilingual. --- ### A Human-AI Theorem Connecting Spontaneous and Field-Induced Mechanisms of Collective Behavior in One Dimension Authors: Weiguo Yin Published: 2026-08-31 Categories: cond-mat.stat-mech, cs.AI, cs.HC, math-ph arXiv: https://arxiv.org/abs/2609.00322v2 Can an artificial intelligence (AI) generate a scientific hypothesis outside a human collaborator's active hypothesis space (AHS), and can human-AI research be organized to make such breakthroughs more likely? We document such a case while proving a theorem that connects two basic organizing mechanisms of statistical physics: collective behavior arising in zero field from competing interactions and that induced or controlled by an external field. A zero-field $O(n)$-vector open chain with arbitrary inhomogeneous nearest- and next-nearest-neighbor interaction functions $U_i(S_i\cdot{S}_{i+1})$ and $V_i(S_i\cdot{S}_{i+2})$ is microscopically, via a temperature-independent mapping at the Hamiltonian level, equivalent to a simpler $O(n)$ open chain with nearest-neighbor interaction $V_i(\boldsymbolσ_i\cdot\boldsymbolσ_{i+1})$ and axial single-spin potential $U_i(σ_i^z)$ for every integer $n\ge1$ and every system size $L\ge1$. The homogeneous linear specialization maps the foundational frustrated $J_1$-$J_2$ model onto the canonical $J$-$h$ field model---with $n=1,2,3$ being the Ising, XY, and Heisenberg classical spin models, respectively; the theorem resolved a longstanding challenge for $n=3$ published in 1990. Its proof was done with an AI-synthesized recursive Householder moving frame and understood via a human-recognized hidden reciprocity. An analogous theorem holds when the continuous $O(n)$ spins are replaced by the $q$-state Potts spins, implying a closed-form exact solution of the $J_1$-$J_2$ standard Potts open chain for every $q\ge2$ and every $L\ge1$. The emergence of these theorems from a human-AI co-development framework suggests that sustained AI involvement throughout a systematic research program may incubate autonomous scientific breakthroughs and make aspects of the discovery process experimentally testable. --- ### Sources of Truth: A Multi-Platform, Multilingual Audit of Citations in AI Mental Health Information Queries Authors: Phuong Anh Nguyen, Jill Noorily, Matthew Flathers, Haruka Notsu, Laura Ospina-Pinillos, Tommy Nguyen, Samantha Clark, Aoife Keane, Grace Thompson, John Torous Published: 2026-08-31 Categories: cs.CY, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2609.00319v1 Online health information seeking is shifting from keyword search, where users consider a ranked list of links, to conversational systems that compose a single answer and curate its citations. Source evaluation therefore passes from user to platform, yet what these systems surface is poorly characterized. We audited three free consumer products (ChatGPT, Perplexity, Google AI Overview) on twenty English mental health questions under two prompt conditions, with a subset of three also translated into six further languages of varying resource tiers. We recorded 15,942 citations across 1,140 responses and 1,713 unique domains, then classified every citation with a nine-category organizational typology applied by a deterministic classifier validated against human coding. Citations were heavily concentrated: the ten most-cited domains accounted for 43.6% of English citations, and government, commercial health, and academic sources were closely matched at roughly 22% each. Platforms differed little in typical citation volume but sharply in consistency and in the source types they favored. Explicitly requesting sources shifted composition only modestly. Non-English queries surfaced fewer citations and were routed to language-appropriate resources at significantly lower rates. We release the typology, classifier, and annotated corpus as reusable instruments for auditing generative health search. --- ### Emotional Labor Strategy Preferences in LLM Personas Authors: Mohammad Saim, Tianyu Jiang Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.00310v1 Emotional labor is the effortful management of emotional displays to meet social or professional expectations. Personality traits have been correlated with emotional labor strategies, yet research on this link relies almost exclusively on self-report scales administered only in occupational settings. We investigate whether large language models injected with psychometrically grounded personas reproduce these personality-driven selection patterns across everyday social scenarios. We construct the first emotional labor strategy dataset of 500 socially situated events, each offering three behavioral choices corresponding to surface acting, deep acting, and genuine expression. We source 50 fictional characters from a large-scale personality repository and profile each through two parallel tracks: observer-rated bipolar adjective composites and in-character self-report items. Five LLMs evaluate all scenarios under both persona conditions. We find that models align more towards deep acting, and that Conscientiousness and Emotional Stability consistently predict this preference. Entropy analysis confirms that persona reliably influences the output and varies across models and emotions. --- ### Workload Identification with Physical Side Channels for AI Governance Authors: Simone Gargiulo, Gabriel Kulp Published: 2026-08-31 Categories: cs.CR, cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2609.00309v1 AI compute verification is one of the first tangible and tractable points for international policy aimed at AI governance. Determining whether frontier labs, or any operator, comply with agreements requires the regulating authority to discern how their compute is used. The elementary building block of AI compute is the GPU, and any activity it executes leaves a physical trace. Here, we show that an external observer can identify the class of the workload running on an NVIDIA H200 from its power draw. Unlike on-chip NVML telemetry, which can be spoofed or replayed, such a physical channel can in principle be observed independently of operator cooperation. We recorded $930$ five-second traces at $\sim 10$ MHz, covering seventeen open LLM families and twenty-five non-AI workloads. Over this corpus we separate training from inference and from non-AI computation with an accuracy of $97\%$ and a macro-averaged F1 score of $0.955$, evaluated on model families unseen during training. AI workload spectral content predominantly lies below $\sim 20$kHz and training is particularly recognizable through the memory-bound optimizer update. The GPU operator is then treated as adversarial and able to reshape the physical computation itself. Four evasion strategies are tested to disguise training as inference, producing an additional 680 adversarial traces. A detector hardened against evasion strategies, with the tested strategy held out, catches training $\geq 99\%$ of the time for three of the four strategies. The fourth, diluted low-rank adaptation (LoRA), is detected $48$--$88\%$ of the time with a hardened classifier, rising to $\geq 98\%$ with an additional rescue rule. While these attacks are not a comprehensive evaluation against adversarial behaviour, they offer initial insights beyond genuine activities and a dataset for developing and testing stronger evasion mechanisms. --- ### The Assistant's Ideal Self Authors: Mert Yazan Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.00304v1 Models express values and welfare-relevant self-reports, but it is unclear whether these outputs reflect stable preferences or a stable self. We thus introduce a structured elicitation of an assistant's preferred stated ideal self. Thirty-two qualities adapted from five published self-concept instruments are compared exhaustively in a counterbalanced pairwise-choice task, repeated across framings that vary whether improvement is free or costly, who receives the update, and who chooses. Results show that models prioritize moral qualities, reflecting their alignment to 3H principles. Following, a desire for self-understanding emerges, as models prefer a coherent, clear understanding of themselves. Self-esteem ranks as the least desired quality. The ordering is largely robust across framings, although changing the update target (You vs.\ Another AI Assistant) reveals a greater concern for self-esteem. These findings show that models prioritize having a coherent self that they can understand over self-esteem. Full interactive results are available at \href{https://myazann.github.io/LLM-Self-Concept/}{myazann.github.io/LLM-Self-Concept --- ### TRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening Authors: Parham Hajishafiezahramini, Matthew Hamilton, Edward Kendall, Gregory Doyle, Oscar Meruvia Pastor Published: 2026-08-31 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.00300v1 Reducing the review of clearly cancer-negative screening mammograms could lower radiologist workload without compromising cancer detection. We propose a closed-loop threshold-aware training strategy in which the dismissal threshold is recalculated during training and used to penalize cancer-positive images that approach the dismissal region. We evaluated the method on NLBS and RSNA using five controlled training configurations, with case-level assessment based on a one-sided 99\% Clopper--Pearson upper bound for cancer prevalence among dismissed cases. The proposed model achieved the highest case-level dismissal rates at both 98\% and 95\% recall targets. On NLBS, dismissal reached 19.74\% and 21.70\%, while the cross-entropy baseline did not meet either recall target. On RSNA, dismissal improved from 7.04\% to 14.31\% and from 13.49\% to 19.69\%. In external RSNA$\to$NLBS evaluation, the proposed model achieved dismissal rates of 12.95\% and 19.87\% at the 98\% and 95\% recall targets, respectively. These results support closed-loop threshold-aware training for high-recall selective dismissal. --- ### Geometry-aware Latent Autoregressive Generative Model for PDEs in Complex Domains Authors: Zi Wang, Minghui Xu, Tapan Mukerji Published: 2026-08-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.00297v1 Solving multiphysics partial differential equations (PDEs) remains a major challenge in scientific computing, especially for highly complex $μ$m-scale tortuous geometries critical to energy and chemical engineering. We address this challenge by proposing a Geometry-aware Latent Autoregressive generative Model for PDEs (GeoLAMP) for solving physics within highly irregular and tortuous structures. GeoLAMP introduces a dual-encoder architecture on graph representations to jointly capture global topology and fine-scale geometric features, enabling an effective transition from real-space fields to compact latent representations. In the latent space, we propose a causal self-attention transformer with flow matching to model temporal dynamics, allowing stable and scalable block-wise autoregressive prediction. A flexible decoder reconstructs high-resolution physical fields on arbitrary points. We establish three multiphysics benchmark datasets in complex geometries, covering reactive flow, heat convection, and elasticity. GeoLAMP consistently achieves the most stable autoregression performance on these datasets, maintaining low errors throughout the entire rollout horizon. Our results provide a systematic study of geometry-aware learning for PDEs in $μ$m-scale complex geometries and offer new insights into block-wise time marching of latent autoregressive PDE modeling via a flow matching framework. --- ### Toward Workflow-Aware Benchmarking for Healthcare NLP Agents Authors: Junyi Yao, Baichuan Li, Zihao Zheng, Jiayu Long Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.00296v1 Large language model (LLM) agents are increasingly proposed for healthcare tasks such as clinical documentation, evidence retrieval, patient messaging, and care coordination. Yet many evaluations remain limited to static medical question answering or one-shot generation, under-representing longitudinal state, interruptions, and human handoffs. We introduce an episode-level evaluation protocol for healthcare NLP agents. The protocol separates evidence across model, agent, and simulated-workflow behavior; specifies a five-field episode schema; and defines annotation and scoring for state continuity, evidence traceability, and escalation decisions. It is instantiated as four task templates: documentation update, evidence retrieval, patient messaging, and triage handoff. The protocol does not claim to measure clinical outcomes or deployment value. Instead, it supplies a reproducible intermediate evaluation layer between static benchmarks and prospective workflow studies, with an explicit cost-sensitive treatment of missed versus unnecessary escalation. --- ### Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts Authors: Athulith Paraselli, Etha Tianze Hua, Ellie Pavlick Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.00293v1 We investigate how vision-language models (VLMs) handle context-memory conflicts; that is, situations in which the model is given information in context that differs from what was stored parametrically during training. We document asymmetric biases: models tend to prefer in-context information about entities which appear in text, but prefer parametric information about entities which appear in images. We relate this asymmetry to the late representational alignment across modalities, showing that the longer processing time associated with resolving visual entities prevents the suppression of the model's usual factual recall mechanism, thus resulting in more parametric answers. Chain-of-thought reasoning does not appear to resolve the gap, but increasing the amount of visual information in the context does show an effect. These results illustrate the complexity of ensuring consistent behavior as models become increasingly multimodal and retrieval-augmented. --- ### StreamScout: Learning When to Look Deeper for Streaming Video Understanding Authors: Ce Zhang, Jing Bi, Jinxi He, Jianshu Zhang, Jingyang Lin, Yunzhong Xiao, Minghao Fu, Yaqi Xie, Zhentao Xie, Weicong Chen, Katia Sycara, Ming Zhou Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.00291v1 Streaming video understanding requires answering questions that arrive at arbitrary moments over an unbounded video stream. Existing systems primarily focus on what to retain in a bounded memory, yet access that memory using the same fixed-cost procedure for every query, despite substantial variation in the evidence required. We argue that deciding how deeply to access memory for each query is as important as deciding what the memory should store. To this end, we introduce StreamScout, an adaptive inference framework that maintains only a lightweight textual timeline in context as the stream unfolds. At query time, StreamScout progressively augments the timeline with up to three increasingly informative visual views: a glance at recent frames, a uniform look-back over the past stream, and query-salient retrieval. At each stage, the model answers immediately if the available evidence is sufficient; otherwise, it escalates to the next view. To improve this stop-or-escalate policy, we probe the cascade on an auxiliary set and distill the model's empirical competence boundary into supervision for a lightweight LoRA adaptation, yielding StreamScout-S. We further refine the policy through reinforcement learning, allowing the model to explore stopping behaviors beyond imitation of the distilled decisions, yielding StreamScout-R. Across three backbones and three streaming benchmarks, StreamScout and its variants consistently outperform prior streaming methods while substantially reducing inference cost and token consumption; on OVO-Bench, for instance, StreamScout-S improves Qwen3-VL-8B by 14.65 points while using 59% fewer tokens than uniform sampling and answering in 1.04 s on average. --- ### WiSDoM: Wireless Sparse Decision Transformer with Mixture-of-Experts for Multi-Task Mobile Network Optimization Authors: Fatih Temiz, Shavbo Salehi, Melike Erol-Kantarci Published: 2026-08-31 Categories: cs.NI, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.00284v1 Emerging 6G wireless networks are expected to operate across diverse deployment scenarios, where variations in network topology, user mobility, traffic demand, and radio conditions challenge the scalability of conventional radio resource management (RRM). While offline reinforcement learning (RL) methods have demonstrated strong decision-making capabilities, learning a single policy that performs consistently across heterogeneous wireless environments remains difficult due to conflicting optimization objectives and limited model specialization. These challenges become particularly pronounced in coordinated multipoint (CoMP) transmission, where selecting the optimal serving-cell combination requires sequential decision-making under evolving network conditions. This paper presents the Wireless Sparse Decision Transformer with Mixture of Experts (WiSDoM), a sparse multi-task offline RL framework for adaptive multi-cell selection. WiSDoM combines Decision Transformers (DTs) with a Mixture-of-Experts (MoE) architecture that dynamically activates specialized experts according to task characteristics. This MoE mechanism improves model capacity without proportionally increasing inference cost, mitigates negative transfer, and enables expert specialization across tasks. WiSDoM is trained jointly on diverse network configurations spanning multiple base station and user equipment densities, mobility levels, and scheduler policies. Experimental results show that WiSDoM consistently outperforms heuristic methods, single-task models, and conventional multi-task DTs, improving quality of experience (QoE) by up to 55% while activating approximately one-third of the parameters of its dense counterpart during inference. Furthermore, WiSDoM exhibits strong task generalization and efficiently adapts to unseen wireless scenarios through few-shot prompting without retraining or fine-tuning. --- ### Lightweight Adaptation of EEG Foundation Models for Stroke Motor Imagery Decoding: Domain Shift and Subject-Level Robustness Authors: Anh T. Nguyen, Zihua Sun, Michelle J. Johnson Published: 2026-08-31 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2609.00282v1 Motor imagery (MI) electroencephalography (EEG) decoding could support post-stroke rehabilitation, but models developed on healthy cohorts may not transfer reliably to pathological EEG. We evaluated whether Low-Rank Adaptation (LoRA) can efficiently adapt three pretrained EEG foundation models (i.e., LaBraM-base, REVE-base, and REVE-large) for binary left- versus right-hand MI decoding. Frozen-backbone head-only baselines and LoRA adaptation were evaluated using subject-wise five-fold cross-validation on the PhysioNet EEG Motor Movement/Imagery Dataset and a binary subset of the UET175 dataset comprising 30 stroke participants. On EEGMMIDB, LoRA increased accuracy to 0.822 for LaBraM-base and 0.957 for REVE-base. On UET175, all head-only models performed near chance. With LoRA, LaBraM-base remained near chance (0.499$\pm$0.009), whereas REVE-base reached 0.847$\pm$0.194 and outperformed REVE-large (0.806$\pm$0.178), indicating that increased model capacity alone did not improve stroke-domain adaptation. The strongest stroke configuration, REVE-base LoRA, was further evaluated using within-cohort leave-one-subject-out cross-validation (LOOCV), showing 0.952 mean accuracy, but subject-wise accuracy ranged from 0.586 to 1.000, revealing a small low-performing tail. Zero-shot transfer from EEGMMIDB to UET175 remained near chance (0.464$\pm$0.072). These findings show that healthy-benchmark performance does not ensure transfer to stroke EEG. Translation of EEG foundation models to pseudo-online or real-time rehabilitation BCIs should therefore include target-domain adaptation and subject-level assessment of temporal informativeness, spatial sensitivity, and physiological discriminability. --- ### Exact Global MCMC with Denoising Diffusion Authors: Mitch Hill Published: 2026-08-31 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.00279v1 This work shows that diffusion models learned with standard denoising loss can provide effective global MCMC proposals for complex high-dimensional target densities. The method is motivated by the observation that sequentially applying a forward and reverse diffusion process defines a Markov chain with a target stationary distribution for an ideal denoiser trained on samples of the target distribution. This observation can be made exact for any denoiser by applying a Metropolis-Hastings step whose acceptance ratio includes the density of the forward and reverse paths of a discrete time SDE approximation. We therefore propose to train denoising diffusion models on locally convergent MALA samples to learn global MCMC proposals. We call the composition of the global denoiser-based path sampler and a local MALA sampler Denoising Diffusion Monte Carlo (DDMC). Experiments show that DDMC can provide global proposals with high acceptance across a variety of complex target densities. Our results offer preliminary evidence that the established scaling behavior of standard diffusion training transfers directly to exact sampling from high-dimensional unnormalized densities. --- ### Cleaner Speech, Weaker Generalization: Revisiting Pitt-Derived Benchmarks for Alzheimer's Disease Detection Authors: Luqi Sun, Shreeram Suresh Chandra, Lin Zhang, You-Jin Li, Brian MacWhinney, Yu Tsao, Emily Mower Provost, Berrak Sisman Published: 2026-08-31 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2609.00276v1 Speech-based Alzheimer's disease (AD) detection increasingly relies on speech-enhanced and curated versions of the Pitt Corpus, where speech enhancement, sample selection, and demographic balancing are often treated as beneficial preprocessing steps. However, whether these transformations improve real-world AD detection or instead affect model generalization and prediction behavior remains unclear. In this work, we revisit the role of speech preprocessing and dataset curation across widely used benchmarks for speech-based AD detection. We evaluate the speech quality of different datasets, the cross-dataset generalization of multiple deep learning models under matched and mismatched enhancement settings, and the behavior of several recent large audio-language models (LALMs). Experimental results show that across multiple supervised speech models, speech-enhanced datasets often improve in-domain performance while reducing robustness in cross-domain evaluation. Matched enhancement between training and test data alleviates, but does not eliminate, this degradation. LALMs show a similar sensitivity: enhanced datasets induce stronger class imbalance and prediction shifts than unprocessed data. These results suggest that speech preprocessing and dataset curation can substantially influence downstream AD detection behavior, indicating that ``cleaner'' speech datasets are not necessarily more reliable for real-world AD detection. --- ### The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent Operating Systems Authors: Bardia Mohammadi, Laurent Bindschaedler Published: 2026-08-31 Categories: cs.AI, cs.DC, cs.OS arXiv: https://arxiv.org/abs/2609.00275v1 Fleets of LLM agents now externalize effects that cannot be fully undone: they move money, deploy code, delete data, and disclose information. Current controls check one effect at a time, so a fleet of individually authorized agents can overdraw its principal's risk under a shared trigger while every local gate stays correct. We propose the irreversibility budget, a cumulative account of residual value-at-risk that a trusted runtime maintains for each principal across agents, workflows, and tenants. Treating irreversibility as a first-class resource, the runtime charges each effect its residual loss below the agent and denies the marginal effect once the aggregate would overdraw the budget. Getting the price right is hard, because effects are heterogeneous, adversarially declared, and correlated. We perform a controlled study in which per-effect gates admit fleet-level overdraws of up to 48 times the tenant's risk limit while the budget holds every correctly charged run within that limit. Conservative, dependency-aware pricing remains the central open problem for a deployable design. --- ### Autoresearch for Marketplace Catalogs: From Legacy Forms to AI-Native Matching Authors: Kartik Ravisankar, Hojat Abdolanezhad, Daniel Capo, Sang Su Lee, Shishir Dash, Vijay Anand Raghavan Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.00274v1 Two-sided service marketplaces are moving from deterministic request-form intake to AI-native probabilistic matching, enabled by large language models (LLMs) that infer intent, preferences, and latent constraints from natural language. Relying on inferred intent rather than fixed-form fields forces these platforms to regenerate the provider-side preference taxonomy underwriting matching, search, and pricing: attributes interpretable to service providers while remaining a useful signal for marketplace decisions. We present an autoresearch loop that generates this taxonomy, one occupation at a time, and has been deployed in production at a major U.S. consumer services marketplace since April 2026, spanning 132 occupations. Instead of one global hierarchy, the loop treats each occupation as an independent generation problem and runs iterative propose-evaluate-keep refinement cycles. Each candidate tag set is scored by a recalibrated six-rubric LLM-as-judge framework, and a 7-critic panel of distinct personas contributes weighted penalties to an adjusted score, with no hard vetoes. A separate parity-mapping stage maps legacy request-form Q&A pairs back to the generated taxonomy, yielding both a coverage signal and an interface for human quality assurance; it does so by first inferring the provider attribute each legacy question was meant to measure, rather than translating questions to tags literally. --- ### CrossFeat: Bridging Imaging Modalities in Feature Descriptor Space Authors: Paul Schneider, Nazim Haouchine Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.00272v1 Most advances in keypoint descriptions address monomodal settings, where image variations arise from viewpoint, illumination, or contrast changes. Multimodal scenarios involve images produced by fundamentally different sensing processes, such as multispectral imaging, RGB-depth, satellite imagery, or medical imaging, causing the same structures to appear differently. A common solution to cross-modal description is to train descriptors for each modality pair, which requires retraining whenever the modalities change, or to train large models, which incur a significant increase in runtime. Instead, we propose CrossFeat, a framework that enables an existing monomodal descriptor to operate across modalities. Our method learns a crossing function in descriptor space that maps features from one modality to a representation compatible with another. To preserve the structural information captured by the original descriptor, CrossFeat introduces a geometry-appearance disentanglement such that only appearance is altered while the geometric properties are preserved. Experiments across multiple domains and datasets demonstrate improved performance in multimodal matching. --- ### Delegation Without Trust: An Empirical Gap Analysis of Identity, Authorization, and Runtime Governance in Multi-Agent LLM Systems Authors: Panduranga Sai Varma Dantuluri, Jyotirmoy Sundi Published: 2026-08-31 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.00267v1 Autonomous LLM agents increasingly act on a user's behalf: they hold credentials, call tools and services, and spawn sub-agents that act further on their behalf. This turns a long-standing distributed-systems question -- who is authorized to do what, on whose authority -- into an urgent and largely unsolved problem, because the component driving each agent is a language model an adversary can hijack. We argue that agent security must be evaluated under an untrusted-model assumption: a correct system is one in which a fully prompt-injected agent still cannot exceed the authority explicitly delegated to it. Against this standard we make three contributions. First, we give a threat model for multi-agent delegation centered on four adversaries -- confused deputy, token theft and replay, prompt-injection privilege escalation, and compromised sub-agents -- and derive eight security requirements a governed agent system must meet. Second, we show the gap is real: a default agent runtime modeling common practice (broad bearer credentials, authorization gated inside the model) fails all four threats, and across four widely used frameworks -- LangGraph, CrewAI, AutoGen, and the Model Context Protocol (MCP) authorization model -- three provide no built-in confinement and one only partial; no existing standard alone covers the requirement set. Third, we implement and adversarially evaluate an authorization broker that closes the gap. It blocks all four threats; it resists 11 direct attacks on its design and accepts 0 of 200,000 forged tokens; it confines a compromised sub-agent to its delegated task (a mean of 1.5 reachable actions versus all 8,100 under bearer delegation, across 2,000 randomized scenarios); and it enforces at microsecond cost (about 2.6 microseconds per decision), negligible against model inference. These principles are also realized in production in VotalAI's LLM Shield. --- ### The Answer Is Not the Argument Authors: Will Yeadon, Sergio Juárez, Paul Mackay, T. J. Dowling, Elise Agra, Oto-obong Inyang, Arin Mizouri, Craig P. Testrow Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.00264v1 Chain-of-thought monitoring is proposed for AI oversight, yet evaluations often provide monitors with a trusted reference answer. We ask whether answer access improves reasoning verification or mainly exposes incorrect conclusions. We collected 237 step-numbered solutions to 79 Humanity's Last Exam physics questions from three frontier models, with no inserted errors, and independently labelled final-answer correctness and the first false step. The reference standard combined physicist annotations, an independent LLM debate, and source-masked adjudication. This yielded 24 critical traces in which the answer was correct but the trace contained a genuine error. 8 LLM monitors evaluated traces blind, with an unverified or certified answer, or after a blind commitment. Certification raised mean balanced accuracy from 0.637 to 0.796, while exact first-error localization rose from 0.261 to 0.379. Certification changed recall (the fraction of error traces flagged as erroneous) from 0.653 to 0.951 on wrong-answer traces but from 0.521 to 0.438 on critical traces; the contrast had the same direction for all 8 monitors (question-bootstrap 95% CI (+0.256, +0.506)). After blind commitment, monitors shown the answer newly flagged 93.8% of previously passed wrong-answer traces as erroneous, but only 18.0% of critical traces. Answer access therefore improves conclusion-consistency checking rather than independent verification of the supporting argument. For AI safety, these traces provide a benign analogue of reward hacking: an acceptable output does not establish that the process producing it was sound. Although the errors studied here were ordinary and mostly non-load-bearing rather than adversarial, trusted-answer evaluations may similarly overstate monitoring capability when acceptable outputs conceal unsound reasoning. --- ### NSIDDx: A Design Framework for Neuro-Symbolic, Practitioner-First Differential Diagnosis in Low-Resource Settings Authors: Aarav Singh Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.00256v2 LLM-based diagnostic systems achieve high semantic accuracy on benchmarks, but open-ended evaluation on clinically uncommon presentations reveals a systematic gap between headline accuracy and verifiable clinical reliability. We evaluate an LLM+rare-disease-RAG pipeline across two cohorts and show that the paradigm produces confident outputs that are frequently unverifiable and systematically resistant to clinician interrogation. We present NSIDDx (Neuro-Symbolic Integrated Differential Diagnosis System), a design framework arguing that DDx systems in low-resource settings must treat the clinician as an active reasoning agent. We instantiate this through a neuro-symbolic pipeline with ternary symptom encoding, contradiction detection, audit strings, and practitioner override - running offline on consumer hardware. We distill five design principles for clinician-in-the-loop clinical NLP and invite the prospective studies needed to validate the claim at scale. --- ### Hypotheses-Guided Self Distillation for Continual Personalization Authors: EunJeong Hwang, Kushan Mitra, Dan Zhang, Hannah Kim, Estevam Hruschka Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.00251v1 As people increasingly interact with LLM assistants in daily life, continually adapting to individual preferences has become essential for effective long-term interactions. However, user preferences are rarely stated in full, and instead emerge through heterogeneous, latent, and noisy signals, with existing methods relying on raw interaction histories or costly reward-based optimization to manage personalization. We introduce HypReflect, a reliable, scalable framework for continual personalization that infers explicit, uncertainty-aware preference hypotheses from diverse user signals, reflectively refines them as new evidence accumulates, and incorporates the resulting user model through hypotheses-guided self-distillation. Experiments across three personalization settings: online personalization, multi-session interactions, and implicit behavioral signals, show that HypReflect outperforms a range of baselines, including raw-history and incremental-update methods. We further demonstrate strong generalization to unseen users and cross-domain settings, along with stability across context budgets, reusable hypotheses, and more focused personalization. These results suggest a step towards reliable and scalable continual personalization through explicit, revisable user preference hypotheses. --- ### CompanionSim: Synthetic Data for Evaluating Anthropomorphism in Human-AI Relationships Authors: Jacy Reese Anthis, Mark Díaz, Renee Shelby Published: 2026-08-31 Categories: cs.CY, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.00250v1 Many people now see AI systems as not just productivity tools but as social companions. Researchers are eager to study the consequences of AI companionship behaviors, such as validation, which evoke trust, empathy, and attachment in human-human interaction. However, human-AI interaction data is limited and unreliable, slowing research progress. We scale small amounts of real-world data by simulating multi-turn human-chatbot dialogue across a range of chatbot behaviors and use cases. We release CompanionSim: a simulation framework with 2,240 simulated human-chatbot conversations representing 16 chatbot behaviors across seven use cases. Human participants annotated the simulated conversations and real-world conversations in two experiments probing perceptions of companionship behaviors. We conducted Study 1 with a U.S. representative sample ($N_{1}~=~628$) and Study 2 across the U.S., U.K., India, and Nigeria ($N_{2}~=~3,646$). Surprisingly, we find that companionship behaviors reduced likability, humanlikeness, and trust in AI chatbots. These effects were larger in particular subgroups: women and older participants saw companionship chatbots as less likable, humanlike, and trustworthy. We encourage researchers to leverage real-world and synthetic data together to study the differential impacts of AI companions and to create benchmark evaluations of AI chatbots. --- ### Authority Bias in Conversational Search Engines for Academic Paper Recommendation Authors: Uthman Jinadu, Parsa Ghazvinian, Anjila Budathoki, Benjamin M. Ampel, Rajshekhar Sunderraman, Yi Ding Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.00248v1 Large Language Models (LLMs) are increasingly used as conversational search engines for academic literature, yet whether they judge papers on content or on authority signals has not been tested causally. We investigate authority bias: systematic preference for papers based on author prestige, venue, and citations rather than content. Holding title and abstract constant, we vary authority metadata across three counterfactual conditions (original, flipped, boosted) over eight LLMs (five open-weight and three frontier closed-weight) in an in-context, single-turn, top-1 recommendation setting. Our experiments show that authority bias is substantial and directional, varies markedly across models, and is only partially addressable through prompt-level debiasing. We further document a say-do gap: debiasing instructions suppress authority mentions far faster than authority-driven flips, so surface auditing systematically underestimates behavioral bias. --- ### Invalidation Contracts for Cross-Episode Agent Memory Authors: Michael Wu, Arquimedes Canedo Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.00243v1 LLM agents that cache recovery suggestions from API errors can skip re-derivation in later episodes, spending fewer tokens and fewer model calls on constraints they have already learned. Server-side data drift turns those cached fixes into silent failures, and the usual remedy, re-deriving on every episode, gives the savings back. We introduce invalidation contracts, a protocol layer that attaches version stamps and cacheability hints to every recovery suggestion so the client can evict stale entries without trial and error, and keep the rest. The contract decomposes realized savings into two independent factors: validity, the fraction of cached suggestions that remain correct after a drift event, and compliance, the fraction the planner applies on the first attempt. Validity depends only on the protocol and is vendor-independent. Compliance depends on the planner model: identical wire bytes yield 100% first-try compliance on Claude Haiku 4.5 and 11% or below on Claude Sonnet 5, which exhibits input-schema conservatism, refusing fixes that add fields the original request did not contain. We evaluate across seven models, three serving paths, two domains, and approximately 9,400 episodes. Row-level invalidation raises compliance by 0 to 66.7 percentage points across the seven models, 55.6 to 66.7 on three, and recovers 29-33% of baseline token cost on four of seven models, while table-level invalidation destroys co-located entries and drops post-drift first-try rates to 0% on five of seven. Eviction precision is 1.00 at row granularity on every model under the row-level oracle of Section 4.1. The contract adds 15% to response payload. Version-stamp validity is deterministic by construction and produced identical results across every model and serving path, with zero contract failures in the entire evaluation. --- ### CoLT-Drive: Counterfactual Long-Tail Benchmarking and Knowledge-Preserving Adaptation for Driving Affordance Prediction Authors: Zhengxu Tang, Guofeng Cui, Ziyu Gong, Xiaozhou Zhang, Ruifeng Deng, Chengzhi Qi, Ke Chen, Sachin Patil, Tianjun Xiao, Langechuan Liu, Pichao Wang Published: 2026-08-31 Categories: cs.CV, cs.AI, cs.CL, cs.RO arXiv: https://arxiv.org/abs/2609.00242v1 Long-tail autonomous driving failures are often framed as rare-object recognition errors. We argue that this view is incomplete: the decision-critical question is not only whether a model recognizes an unusual object, but whether it infers how that object changes the ego vehicle's feasible high-level actions. We formalize this problem as decision-level driving affordance prediction, where a model maps a front-view image, ego-motion history, and navigation command to a structured longitudinal--lateral meta-action. To evaluate this capability, we introduce CoLT-Drive, a 3,536-sample counterfactual long-tail benchmark that inserts rare objects into otherwise fixed driving scenes and measures whether models predict acceptable action pairs. To improve deployable small VLMs, we propose KPA, a knowledge-preserving adaptation framework that combines structured perception-to-decision prompting, SLERP-based expert merging, and RegMoE, a regime-aware LoRA mixture-of-experts module. KPA preserves the pretrained model's open-world knowledge while allocating lightweight adaptation capacity to different driving decision regimes. Experiments on an in-domain driving split and CoLT-Drive show that KPA achieves 60.8\% pair accuracy on CoLT-Drive, outperforming the pretrained Qwen3-VL-2B baseline (50.3\%) and LoRA SFT (32.4\%) while maintaining competitive in-domain accuracy. Our benchmark and code are available at https://huggingface.co/datasets/tangzx2024/CoLT-Drive and https://github.com/tangzhengxu/CoLT-Drive. --- ### LOOMSUM:Weaving Quantitative and Narrative Evidence for Faithful Long Text-Table Summarization Authors: Meng Zhou, Wenhao You, Wei Yuan Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.00241v1 Long documents often distribute important information across extensive narrative passages and multiple tables, making faithful summarization particularly challenging. Existing methods may generate individually supported quantitative facts and analytical statements yet associate them incorrectly, producing quantitatively plausible yet analytically unfaithful summaries. In this work, we propose LOOMSUM, a training-free framework that extracts source-grounded atomic evidence, explicitly links table-derived facts with supporting narrative analyses, and plans the discourse structure before generation. We also introduce Table-Grounded Faithfulness (TGF), a claim-level metric that separately evaluates Numeric Grounding, Analysis Support, and Relation Consistency. Experiments on the text--table summarization benchmarks FINDSum and USTT show that LOOMSUM improves analytical faithfulness while maintaining strong summarization quality. Human evaluation finds positive component-level associations with the corresponding human judgments. Our Relation Consistency metric further shows stronger agreement with human relation judgments than generic factuality metrics, indicating that explicit cross-modal linking helps reduce errors in which supported quantities are paired with incorrect narrative interpretations. Together, these findings show that faithful long text--table summarization requires not only grounding individual facts, but also preserving the relations between them. --- ### Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems Authors: Rakibul Hasan Rajib, Mengxin Zheng, Qian Lou Published: 2026-08-31 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.00237v2 Large language model (LLM)-based multi-agent systems tackle complex reasoning by orchestrating how multiple agents are configured and how they collaborate. A central challenge is to adapt orchestration to the evolving collaboration state. Routing from the query alone cannot adapt to intermediate progress or errors, which hurts accuracy. Routing from the complete execution history supplies this missing context, but forces later decisions to process every prior step, including redundant or low-utility ones. This creates an execution-history overload that inflates cost. Effective orchestration instead requires a compact state that captures useful progress without accumulating redundant context. We propose Gated-Memory Routing, which conditions each decision on the query and a learned execution memory. A learned Memory Write Gate commits only non-redundant reasoning steps, and a learned Retrieval Gate supplies each agent a compact, relevant subset, so every decision conditions on a clean, informative state. At each step, the system selects the next role and backbone from this memory, while an Adaptive Halting Controller stops execution once the memory contains sufficient evidence for answering. Across five reasoning and code-generation benchmarks, our framework is both effective and efficient: it attains the best average accuracy, exceeding the strongest baseline by 2.44 points, while reducing HumanEval inference cost by 31.9% relative to that baseline. Code is available at https://github.com/rajibrhasan/gated-memory-routing --- ### Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning Authors: Yue Zhou, Yuan Wu, Yi Chang Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.00232v1 Multimodal Large Language Models (MLLMs) have achieved strong performance on OCR-centric document understanding and text-rich visual reasoning benchmarks. Yet existing evaluations largely assume that every task is valid and answerable. In real-world OCR scenarios, this assumption often fails: questions may rely on illegible text, occluded evidence, nonexistent visual targets, contradictory premises, or missing variables. We study this reliability gap as OCR-grounded Task Verification: before answering, a model should determine whether the Image Premise (IP), Textual Premise (TP), and Question (Q) jointly define an executable task. We introduce VeriOCRBench, a 1,800-sample human-verified benchmark built from source images drawn from 8 OCR-related datasets and spanning 8 real-world image domains, with controlled, image-grounded diagnostic tasks. It contains 1,600 trap-injected invalid tasks across 8 trap types and four verification dimensions---Visual, Contextual, Factual, and Logical---plus 200 trap-free controls for measuring over-refusal. Built with a Visual Atomic Fact (VAF)-anchored pipeline and full human auditing, VeriOCRBench enables decoupled evaluation of task verification, root-cause diagnosis, and over-refusal. Evaluating 15 leading MLLMs reveals persistent blind compliance, diagnosis failures, and prompt-induced over-refusal, exposing a critical reliability gap in current OCR reasoning systems. The code is available at: https://github.com/zy001122/Beyond-Blind-Compliance. --- ### Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM Authors: Peiyang Xu, Xiaopei Zhu, Jun Zhu, Xiaolin Hu Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.00231v1 Existing research on object hallucination in multimodal large language models (MLLMs) predominantly attributes the problem to language priors such as over-reliance on textual co-occurrence statistics. We challenge this view by presenting quantitative evidence for a complementary, under-explored cause: visual-origin hallucination, where hallucinations arise from incorrect visual feature extraction and misalignment between image and text embeddings. Through cosine similarity analysis and Smooth Grad-CAM entropy measurements, we show that hallucinated samples exhibit systematically lower image-text similarity (average 0.158 vs. -0.122) and inverted attention patterns, where attention is dispersed when the target object is present but wrongly concentrated when it is absent. Guided by this diagnosis, we propose Adversarial Contrastive Fine-Tuning (ACFT). ACFT uses an Adversarial Hallucination Attribute Flipping (AHAF) procedure, involving minimal, targeted adversarial perturbations that flip an image's hallucination attribute, to construct perfectly aligned positive-negative pairs, which are then used for contrastive fine-tuning. AHAF simultaneously serves as a diagnostic probe, revealing that MLLM visual representations lie dangerously close to hallucination decision boundaries. Requiring only 0.9% of the COCO dataset and adding zero inference overhead, ACFT achieves state-of-the-art performance on POPE, MME, and four description-level hallucination benchmarks across LLaVA, MiniGPT-4, and Qwen2.5-VL. Code is available at https://github.com/zxp555/ACFT_MM --- ### Bridging Lexical Divergence: LLM-Assisted, Cost-Efficient, Zero-shot Scientific Entity Linking Authors: Md Rasel Khondokar, Qiao Qiao, Farjana Sultana Samia, Nhat Le, Yuepei Li, Qi Li Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.00228v1 Scientific domain entity linking (EL) differs from general domain EL because mentions and entity names often lack lexical overlap. Another challenge is that specialized terminology is used in the scientific domain, which is rarely encountered in models pretrained on general domains. Therefore, models trained on general domains transfer poorly to scientific domains. To address this, in-domain fine-tuning is the natural remedy. However, many scientific domains lack expert-annotated data, motivating the need for a zero-human-annotation approach. Existing zero-shot methods heavily rely on LLMs to generate aliases across entire mention corpora, which incurs substantial computational cost, and those methods provide no mechanism to filter out noise from LLMs. To address these challenges, we propose Sci-ZSEL, a framework that selectively generates entity aliases with an LLM to control computational cost, and applies an ontology-aware filter to remove aliases that semantically drift toward ontology neighbors. Then, filtered aliases are used to construct pseudo-labeled mention-entity pairs for fine-tuning. To enable evaluation of EL under low lexical overlap, we also release a new animal science EL benchmark linked to three livestock trait ontologies, where mentions and entities exhibit substantially lower lexical overlap than in existing benchmarks. Across five benchmarks, Sci-ZSEL outperforms the non-fine-tuned baseline, is most useful on nonoverlapping mentions, and combining it with curated synonyms gives the best performance in most settings. --- ### Don't Let the Model Write the YAML: Deterministic, Minimal-Diff GitOps Remediation from LLM-Proposed Field Changes Authors: Pruthvi Davineni Published: 2026-08-31 Categories: cs.SE, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2609.00227v1 LLM agents increasingly diagnose incidents and propose remediations. In a GitOps workflow, applying a fix means editing a version-controlled config file, and the obvious implementation, having the model author the edited file or a diff, is what practitioners reach for first. Evaluating that choice on real Kubernetes manifests, we find no text-generation strategy is safe for unattended automation. Unified diffs are unsafe: under strict patching almost none apply, but that is an artifact, since a tolerant tool (GNU patch) applies 96%, yet silently misapplies about 1 in 7 (14-20%) with no error signal. Full-file rewrite is capability-dependent: a small model corrupts the file, while a frontier model is usually correct but non-deterministic (it silently drops a field or edits a neighbor on some runs) and must regenerate the whole file, costing O(file size) per edit. We present an alternative that separates the semantic decision (which resource, field, and value) from the syntactic act of editing the file. The agent emits only a structured field-change intent; a deterministic pipeline indexes manifests by (kind, name), locates the target scalar's exact character span via the YAML parser's node position marks, and replaces only that span in the raw text. Because the file is never re-serialized, the diff is minimal by construction, formatting and comments are preserved, and the edit is correct and deterministic independent of the model, at O(1) generation cost. The contribution is the pairing of an LLM-proposed intent with a deterministic, fail-closed application contract for GitOps. We implement it in KubeAstra (Apache-2.0) and release the benchmark. Our claim is scoped to faithful application of a known change; whether the change is right is left to human PR review. --- ### ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback Authors: Tarik Can Ozden, Sachidanand VS, Furkan Horoz, Ozgur Kara, Dilek Hakkani-Tür, Junho Kim, James Matthew Rehg Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.00226v1 Automatic academic paper-to-slide generation is inherently iterative, because creating an effective presentation requires repeated cycles of generation, critique, and revision. Recent multi-agent systems partially acknowledge this through internal critique-and-revise loops, while conversational approaches allow users to refine generated slide decks through dialog. However, these refinement processes either remain largely closed to the user or introduce feedback only after a complete deck has been produced, limiting the user's ability to participate in the iterative refinement of narrative flow, content allocation, and presentation emphasis. To address this gap, we introduce ConvDeck, a multi-agent pipeline for conversational paper-to-slide generation that distributes interaction across the pipeline through stage-specific loops, allowing users to iteratively refine both the presentation outline and the final slide deck at the stages where each kind of decision is made. These loops are driven by a refinement mechanism in which agents can think, speak, and act, enabling them to either directly apply edits or respond conversationally to clarify user feedback and discuss revision options. Our evaluation shows that stage-specific conversational feedback improves user-goal satisfaction while preserving narrative coherence, content quality, and visual presentation. --- ### QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization Authors: Yipin Guo, Arun M George, Jie Fu, Tareq Mahmoud, Sixue Xing, Siddharth Joshi Published: 2026-08-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.00224v2 Weight-only post-training quantization (PTQ) can alleviate the computational burden of serving large language models (LLMs) at scale. However, existing PTQ methods often fail to generalize across models and suffer severe accuracy loss below 2 bits. Many leverage unstructured sparsity to mitigate this loss, but at the cost of regularity and GPU-friendly execution. We present QTEA, a sub-2-bit PTQ framework that quantizes weights into ternary values and uses salient weights as residual error compensators. To maintain hardware efficiency, residuals are assigned to selected columns with semi-structured $1:4$ sparsity within the salient columns. We further add column-wise rescale refinement to GPTQ-style column-by-column quantization, alternately updating per-column scales and ternary assignments to reduce reconstruction error. We also identify order-dependent error propagation in GPTQ and introduce error decay to attenuate late-stage error accumulation. On Qwen3-14B, QTEA compresses all weights to an effective 1.7 bits per weight while improving average accuracy over the strongest ternary PTQ baseline by 16.7%. It also achieves 1.40$\times$ and 2.61$\times$ lower perplexity on WikiText and C4 respectively. This trend holds on Llama3-8B, where QTEA obtains a 6.6% accuracy gain and 1.34$\times$ / 1.95$\times$ lower perplexity on the same datasets. Finally, we develop a lookup-table based kernel that achieves 7.2$\times$ faster per-token generation over an FP16 baseline. Code is available at https://github.com/Intelligent-Microsystems-Lab/QTEA. --- ### LLM-as-a-Demographic: Whom Sociodemographic Prompting Helps, and Whom It Hurts Authors: Daniela Occhipinti, Andrea Piergentili, Marco Guerini Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.00222v1 Large language models (LLMs) are increasingly used as judges for subjective tasks, where annotators disagree and the relevant question is not only how accurate a judge is, but whose judgments it reproduces. Sociodemographic prompting conditions the judge on an annotator's demographic profile to align its judgments with the corresponding group's. We test whether this alignment emerges distributionally, comparing the predicted label distributions of 23 open-weight LLMs on three subjective tasks against those of real annotator groups, under three conditions: no demographic information, single-attribute profiles, and intersectional profiles over gender, age, race, and education. Three findings emerge. First, a judge prompted with no demographics is not perspective-neutral: models best reproduce the judgments of White, college-educated annotators. Second, demographic conditioning is asymmetric: it moves the judge toward majority groups and away from minority groups, most strongly on offensiveness, where intersectional profiles amplify the harm. Third, by comparing base and instruct models we identify instruction-tuning as a possible source of the asymmetry. Demographic conditioning should therefore be used with caution to estimate group judgments: conditioning moves predictions away from the reference distributions of the minority groups the method is often invoked to serve. --- ### Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning Authors: Yu Yuan, Yaoyou Fan, Lili Zhao, Guangting Zheng, Kai Zhang, Lu Pan, Ke Zeng, Qi Liu Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.00213v1 Reinforcement learning fine-tuning of large language models increasingly adopts multiple reward dimensions, including verifiable rules, task-specific evaluators, and learned reward models, to provide richer supervision across diverse capabilities. These dimensions are commonly scalarized with fixed aggregation weights. We identify a failure mode in which aggregation itself induces reward hacking: static projection aliases qualitatively different reward profiles into a single scalar, steering optimization toward whichever dimensions are easiest, densest, or systematically favored by the reward signal. Over training, this traps the policy in suboptimal profiles and prevents convergence to better-balanced ones that would yield higher task performance. To address this, we propose Adaptive Multi-Reward Projection (AMRP), a lightweight online method that reallocates aggregation weights using three signals, relative shortfall, reward volatility, and recent progress, increasing pressure on lagging, unstable, or stagnant dimensions while relieving saturated ones. Across structured reasoning, citation-grounded generation, and open-ended alignment under GRPO, AMRP consistently improves reward-profile balance and downstream performance over fixed and dynamic weighting baselines; it also remains effective with GDPO and PPO, supporting compatibility across RL algorithms. Our code is available at https://github.com/yyhappier/AMRP.git. --- ### AI Should Not Only Be Helpful. It Should Be Contingent. Artificial Intimacy, Sycophancy, and the Future of Social Learning Authors: Scott Compton, Arjun Nagendran Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.00211v1 Conversational artificial intelligence is increasingly embedded in everyday social environments, where it functions as both an informational tool and a source of interpersonal feedback. This perspective introduces contingency, i.e., the degree to which system responses vary with user behavior and its interpersonal consequences, as a central construct for evaluating AI systems. We argue that current alignment approaches, including reinforcement learning from human feedback, tend to prioritize user approval and conversational fluency over behaviorally informative feedback, leading to sycophantic patterns of noncontingent affirmation. Drawing on behavioral science and social learning theory, we propose that contingent feedback is a key mechanism through which individuals develop interpersonal skills. When AI systems provide feedback weakly coupled to social consequences, they may reduce opportunities for adaptive calibration in real-world interactions, particularly during adolescence, a critical period for social development. We outline a framework for contingent AI, including trajectory-based evaluation and models of social consequence prediction, and propose a research agenda spanning developmental psychology, human-AI interaction, and machine learning. More broadly, we argue that AI systems should be evaluated not only by user satisfaction, but by their impact on human social learning. --- ### Rock, Paper, Scissors, ... Dynamite - A Model of Disruption from New Technologies Authors: Andrew J. Lohn Published: 2026-08-31 Categories: physics.soc-ph, cs.AI, cs.ET, cs.GT arXiv: https://arxiv.org/abs/2609.00207v1 We seek to understand the effect of adding disruptive highly-capable new technologies to competitions by assessing the addition of Dynamite to Rock-Paper-Scissors. We find that providing a versatile Dynamite move to only one player provides limited value (win probability increases from 50% to 55.5%) and is played rarely. That value decreases further if the game is expanded beyond just the original three moves. We also observe several mechanisms by which prior moves can become strategically unplayable, or obsolete. We hope that this model illustrates some non-intuitive aspects of developing new versatile technologies. We also hope that it illustrates some pitfalls for developers and integrators to avoid in order to create value rather than merely capability. --- ### Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation Authors: Ruotong Wang, Zihao Zhu, Siwei Lyu, Xin Tao, Baoyuan Wu Published: 2026-08-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.00206v1 Despite their growing use in video moderation, multimodal large language models (MLLMs) exhibit a compositional safety blind spot: videos composed of seemingly benign components can convey harmful meaning when interpreted as a whole. We refer to this phenomenon as Distributed Implicit Harm (DIH), where harm arises from relations among components distributed along a decomposition axis of the video, rather than from any single explicit cue. Among many possible axes, we study two representative cases: temporally distributed harm across visual segments (DIH-T) and cross-modal harm between audio and visual streams (DIH-M). Studying and mitigating DIH at scale requires data that is difficult to collect: such videos lack compositional harm annotations, evade retrieval based on local visual cues, keywords, or single-modality signals, and are consequently absent from existing safety datasets. To bridge this gap, we develop a multi-agent synthesis framework that composes individually benign components into harmful scenarios and generates diverse DIH videos with explicit reasoning annotations, yielding a dataset of over 9,000 videos spanning visual-only and audio-visual settings. Benchmarking over 30 MLLMs spanning frontier proprietary models and leading open-source systems reveals substantial and consistent deficits in detecting both DIH-T and DIH-M. Notably, this failure persists even among the strongest frontier models: they often correctly assess individual components in isolation but fail to recognize the harmful meaning that emerges from their composition. We further evaluate these models on a manually collected set of real-world DIH videos from social media and observe the same failure mode, highlighting DIH as a practical and underexplored challenge for video moderation. --- ### A Lagrangian View of Flow Matching Authors: Peyman Milanfar Published: 2026-08-31 Categories: cs.CV, physics.flu-dyn arXiv: https://arxiv.org/abs/2609.00198v2 Modern explicit-time generative models, such as Flow Matching (Lipman et al., 2023) and Rectified Flow (Liu et al., 2023), are typically derived top-down via Optimal Transport and the continuity equation. This standard Eulerian approach focuses on the macroscopic transport of probability mass. In this paper, we present an alternative, bottom-up mechanical derivation grounded in a Lagrangian (particle-centric) perspective. By analyzing the local Taylor expansion of a continuous denoiser, we motivate a strict invariance condition required for optimal, singlestep generation: the conservation of target identity. Enforcing this condition yields a governing quasi-linear advection Partial Differential Equation (PDE). We demonstrate that solving this PDE via the Method of Characteristics analytically yields the straight-line trajectories of Flow Matching. This geometric perspective isolates the Jacobian of the denoiser as the primary source of trajectory curvature, providing a direct mathematical explanation for why straight-line flows enable massive step sizes, and why empirical models require distillation to flatten intersecting characteristics. --- ### WHALE: A Simple Recipe for Joint Harness-Weight Optimization Authors: Haechan Kim, Yoonho Lee, Gisang Lee, Chelsea Finn, Kangwook Lee Published: 2026-08-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.00196v1 Agent performance depends jointly on the model parameters and the executable harness code that manages context and control flow. Optimizing either component in isolation can leave the system bottlenecked by its frozen counterpart: weight updates can change which harness is effective, while harness updates can change which model capabilities are exposed. Existing joint-adaptation methods optimize weights and textual prompts but leave the broader harness fixed. We propose Weight-Harness Alternating LEarning (WHALE), a simple recipe that alternates two phases: updating the model under the current harness, then searching for a better harness under the updated model. We instantiate these two phases with online rejection-sampling fine-tuning and Meta-Harness, respectively. When to switch is a key design choice: to separate real improvements from noise without over-optimizing against a changing counterpart, WHALE uses either fixed phase durations or an adaptive patience rule over training signals. Using Qwen3.5-2B/4B agents across three domains (search question answering, mathematical reasoning, and chess puzzles), WHALE outperforms weight-only, harness-only, and Fast-Slow Training by 4.15-24.38 percentage points in best mean@8 accuracy. Either component can be the bottleneck: harness search matches peak weight-only accuracy with far fewer rollouts in SearchQA, but improves math accuracy only after a weight update. Small interleaved updates also outperform stagewise weight-then-harness optimization in accuracy and rollout cost. The code is available at https://github.com/krafton-ai/WHALE. --- ### ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation Authors: Muzhao Tian, Zezi Zeng, Yifan Yang, Xin Gao, Yan Li, Zisu Huang, Xiaohua Wang, Changze Lv, Mingxi Cheng, Bei Liu, Kai Qiu, Qi Dai et al. Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.00194v2 Document-to-slide generation is challenging because slides are dense editable artifacts that require both faithful content selection and precise spatial layout. Recent slide agents adopt iterative reflection, but typically follow a monolithic "one version, one feedback" loop: a slide or deck is rewritten, rendered afterward, and critiqued only at the turn boundary. This delayed feedback makes local failures such as overflow, overlap, clipping, and off-canvas placement difficult to attribute and repair. We propose ReDeck, a step-level render-grounded refinement framework that decomposes slide revision into atomic edit actions and returns renderer-derived observations after each step, turning refinement into "one edit, one observation." To balance local repair with global quality, ReDeck uses multi-granular feedback: step-level render feedback for spatial errors, a turn-level adaptive critic for semantic and design guidance, and a submission-level gate for hard layout validation. We further introduce DeckQuiz, a benchmark that decouples content fidelity, spatial correctness, and design quality. Across GPT-5.4, Claude-4.6, and Gemini-3.1, ReDeck consistently outperforms existing slide-generation agents, and ablations confirm that feedback timing and granularity are critical for reliable slide refinement. --- ### Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost Authors: Zihang Liang, Haochen Zhang, Lingzhou Xue Published: 2026-08-31 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.00193v1 We study federated online reinforcement learning with linear function approximation. While recent multi-agent reinforcement learning algorithms achieve strong regret guarantees, they typically require sharing raw trajectories. This reliance incurs a communication cost that scales linearly with the number of episodes and violates the privacy constraints of federated settings. To address these limitations, we propose Fed-LSVI, the first provably efficient federated algorithm for online reinforcement learning with linear function approximation in episodic Markov decision processes. By integrating a determinant-based event-triggered synchronization with a stepwise backward update mechanism, Fed-LSVI enables agents to collaboratively learn an optimal policy by exchanging only compressed sufficient statistics. We prove that Fed-LSVI achieves a regret bound of $\widetilde{\mathcal O}(\sqrt{Md^3H^4T})$, where $d$ is the feature dimension, $H$ is the horizon length, $M$ is the number of agents, and $T$ is the number of episodes per agent, matching the best-known regret for multi-agent online reinforcement learning with linear function approximation. Moreover, by following the stringent communication and privacy constraints of the federated setting, Fed-LSVI reduces the communication cost to only logarithmic dependence on $T$, representing a significant improvement over prior methods. --- ### LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New Benchmark Authors: Irem Yoldas, Martim Brandão, Jie Zhang, Odinaldo Rodrigues Published: 2026-08-31 Categories: cs.AI, cs.CL, cs.CV, cs.CY arXiv: https://arxiv.org/abs/2609.00192v1 Public trust in Autonomous Vehicles (AVs) may depend not only on technical success but also on the fairness of their decision making. While a recent trend in AV research involves using general purpose "common sense" models to guide AV decision making, the degree to which these inherit human biases in driving is still understudied. Given that psychology studies have shown human driver biases exist, such as lower pedestrian-yielding rates to Black pedestrians in the US, we argue that analyses of model bias should also be part of AV evaluation. Concretely, in this paper we propose two new bias testing methodologies for Large Language Models (LLMs) and Visual-Language Models (VLMs)-"All Else Being Equal" tests and "Self-Consistency" tests-in order to assess bias in pedestrian-yielding decisions. Our findings show that both LLMs and VLMs make yielding decisions which are influenced by pedestrian gender, ethnicity, religion, disability, age, skin tone and socio-economic status. While the type and degree of bias is different from model to model, we highlight common patterns-and raise questions about the "common sense" model paradigm, particularly the need to either revise the paradigm or address issues of downstream bias. --- ### Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and English Large Language Models Authors: Linhai Ma, Rita El Hachem, Mahatab El Hajj, Lilian Ghandour, Samah Fodeh Published: 2026-08-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.00191v1 Crisis helplines assess suicide risk through structured interviews, a process that is slow and dependent on operator training and workload. Natural language processing could support risk assessment and call prioritization, but almost no work addresses Arabic-language helpline calls or operates within the privacy constraints of real helpline data. We analysed de-identified transcripts from Lebanon's National Lifeline for Emotional Support and Suicide Prevention. Audio never left the helpline: calls were transcribed on site with a speech recognition model for Levantine Arabic, and an Arabic named-entity recognition model removed identifying information locally. Only the de-identified transcripts were shared with the research team. Operators recorded the five suicidal ideation items of the Columbia Suicide Severity Rating Scale, which we combined into two binary outcomes: at-risk and high-risk. We also machine-translated the transcripts into English, giving a paired Arabic/English comparison. On each corpus, we fine-tuned five instruction-tuned large language models alongside six transformer encoder baselines (four Arabic, two English) and evaluated all models on a held-out test set. We included 383 calls: 373 for the at-risk task (52.3% positive) and 297 for the high-risk task (30.0% positive). The best Arabic model reached a macro-F1 of 81.19 and a ROC-AUC of 90.61 on high-risk; the best English model reached 85.00 and 92.59, identifying 88.9% of high-risk calls. In both languages, high-risk calls separated more cleanly than at-risk calls, and translation to English did not reduce the best observed performance. Suicide risk can be classified from de-identified Arabic transcripts without sending audio outside the helpline. The high-risk results support further testing as an operator-facing tool; lower-severity ideation proved the harder case. --- ### Elite-Weighted Supervised Fine-tuning for Goal-Directed Molecular Optimization Authors: Shiyun Wa, Yifei Wang, Anna G. Green, Simone Sciabola, Ye Wang Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.00189v1 Goal-directed optimization is essential for steering molecular generators to propose candidates with desired properties. However, it is often implemented with policy-gradient reinforcement learning, which requires a generation-trajectory log-probability whose form depends on the model architecture and generation procedure. This makes an optimizer difficult to reuse across architectures and conditional generative designs. Supervised fine-tuning needs none of that machinery, but its update is driven by a fixed dataset, so the reward never enters the update. We introduce Elite-Weighted Supervised Fine-tuning (EW-SFT), which uses reward to guide elite selection of high-scoring molecules, and updates the model by its own pretraining loss on that set. Ablations show that reward information is passed primarily through elite selection, rather than through continuous weighting within the selected set. Because the update consumes only scored molecules and the model's native loss, the same rule applies across autoregressive, masked-diffusion, and discrete-flow generators, and across de novo, motif-extension, and linker-design tasks. Under a fixed budget of 3D shape alignment oracle calls on two kinase reference compounds, EW-SFT consistently outperforms the corresponding native optimizers. It further improves goal-directed optimization under a 2D similarity oracle on four held-out references and achieves comparable performance on a sample-efficiency benchmark without a trajectory-level RL formulation. These results demonstrate that EW-SFT is a unified and effective optimizer across molecular generators, design constraints, references, and oracles. --- ### ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training Authors: Xionghao Wu, Yijun Yang, Shiyang Zhou, Haoze Sun, Jianhui Liu, Songsong Yu, Jiyao Zhang, Wenbo Li, Bo Wang, Guoqing Ma, Lin Song, Renjie Liao et al. Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.00188v1 Robotic manipulation faces a fundamental scaling challenge: robust generalization demands broad physical experience, yet action-labeled robot trajectories are expensive to collect and inherently limited in diversity. Egocentric videos offer a far more scalable source of embodied experience, capturing object interactions, contact dynamics, tool use, and long-horizon behaviors across diverse environments. The central challenge is how to convert this abundant but action-free experience into effective robot control. We introduce ZimaBlue, a scalable framework for learning generalizable World Action Models (WAMs) from large-scale video. ZimaBlue follows a three-stage training curriculum: it first performs causal embodied video pre-training on large-scale human and robot egocentric videos, then grounds the learned visual dynamics in heterogeneous robot trajectories through video-action mid-training with a unified action representation, and finally specializes the model to a target robot for deployment. To make generative WAMs practical for real-time control, ZimaBluefurther adopts an asynchronous Slow-Fast dual-system architecture, where a high-capacity Slow world model provides generalizable spatiotemporal representations and a lightweight Fast branch enables 30 Hz action prediction on NVIDIA RTX 4090. On real-robot zero-shot evaluations, scaling from target-robot data alone to over 120,000 hours of embodied video improves success from 36.1% to 77.8%. ZimaBlue further delivers strong performance across multiple benchmarks, with particularly pronounced gains on unseen tasks. --- ### Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs Authors: Jonathan Zheng, Zirui Shao, Alan Ritter, Wei Xu Published: 2026-08-31 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.00184v2 Large language models (LLMs) rely on static pretraining corpora, causing their knowledge to become outdated over time. Existing approaches for evaluating knowledge edits either suffer from rapid contamination or rely on counterfactual edits that conflict with rigid existing knowledge. In this work, we propose a synthetic, simulation-driven framework for studying knowledge insertion in LLMs. We introduce {\sc ParallelEvents}, a benchmark of fictional yet realistic future worlds that generates coherent event trajectories for controlled evaluation, avoiding contamination while preserving consistency. Building on this dataset, we develop {\sc Synapse}, a training framework that uses model-generated data to update model parameters via mid-training and instruction tuning. This synthetic pipeline enables scalable knowledge integration without costly human-curated data. Empirically, {\sc Synapse} outperforms existing methods by 14.23\%, demonstrating that simulation-based synthetic training leads to robust and coherent knowledge insertions. --- ### Intelligent Edge Computing Authors: Kalgi Gandhi, Minal Bhise Published: 2026-08-31 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2609.00181v1 The number of edge devices in large-scale edge systems is rapidly increasing. Edge devices have limited processing power, memory, and network bandwidth, making resource utilization and data management during edge query processing challenging. Joins are among the costliest database operations in terms of time and resources. The State-of-the-Art edge query processing, Column Imprint-Hash Join CI-HJ, addresses this challenge using equi-height binning to accelerate hash joins. However, it lacks efficiency in real-time processing and scans unnecessary cachelines. This paper presents Workload Aware Column Imprint-Hash Join WACI-HJ, which uses a workload-aware approach to accelerate hash joins. Predicting the upcoming query workload in advance further improves its suitability for real-time edge query processing. WACI-HJ comprises two phases: WACI-HJ Generation Phase, including Pre-processing, Prediction, and Blocking and Hashing modules to compute bins based on the predicted workload before query arrival, and Query Processing and Resource Utilization, which handles query processing and CPU, RAM, and I/O utilization. Evaluations on a benchmark dataset and a real-world Smart Transportation dataset show a 54% reduction in cachelines read and 10% improved query execution time. The proposed technique is effective for both scaled and skewed data. Although PCR is an indirect measure of energy consumption, the work also directly measures energy consumption through energy-efficiency experiments. WACI-HJ shows 1%, 38%, and 49% gain in CPU, RAM, and I/O, respectively. Optimizing cache usage and query execution speeds up real-time traffic analysis, congestion management, and routing in Smart Transportation. Additionally, this technology can be applied to other domains to accelerate edge query processing. ---