# Research Papers — 2026-08 · bundle page 18 of 240 > Full-text markdown of papers #851–900 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/18 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/17.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/19.md) ### Argument-Aware Semantic Alignment of Normative Texts: A Toulmin-Based Neuro-Symbolic Approach Authors: William Schroeder Published: 2026-08-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.29529v1 Semantic alignment between specialized normative texts is challenging when equivalent requirements use different terms, syntax, and levels of abstraction. Lexical overlap, distributional embeddings, and semantic similarity capture topical relatedness but often miss the argumentative structure by which normative claims are supported, qualified, and justified. This paper asks whether explicit argument structure adds information complementary to neural semantics for aligning requirements. We treat cross-standard control mapping as argument-aware semantic alignment and build a neuro-symbolic pipeline that combines neural text representations with Toulmin features. An LLM explicitation step identifies claims, grounds, warrants, qualifiers, and backing and reconstructs enthymemes. These feed an alignment model via argument-aware similarity and structural features. On a NERC-CIP to NIST-CSF mapping benchmark, argument-derived features improve alignment over a neuro-symbolic semantic baseline. Feature selection shows especially strong signal from warrant-related features, indicating that the link between a claim and its supporting reasoning is not captured by conventional similarity alone. A compact claim--grounds--warrant subset remains competitive with the full Toulmin feature set. The results give preliminary evidence that argument structure is a useful intermediate representation for aligning specialized normative texts. Cybersecurity standards are used as a controlled testbed, not as proof of domain-independent generalization. The argument graphs produced by LLM explicitation may also support later work on retrieval, reasoning, and explanation over normative text. --- ### MedCache: Efficient and Temporally Valid Memory for Longitudinal Clinical Agents Authors: Hei Ting, Chan, Chenwei Wu, Xueshen Liu, Boyuan Zheng, Liyue Shen, Jiasi Chen, Z. Morley Mao Published: 2026-08-30 Categories: cs.LG, cs.DC, cs.MA arXiv: https://arxiv.org/abs/2608.29528v1 Longitudinal clinical agents must maintain an evolving patient state from evidence distributed across visits, time points, and specialties. However, how agent memory should be designed for this setting remains unclear. We introduce a benchmark of multi-visit, multi-specialty patient records that evaluates long-context evidence retrieval, cross-time evidence aggregation, and cross-specialty clinical reasoning. Using this benchmark, we systematically study four memory design choices: curation, organization, retrieval, and memory-augmented reasoning. We find that temporal validity is more important than simply retaining more history; specialty-factorized memory reduces context but can hide shared evidence; and multiple agents help when specialists must reason together, not merely when evidence comes from multiple memories. Guided by these findings, we propose \textit{MedCache}, a hybrid framework that constructs temporally valid patient memory, organizes evidence into overlapping specialty views, routes each query to relevant memories, and adaptively invokes one or multiple specialists. Experiments show that MedCache improves reasoning accuracy and memory efficiency over strong single-agent and multi-agent baselines, while generalizing across model backbones and external datasets. --- ### Ontology-Guided Multi-Agent Extraction of Evaluation Objects from Academic Review Texts: Evidence from Chinese Library and Information Science Authors: Haolin Chen, Hongyi Dong, Yu Zhu, Yijia Hong, Leiqing Niu, Jiyuan Ye Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29526v1 Academic reviews, scholarly commentaries, and book reviews serve as sources of evaluative statements about theories, methods, literature, institutions, and policies, providing valuable evidence for scholarly evaluation. Existing scientific entity extraction methods mainly target research articles and are less effective for evaluation objects, which are often abstract, context-dependent, and characterized by ambiguous type boundaries. This study proposes an ontology-guided multi-agent framework for evaluation object extraction. The framework combines candidate discovery, ontology-constrained classification, and domain review. Experimental results show that it achieves a Precision of 90.33%, Recall of 84.55%, Entity-level F1 of 87.34%, Strict Typed F1 of 79.78%, and Type Accuracy of 91.35%, substantially outperforming rule-based and zero-shot baselines. Ablation results indicate that the multi-agent workflow improves recall and stability, while ontology-based boundary constraints enhance fine-grained classification and reduce category confusion. The framework supports the structured utilization of evaluative scholarly texts and provides methodological support for evidence-based research evaluation and STI mining. --- ### Online Gate-Driven Flow Control in Resin Transfer Moulding Using a Neural-Network Surrogate Authors: Nicholas Wright, Oliver Maclaren, Piaras Kelly, Suresh Advani, Ruanui Nicholson Published: 2026-08-30 Categories: math.OC, stat.ML arXiv: https://arxiv.org/abs/2608.29521v1 In resin transfer moulding, complete saturation of the fibre preform is necessary before the resin front reaches the outlet vent(s), to prevent dry-spot formation. In practice, the flow front rarely advances uniformly due to race-tracking effects. We propose a combined estimation and control strategy to address this issue. We use pressure-sensor data collected during filling to estimate the unknown race-tracking strengths via an iterated extended Kalman filter, and to simultaneously optimise auxiliary gate pressures to prevent the resin from arriving at the vent before complete saturation occurs. To make this approach feasible in real time, we replace the expensive finite element-control volume model with neural network surrogate models. The Bayesian approximation error framework is used to account for the discrepancy between the surrogates and the original model. To make the training of the surrogates feasible with time-dependent control actions, we prove that the flow-front geometry depends only on the time-averaged gate pressures. We demonstrate the methodology on a representative forked geometry, showing that the combined estimation-and-control framework can substantially reduce the number of unfilled nodes at the end of filling compared with an uncontrolled baseline. However, the level of improvement depends strongly on the location and number of auxiliary gates. --- ### FuncRoom-Agent: Sequential Feed-Forward 3D Functional Indoor Scene Generation Authors: Hao Feng, Zhi Zuo, MingJian Liang, Jingyu Hu, Xiaowei Hu, Liupengfei Wu, Dian Zhang, Guoxin Fang, Zhengzhe Liu Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29519v2 We introduce Function-Room Generation, a new indoor 3D scene generation setting that creates rooms supporting explicit functional goals rather than merely visually plausible layouts. Existing agentic and executable methods improve controllability, but often depend on costly test-time generate--evaluate--revise loops, making functional room generation slow and computationally expensive. We address this challenge with three technical contributions. First, we design a recursive domain-specific language to effectively organize the hierarchical object compositions required by functional rooms, from room structure and major furniture to dense support-surface and nested small objects. It represents rooms as staged executable programs with explicit geometric and functional relations. Second, we propose a sequential feed-forward scene construction framework that distills recursive construction traces into a scene construction expert. At inference time, the expert writes executable DSL code stage by stage, and a deterministic executor directly instantiates each stage without teacher agents, online critics, or iterative repair. Third, we introduce ScenePRM, an execution-grounded process reward framework that improves the expert through reinforcement learning with functional, geometric, relational, and future-constructability feedback. We further establish a function-oriented benchmark and show state-of-the-art performance on both general indoor scene generation and function-room generation, achieving stronger functional completeness, relation correctness, geometric executability, and generation efficiency. --- ### LLM Judges as Raters: A Pre-Registered Audit of Severity, Halo, Reliability, and Version Instability in LLM Essay Scoring on Public Corpora Authors: Veerendra Kumar Sunkavalli Published: 2026-08-30 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2608.29517v1 Large language models (LLMs) are increasingly used as essay graders in learning analytics, evaluated almost exclusively with agreement statistics. Educational measurement warns that raters also differ in severity, show halo, and drift as instruments. We treat LLM judges as raters and run a pre-registered rater-effects battery (many-facet Rasch severity, residual halo, generalizability/decision studies, cross-version shifts, differential functioning) on public corpora in two languages (ENEM/Essay-BR; ASAP): 2,377 essays, 12 judges, 4 providers, 5 version contrasts, replicated cells, released as a score tensor. Judge severity spans 219 points on ENEM's 0-1000 scale; on ASAP the panel spread is 15-33% of the score range against a between-trained-human gap near 1%. Judge-human correlations sit in an undiscriminating .47-.56 band. All five version contrasts shift severity beyond a family-wise permutation null (up to 133 points), and one judge was deprecated mid-study, caught by identity canaries. Two pre-registered tests returned honest nulls: severity-adjusted leaderboard reversals did not survive a permutation null, and "silent drift" was refuted: agreement moved with severity in four of five contrasts. Replication yields self-consistency (phi>=.80 at k<=2) but not human-level accuracy, and a same-instrument check overturned our own halo comparison: matched on instrument and calibration, we find no credible evidence that judge halo exceeds the trained-human range. --- ### On the Plasticity Collapse in Continual Machine Unlearning Authors: Yingdan Shi, Xiang Xu, Kaize Ding, Alfred O. Hero, Ren Wang Published: 2026-08-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.29513v1 Machine unlearning enables deep neural networks to selectively remove the influence of specific data in response to privacy and regulatory requirements. While prior work largely studies single-shot unlearning, real-world systems must accommodate continual unlearning, where multiple unlearning requests occur sequentially over time. In this work, we identify a fundamental limitation of this setting: plasticity collapse, a progressive breakdown in a model's ability to effectively forget. Through theoretical analysis of continual unlearning dynamics, we show that continual unlearning operations accumulate geometric constraints in parameter space, leading to saturated subspaces that restrict future updates. This structural effect induces two distinct failure modes: (1) Forward failure -- diminishing forgetting quality for subsequent tasks, and (2) Backward failure -- spontaneous re-memorization of previously forgotten information. Extensive experiments across multiple architectures, datasets, and methods in image classification confirm that plasticity collapse is not an artifact of specific implementations, but a pervasive phenomenon inherent to continual unlearning. Our findings reveal a critical barrier to the long-term reliability of machine unlearning systems and motivate the development of plasticity-preserving unlearning algorithms. Our code is available at https://github.com/TIML-Group/Continual-Machine-Unlearning-Plasticity-Collapse --- ### ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity Authors: Haoran Wang, Matthew Lau, Alec Helbling, Matthew Hull, ShengYun Peng, Mansi Phute, Martin Andreoni, Willian T. Lunardi, Duen Horng Chau, Wenke Lee Published: 2026-08-30 Categories: cs.CV, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.29510v2 Aerial object detection is increasingly deployed in real-world applications, but models remain vulnerable to physical, universal adversarial patches that cause them to miss objects. Furthermore, defenders face the practical constraint of training data scarcity: aerial imagery is costly to collect and label, so a deployment site typically yields hundreds of images rather than the tens of thousands that adversarial robustness benchmarks assume. To tackle model vulnerability and training data scarcity, we propose Adversarial Robustness with Manifold-Oriented Training (ARMOR), a novel defense that realizes the core insights of on-manifold adversarial training (OMAT) in low-data regimes. ARMOR builds on the insight of OMAT to model the data manifold - the compact structure capturing the data's relevant features - to learn and robustify these features during training. While OMAT relies on the data-intensive operations of training large generative models and adversarial training to achieve this, ARMOR adopts a data-efficient approach that reuses labels the detection task already supplies: ARMOR (i) masks image backgrounds to retain object-relevant features, and (ii) injects randomized patches on objects to improve feature robustness. Our low-data experiments with physically-realizable adversarial patches evaluate both query-free transfer attacks and defense-aware attacks. ARMOR maintains strong clean performance of over 0.90 model confidence, while improving adversarial robustness by up to 0.32 in model confidence over state-of-the-art defenses. Physical experiments with printed patches confirm that these gains survive deployment. Overall, ARMOR translates insights from manifold-based training to defend object detectors amidst training data scarcity. --- ### Denoising as Projection: Constrained Optimization with Gradient-Guided Diffusion Authors: Runyu Zhang, Jiawei Zhang, Gioele Zardini, Saurabh Amin, Asuman Ozdaglar Published: 2026-08-30 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2608.29507v2 Diffusion models are increasingly used not only for sampling from learned data distributions, but also for generating samples that optimize task-specific objectives. A common approach is to guide the reverse diffusion process using gradients of an external objective. However, when the data distribution is supported on a structured feasible set, such as a manifold or a constraint set, gradient guidance can move samples away from the learned data geometry. In this paper, we study a simple projected-gradient-guided diffusion update based on the observation that the Stein denoising operator can act as an approximate projection onto the data geometry. The proposed update incorporates the objective gradient inside the denoising step, yielding an inference-time method that uses only a pretrained denoiser and gradient evaluations. We analyze this update as an inexact projected-gradient method for constrained optimization over learned feasible geometries. Our theory covers three settings: linear manifolds, compact convex feasible sets, and compact Riemannian submanifolds. In all these settings, we prove descent and finite-time convergence guarantees. Numerical experiments support the theoretical interpretation and illustrate how the proposed update balances objective descent with preservation of the learned geometry. --- ### Adversarial Online Classification with a Preview Authors: Roi Livni, Sahil Singla Published: 2026-08-30 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2608.29503v1 Worst-case online classification is governed by sequential complexity, such as Littlestone dimension, and can be impossible even for statistically simple classes, such as thresholds of VC dimension one. We study a preview model in which an oblivious adversary fixes an entire labeled sequence of length $T$, a uniformly random subset of size $pT$ is revealed before prediction begins, and the remaining $(1-p)T$ examples are then presented in their original adversarial order. Against the best full-sequence hypothesis evaluated on the unrevealed examples, we characterize the dependence on the preview rate $p$: for binary classes of VC dimension $d$, the optimal excess loss is $Θ(d/p+\sqrt{dT})$, up to the trivial cap at $T$; for multiclass classes we obtain the corresponding $\widetilde O(d_{\rm DS}/p+\sqrt{d_{\rm Nat}T})$ bound with no dependence on the number of labels. Thus a random preview can replace worst-case sequential complexity by classical statistical dimensions without randomizing the online order. To achieve the sharp binary bound, our ChainedPrediction algorithm uses an online analogue of chaining, implemented as a multiscale aggregation algorithm rather than only as an analytic argument. --- ### Target-Aware State-Adaptive $p$-Dirichlet Graph Neural Regression for Non-Invasive Body-Composition Estimation Authors: Nadejda Drenska, Matthew Lemoine, Gowri Priya Sunkara, Yu Wang, Sri Lakshmi Sravani Devarakonda, Steven B. Heymsfield Published: 2026-08-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.29496v1 Accurate estimation of body-composition outcomes, including body fat percentage (BFP), bone mineral density (BMD), and appendicular lean mass (ALM), is important for evaluating metabolic, skeletal, and muscular health. Direct assessment using dual-energy X-ray absorptiometry (DXA), however, requires specialized equipment and involves ionizing radiation. We propose a target-aware, state-adaptive $p$-Dirichlet energy-flow graph neural regression ($p$SADE-GNR) framework for estimating these outcomes from non-invasive anthropometric measurements. A neural encoder maps participant representations to hidden states that are propagated over an outcome-specific participant-similarity graph by a state-adaptive forward-Euler discretization of the graph $p$-Dirichlet energy flow. Graph distances weight each original or latent coordinate by its normalized absolute training-fold correlation with the outcome. Using clinical data from the Pennington Biomedical Research Center and five-fold cross-validation, the correlation-weighted model using the original standardized measurements achieved the lowest root mean squared error in all nine primary outcome-cohort combinations and outperformed previously reported support vector regression or least-squares support vector regression reference values in eight of nine comparisons. Autoencoder, variational-autoencoder, and Gaussian-mixture variational-autoencoder representations generally did not improve primary-outcome prediction or reduce computational cost. In an exploratory age-prediction analysis including ALM, BMD, and BFP as predictors, the correlation-weighted GMVAE model achieved the lowest mean error in all three cohorts. These results support target-aware, state-adaptive $p$-Dirichlet graph neural regression for non-invasive body-composition estimation. --- ### Learning Human Health and Diseases from 24-hour Wrist Movement Authors: Yong Wang, Dylan McGagh, Katya Broomberg, Zizheng Zhang, Jonathan Carter, Junayed Naushad, Laura Brocklebank, Yang Sun, George Nicholson, Dianjianyi Sun, Canqing Yu, Jun Lv et al. Published: 2026-08-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.29494v1 Much of human health and function unfolds beyond the clinic, through the movements of everyday life. Wrist-worn accelerometers capture these movements continuously, yet their rich signals are often reduced to a small set of predefined behavioural summary measures. Here, we present Sensori, a self-supervised foundation model that learns general-purpose health representations directly from 24 hours of raw tri-axial wrist movement. We developed and evaluated the model across four population-based cohorts from the United Kingdom, China and the United States, comprising 122,640 participants contributing 683,617 person-days of free-living recordings. Sensori condensed each day of movement into a representation that captured diverse movement behaviours, demographic characteristics, health axes and physical function. Evaluation in independent cohorts showed that these representations generalised across populations and measurement settings without retraining. When added to common clinical covariates, Sensori significantly improved prevalent disease classification for 52 of 102 eligible conditions (median delta AUROC, 0.060; range, 0.012-0.242) and incident disease risk prediction for 26 of 87 eligible conditions (median delta Uno's C-index, 0.064; range, 0.025-0.172), with the largest gains for neurological and psychiatric disorders. These findings establish 24-hour wrist movement as a rich and scalable source of health information, with the potential to support passive health monitoring and disease prediction at population scale. --- ### CoCoA: Context-Conditional Cultural Alignment for Large Language Models Authors: Kyungdon Lee, Wei Xu, Alan Ritter, Dong-Ho Lee, JinYeong Bak Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29492v1 Large Language Models (LLMs) often favor Western-associated entities across cultural contexts. Conventional debiasing methods aim for uniform neutrality, but cultural bias mitigation demands context-conditional behavior, preferring culturally appropriate entities when cultural cues are present and remaining neutral when they are absent. We propose CoCoA (Context-Conditional Cultural Alignment), a framework that learns this behavior through dual-context training on the same entity pairs under contexts with and without cultural cues. CoCoA combines a contrastive alignment objective with calibration and drift regularization, optimized through goal-aware gradient reconciliation. We evaluate CoCoA on CAMeL and Camellia, two entity-centric cultural bias benchmarks, across ten language settings and four LLMs. CoCoA reduces the Cultural Bias Score from 43 to 24 on average while maintaining near-neutral preferences at 50.2, with minimal impact on general performance across five standard benchmarks. These findings highlight that effective cultural alignment requires context-conditional modeling rather than uniform debiasing, and establish a new direction for mitigating entity-centric cultural bias in LLMs. --- ### Generalizable Multi-Agent Planning from Signal Temporal Logic Specifications via Diffusion Authors: Joe Eappen, Zikang Xiong, Shreyash S. Iyengar, Suresh Jagannathan Published: 2026-08-30 Categories: cs.MA, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2608.29490v1 Multi-agent systems in the real-world (e.g., drone swarms, autonomous cars, warehouse robots) must satisfy rich, temporal tasks while avoiding collisions. Signal Temporal Logic (STL) elegantly encodes such objectives, but current STL planning methods face critical limitations. State-of-the-art optimization-based approaches can handle arbitrary STL specifications but struggle with scalability, becoming computationally impractical as the number of agents grows. Learning-based methods efficiently handle a large number of agents with rapid planning times but fare poorly when deployment-time objectives differ from those used during training, and do not support planning tasks that require different specifications to be ascribed to different agents (i.e., heterogeneity) or team-level specifications requiring coordination of multiple agents. This fundamental trade-off between generalizability and scalability presents a challenge for realizing multi-agent STL planning algorithms in practice. To overcome this challenge, we introduce a new diffusion method for multi-agent planning with STL specifications. Using a differentiable approximation of STL, we integrate the STL gradient in the denoising process, making our approach generalizable to novel formulas whose predicates are placed anywhere within the goal region covered during training, while achieving the same scalability as existing learning-based methods. Our method supports heterogeneous specifications, and by using diffusion models, naturally enhances plan diversity, thereby significantly reducing safety-related violations (e.g., collisions) among agents. A detailed evaluation study justifies the utility of STL-guided diffusion-based multi-agent planners for constructing generalizable, scalable, and diverse plans. Videos and code are available at https://www.jeappen.com/diff-ma-stl/ and https://github.com/jeappen/diff-ma-stl . --- ### SpatialTrust: A Benchmark for Environmental Risk Recognition in Secure Authentication Authors: Junbin Lu, Hsiang-Wei Huang, Saesha Wadhwa, Yu Ting Hsu, Jenq-Neng Hwang Published: 2026-08-30 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2608.29489v1 Visual environmental risk recognition plays an important role in secure authentication, where a user's surroundings may reveal sensitive information or introduce potential security risks. However, existing evaluations of multimodal large language models (MLLMs) rarely examine whether models can reliably recognize, localize, and explain such risks in spatially grounded authentication scenarios. We present SpatialTrust, a question-answering benchmark for evaluating environmental risk recognition in secure authentication. SpatialTrust assesses five complementary abilities: sensitive factor detection, direct factor identification, indirect factor identification, direct factor explanation, and indirect factor explanation. We evaluate both proprietary and open-source MLLMs and find that current models show limited performance, especially in understanding and explaining indirect risks, indicating that spatial risk awareness remains a challenging capability for MLLMs. In addition, we introduce SpatialTrustGuard, a structured QA-and-audit pipeline that improves Qwen3-VL-30B-A3B-Instruct from 36.78% to 41.12% overall. Our findings highlight the need for dedicated benchmarks and structured inference methods to improve the trustworthiness of MLLMs in secure authentication. --- ### GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation Authors: Arka Mukherjee, Soham Roy, Kartikeya Trivedi, Shreya Ghosh Published: 2026-08-30 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2608.29483v1 Modern Vision-Language Models (VLMs) perform well above the human baseline in image geolocalization, a task critically important in disaster response, OSINT verification, and location privacy. However, most efforts to study AI behavior on the task remain limited to static image-based retrieval, classification, and predictions. We argue that faithful recreation of the task should involve embodied navigation, where a multimodal agent autonomously explores its surroundings to gather observations before submitting a prediction. To this end, we introduce \textbf{GeoAgent}, an agentic environment-based benchmark that requires agents to navigate Street View environments to refine their geolocalization through sequential reasoning. Our analysis shows that modern VLMs struggle to discern regional patterns while succeeding at country- and continent-level predictions. When compared to static image-based baselines, agentic navigation significantly improves accuracy across established metrics. We also note severe bias in a developed/developing region context across frontier model architectures and poor self-improvement capabilities given incorrect priors. Overall, our work establishes the challenges of embodied navigation and geospatial reasoning. We publicly release our code and the GeoAgent environment: https://geoagent-benchmark.github.io --- ### SIC-Agents: Benchmarking and Building an Adaptive Simulator for Pediatric Serious Illness Communication Training Authors: Zihan Wang, Anita Marie Slominska, Rennie Bimman, Elizabeth Di Flumeri, Amanda Mayappo-Neeposh, Conall Francoeur, Tamara Ellen Carver, Xiao-Wen Chang, Doina Precup, Esin Darici Haritaoglu, Ismail Haritaoglu, Akshatha Arodi et al. Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29481v1 Pediatric serious illness communication (SIC) is critically important, yet scalable communication training for clinicians remains limited. Compared with other dialogue simulation settings, pediatric SIC poses additional challenges, including multi-party interactions, response to parental distress and strong dependence on feedback dynamics. Existing LLM-based simulators optimize generic dialogue quality rather than curriculum-contingent behavior required for effective SIC training. In collaboration with educators and pediatric clinicians, we introduce the first benchmark suite and simulation framework tailored to pediatric SIC training. Our benchmarks, PitfallBench and DialogueBench, evaluate simulators both at the turn-level and across full dialogues. We further propose SIC-Agents, a self-improving framework that generates a clinician-editable skill document to guide simulator behavior. Our experiments show that SIC-Agents outperforms static expert prompting. To support future research, we release our benchmarks for parent simulation in pediatric SIC at https://github.com/Beikewzh/sic-benchmarks --- ### Applications of Risk Science to AI Fairness Evaluation: Principles, Challenges, and Best Practices Authors: Kyra Wilson, Sabrina Kang, Saloni Dash, Aylin Caliskan Published: 2026-08-30 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.29478v1 Scholarly work which aims to describe potential societal impacts (e.g., risks) of proliferating technology (especially related to artificial intelligence or other algorithmic systems) is likely to have an impact beyond the scientific communities it was written for, given that general society itself is a primary object of study. However, it is an open question whether the current practices of AI evaluation scholarship follow the principles and best practices established by risk science, which aims to systematically generate knowledge related to understanding, assessing, communicating, managing, and governing risk. In this work, we examine this in depth by conducting a literature review of scholarly works purporting to evaluate the bias or fairness of technological systems used for tasks related to hiring and employment. Through analysis of 22 common fairness evaluation metrics and studies using them, we find that most characterize the severity of bias- or fairness-related consequences but do not follow best practices to characterize the uncertainty around either the occurrence of these consequences or severity estimates. Next, we conduct a case study of fairness evaluation for an AI-mediated resume screening task and demonstrate how principles of risk science can be incorporated into such an evaluation. Finally, we propose the AI Risk Report Card, which facilitates the reporting and communication of risk assessment results to stakeholders in positions to act based on the predicted risks. The outcomes of these activities suggest that further research at the convergence of risk science and AI evaluation can lead to advancements in AI assessments of societal impact by enabling shared frameworks to evaluate and discuss AI risks both within and outside of the scientific community. --- ### MUDDLE: Measuring Understanding of Documents under Distractor and Length Effects Authors: Jason Luo, Saibilila Abudukelimu, Judy Song, Andrew Feng, Shivank Garg, Vasu Sharma, Kevin Zhu Published: 2026-08-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.29477v1 Document question-answering systems increasingly answer questions over collections of retrieved documents rather than one clean source, so robustness to distracting context matters as much as reading ability. When such systems fail, it is often unclear whether the context was too long or the distractors were too close to the topic, because prior work tends to conflate these two effects. We present MUDDLE, a controlled benchmark that separates them. MUDDLE uses 270 human-annotated questions, each tied to a single source document, and instantiates every question in five conditions: the source alone, the source with two or four topically similar hard negatives, and the source with two or four random distractors. The random distractors are matched to the hard negatives in length and provenance, so an accuracy gap between the two arms reflects topical similarity rather than length. All five conditions are rendered in markdown, page images, and raw PDF, but the distractor sweep reported here is run in markdown, since a source plus its distractors exceeds current image and PDF input limits. We score answers with an LLM judge across three model families. In the complete markdown sweep, hard negatives lower accuracy more than length-matched random documents at both context sizes for gpt-5-mini, while random documents stay near the no-distractor baseline. The effect is small but directionally consistent, and for gpt-5-mini hard negatives significantly underperform length-matched random distractors when pooled across context sizes. We release the data and evaluation code for a reproducible study of context degradation. --- ### Seeing Through Extreme Visual Sparsity: Surface Understanding from a Single Random Visual Patch Authors: Sindhuja Penchala, Sudip Mittal, Noorbakhsh Amiri Golilarz Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29475v1 Surface material recognition from incomplete visual observations remains a challenging problem in robotic perception and environmental understanding. This paper discusses Sparse Surface Understanding Framework (SSUF), a unified dual-task learning framework that adapts four pretrained architectures-Convolutional Autoencoder (ConvAE), Vision Transformer (ViT), Swin Transformer, and Masked Autoencoder (MAE) for si-multaneous surface reconstruction and material classification. Experiments were conducted on the Touch-and-Go dataset using a sparse observation protocol in which only 10% of the original image remained visible while the remaining regions were masked. To enable a fair comparison, reconstruction-oriented models were extended with classification heads, whereas classification- oriented models were augmented with reconstruction decoders. The resulting architectures were assessed using reconstruction quality, classification performance, model complexity, and in-ference efficiency metrics. Experimental results revealed distinct strengths across the models. Swin Transformer achieved the best classification performance with an accuracy of 89.21%, an F1-score of 0.8922, and a ROC-AUC of 0.9813. In contrast, MAE produced the highest reconstruction scores among evaluated models, with a PSNR of 16.06 dB and an SSIM of 0.4501, while ViT provided the best overall balance between reconstruction and classification performance. Furthermore, all models achieved real-time inference, requiring less than 5 ms per image. Over-all, the results show that pretrained architectures can support material recognition under severe visual sparsity, while accurate image reconstruction remains challenging. --- ### Ingest-Time Fact Compilation for Cost-Efficient and Reliable Question Answering over Revised Corpora Authors: Kyle Wild, Yusuke Takahashi, Asako Uraki Published: 2026-08-29 Categories: cs.AI, cs.DB, cs.IR arXiv: https://arxiv.org/abs/2609.29661v1 Most agentic question answering (QA) systems do an important part of their semantic work at the worst possible time: every time someone asks a question. When a corpus contains revisions, drafts, revocations, deletions, and sources with different levels of authority, the model must reconstruct the governed current state on every read - then throw that work away and repeat it on the next query. This is a bit like a database that rebuilds a materialized view every time someone reads from it. We present ingest-time fact compilation, an architecture that performs this work when corpus data is ingested or changed. Raw passages are rephrased into self-contained facts; rules governing revisions, deletions, effective dates, and source trust are resolved once; and the resulting state is stored as typed records carrying source and revision provenance. At query time, an inexpensive model reads the compiled record instead of reconstructing it from noisy candidates. In a controlled synthetic experiment across five seeds, the same low-cost model produced the correct value, source, and revision in only one of 30 trials under query-time reconstruction, but in all 30 trials from the compiled substrate, at 12.89 times lower mean read cost per question. On simpler revision questions both architectures were exact, but the compiled path used 21.6 times fewer tokens. A separate test found that fact rephrasing roughly halved verbose Federal Reserve dialogue while preserving high source entailment, but left concise Wikipedia prose essentially unchanged. These results support a narrow but practical claim: resolving a corpus state once can make subsequent QA cheaper and more reliable for inexpensive models. We release the open source, MIT-licensed implementation and experimental artifacts. --- ### How To Do Things With Prompts Authors: Kristina Šekrst, Virna Karlić Published: 2026-08-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.29657v1 When users address large language models, they produce directive speech acts whose pragmatic features differ from those of both everyday conversation and traditional human-computer interaction, and these features change as users gain familiarity with the systems they address. This paper applies speech act and politeness theory to a corpus-pragmatic analysis of 2,000 English-language prompts drawn from publicly shared ChatGPT conversations, 1,000 from 2023 and 1,000 from 2025, using the ShareChat dataset. Each prompt is annotated for illocutionary force, directness, propositional content, and the presence of politeness markers, and the distribution of these features is compared across the two sampling years. The results show a consistent movement toward indirect, implicit, and fragmentary realizations of directive force, accompanied by a decline in politeness marking. The largest single change, a shift of 14.9 percentage points, occurs in propositional content, where explicit specification of the requested action gives way to implicit reliance on the system's inferential capacity, suggesting that users have updated their model of what the system can recover from reduced input, treating it as a competent implicature resolver. Rather than asking whether LLMs "really" understand language, we should ask: what kind of language have we created in learning to speak to them? --- ### VG-TIE: An interpretable tabular-to-image encoding method based on visibility graphs Authors: David Chushig-Muzo, Luis M. López-Ramos, Ángeles Rodríguez de Cara, Eva Milara, Luis Zhinin-Vera, Diego H. Peluffo-Ordóñez Published: 2026-08-29 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.29650v1 Tabular-to-image encoding methods enable the application of models based on both convolutional neural networks and vision transformers to tabular data, transforming feature vectors into images. Existing methods employ linear and nonlinear dimensionality reduction techniques (e.g., Principal Component Analysis (PCA), t-SNE, and UMAP) to determine pixel positions, resulting in images whose spatial layout do not inherently reflect feature relationships. This paper introduces Visibility Graphs for Tabular-to-Image Encoding (VG-TIE), a novel method that encodes the structure of feature values using Natural Visibility Graph (NVG) and Horizontal Visibility Graph (HVG) into a two-dimensional space obtained through PCA. The resulting images are model-agnostic and intrinsically interpretable. Each pixel corresponds to an input feature, its intensity reflects the magnitude and direction of deviation from the population mean, and edges represent formally defined visibility relationships between features. VG-TIE provides two interpretability methods: (i) feature ranking from node degree distributions; and (ii) local and global feature importance from pixel intensity combined with Grad-CAM. Experiments on six public tabular datasets show that VG-TIE is competitive with other tabular-to-image methods while providing interpretability on feature importance and ranking similar to intrinsic interpretable methods. The results highlight the potential of the proposed image-based transformation to provide an effective framework that expands the use of deep learning across tabular data domains. --- ### Albireo: Adaptive, Energy-Efficient Inference Framework for Video Object Detection on the Edge Authors: Amir Taherin, José Cano, Bin Ren, Yanzhi Wang, David Kaeli Published: 2026-08-29 Categories: cs.CV, cs.AR, cs.LG, cs.PF, cs.RO arXiv: https://arxiv.org/abs/2609.29648v1 Video object detection on edge devices runs computationally expensive detectors over long frame streams, causing high energy consumption and sustained GPU utilization. Although consecutive frames are highly redundant, naive frame skipping is content-blind: it skips during critical moments such as object entry, occlusion recovery, and abrupt motion, degrading detection quality. We present Albireo, a detector-agnostic, codec-free adaptive inference framework that wraps off-the-shelf detectors and decides when detector invocation can be safely skipped based on scene content and per-object temporal state, requiring no detector modification or retraining. Albireo maintains a 10-dimensional Kalman filter (KF) per active object and invokes the detector only when prediction uncertainty exceeds a threshold; on skipped frames, boxes are predicted from the KF state at near-zero GPU cost. A KF-based rescue mechanism preserves confirmed objects through brief detector misses to prevent output fragmentation, while a lightweight empty-scene screen avoids detector calls on objectless frames. We evaluate Albireo on the BDD100K MOT validation split with three architecturally distinct detectors (YOLO11x, YOLO26x, RF-DETR-Large) on two NVIDIA Jetson platforms (AGX Thor, AGX Orin). Across all configurations, Albireo keeps AP@50 within +/-1.2 pp of per-frame inference while reducing total energy by 12.1-17.6%. On YOLO26x, it improves AP@50 by +0.8 pp while reducing energy by 17.6% (Thor) and 14.4% (Orin) and per-frame energy-delay product by 24.9% and 26.1%, respectively. Thus, the default operating point improves accuracy, energy, and latency together. In contrast, FixedSkip-2, a fixed-interval baseline with a 50% skip rate, loses 8.6 pp AP@50. Source code, evaluation pipeline, and per-clip results are available at https://github.com/amirtaherin/albireo --- ### AgentKernel: The Trust-Native Agentic Operating System Authors: Zhenhua Zou, Sheng Guo, Qiuyang Zhan, Lepeng Zhao, Shuo Li, Zhuotao Liu Published: 2026-08-29 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.29647v1 Modern AI agents routinely cross trust boundaries: they ingest untrusted content, combine it with privileged instructions, persist intermediate beliefs in long-term memory, and invoke privileged tools. This creates an attack surface in which malicious payloads can enter through model inputs and cause harmful tool actions. Yet current governance stacks remain application-level middleware that share a process trust boundary with the agents they monitor. We argue that agents need an operating-system substrate providing mandatory, non-bypassable services for identity, input mediation, memory governance, and execution control. We introduce AgentKernel, a trust-native agent operating system built around the premise that security must be a first-class design constraint. AgentKernel wraps the agent lifecycle in a mandatory enforcement boundary organized into four pillars: Identity, Perception, Cognition, and Execution. Each pillar adapts classical OS security principles to failures at the semantic plane, including delegation abuse, prompt injection, memory poisoning, and tool misuse. AgentKernel treats structural security as a capability multiplier. Kernel-managed identity supports trustworthy cross-organization collaboration; graduated perception replaces brittle single-point filters; information-flow-controlled memory improves retrieval fidelity while limiting poisoning; and semantic-to-kernel enforcement permits broader tool privileges behind a non-bypassable boundary. We position AgentKernel as the missing OS layer beneath orchestration frameworks, agent runtimes, governance platforms, and execution sandboxes, and use systematic comparison and security analysis to show how a single integrated architecture can enforce security across the full agent lifecycle. --- ### SpectralCTGaussians: Projection-Domain Reconstruction and Basis Material Decomposition for Spectral CT using 3D Gaussian Splatting Authors: Reinout Vos, Saptarshi Neil Sinha, Michael Weinmann Published: 2026-08-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.29638v1 Spectral computed tomography (CT) extends conventional CT by measuring attenuation across multiple energy channels, allowing improved modeling of physical X-ray interactions and energy-dependent material behavior and leading to richer scene understanding. We present a novel method for spectral CT reconstruction and basis material decomposition using 3D Gaussian Splatting by adding per-Gaussian basis material fractions to the set of learnable parameters, which together with a set of energy-dependent basis functions define the attenuation across the full spectral range. The basis functions represent various physical attenuation models such as photoelectric absorption and Compton scattering, and are jointly optimized across all energy channels through a differentiable polychromatic forward model, with material decomposition performed via mean-shift clustering of the resulting coefficients. We evaluate our method on a baseline real-world dataset as well as a synthetic dataset that we introduce, comparing against traditional reconstruction algorithms and state-of-the-art learning-based CT reconstruction methods. Our approach outperforms all traditional baselines in novel view synthesis and achieves the best PSNR among all compared methods for spectral CT volume reconstruction, while describing all energy channels with a single shared representation that requires a number of Gaussians comparable to single-channel Gaussian splatting-based CT reconstruction approaches. For basis material decomposition, no traditional or learning-based baseline offers one-step decomposition with direct RGB material segmentation, and our method additionally recovers the photoelectric basis with higher PSNR than traditional pipelines. --- ### A Manifold-Aware Topic Modeling Approach via Rank-Based Prototypes Authors: Thiago César Castilho Almeida, Daniel Carlos Guimarães Pedronette Published: 2026-08-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.29630v1 Recent topic models leverage pretrained embeddings, but neural architectures produce latent representations without grounding in specific texts, and clustering-based pipelines assign representative documents only post hoc, relying on absolute distances distorted by hubness and anisotropy in high-dimensional spaces. We introduce MARETopic, a training-free framework that casts topic discovery as rank-based prototype selection. After projecting embeddings onto a low-dimensional manifold, MARETopic builds ranked lists encoding ordinal neighborhood structure. A greedy algorithm selects exactly K exemplar documents, real corpus texts, whose neighborhoods cover the corpus. Two variants share this criterion. MARETopic$_\text{Corr}$ scores candidates with a query performance predictor and a rank correlation measure, leading Purity and NMI on the two benchmarks with the most categories, ahead of both neural and clustering-based topic models. MARETopic$_\text{Diff}$ scores them with a rank-based diffusion matrix, needs neither measure, and runs 1.7 to 1.9 times faster. Without a single gradient update, MARETopic leads topic coherence on two of three datasets. A novel inter-topic Maximal Marginal Relevance step raises vocabulary diversity at little cost in coherence. Our code is available at https://github.com/thcastilho/maretopic. --- ### Optimal Recovery Meets Bayesian Learning: Where Worst-Case Bounds Pay Off Authors: Gordei Verbii Published: 2026-08-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.29622v1 Worst-case Optimal Recovery (OR) and Bayesian learning describe the same Gaussian-quadratic-Hilbert problems in two vocabularies. We sharpen the correspondence - the radius of information equals a nugget-optimized GP posterior variance and is attained by the posterior mean at a closed-form balance nugget - and measure, inside three published Bayesian systems, where the worst-case side pays. The ledger is two-sided: the losses instruct as much as the wins. Morozov calibration tracks a test-access oracle within $1.00$-$1.19\times$ where $σ$-blind rules fail, is $4.9$-$6.3\times$ more reproducible across noise draws ($p=0.002$-$0.004$), and is the only deployable rule whose selection survives a change of backend ($1.36\times$ against $12$-$30\times$ for the released weight, ML-II and GCV); tight certificates cover at the information-theoretic floor with no numerical slack. But on exchangeable data split-conformal beats the OR head on interval score, a water-filling prior adds nothing without an oracle noise hint, and under covariate shift the OR band keeps coverage on every dataset yet loses interval score to split-conformal, and to a feature-free constant band, on most cells; what pays is not shift but shift on a learnable target, which a training-free audit statistic predicts before any model is fitted. In Bayesian optimization the certified width is a validity floor whose scalar inflation we prove inert under a checkable margin condition and check at every step. Inertness is graded, not binary, and in the size of the inflation as much as in the objective: $κ{=}2$ is inert wherever $κ{=}5$ is and on more cells besides, while $κ{=}5$ moves half the Ackley seeds and every Griewank seed. Exploration is a shape problem, not a scale one. The design rule: match the guarantee tool to the data regime, and audit the regime first. --- ### Free the Language Model From the Vision Encoder: Semantic Serialization as a Perception Interface for Small Language Models Authors: Cong Xu, Ravi Sankar Published: 2026-08-29 Categories: cs.RO, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.29601v1 End-to-end vision-language models (VLMs) bind visual competence to the scale of their language model: as the language model shrinks, perception and reasoning degrade together. We study an embodied scene question-answering (QA) interface in which vision never enters the language model. A frozen perception stack detects and ranges objects; a deterministic semantic serializer compiles the perceived state, errors included, into decision-aligned text; an unmodified text-only large language model (LLM) answers. On a visible-scope-matched, occlusion-audited campus-robot benchmark, under a prospectively frozen criterion, the serialized interface, using detectors fine-tuned in-domain within each fold, outperforms a zero-shot VLM whose language model has the same 7B scale (0.7892 vs 0.7462), with a larger margin at 3B (0.7673 vs 0.6913). Preregistered decoupling experiments show the gain survives paraphrase, attributing it to decision-aligned computation rather than answer-string leakage, while novel judgment vocabularies bound its scope. The advantage grows as the reader shrinks to 1.5B and reverses at 0.5B, and a ground-truth oracle locates the reader-capability floor. Under matched task supervision the interfaces converge: a VLM fine-tuned with low-rank adaptation (LoRA) overtakes the zero-shot system but only ties an equally supervised text reader (0.8441 vs 0.8396, no statistically resolved difference), and both routes remain perception-bound. Reported perception parameters are comparable to those of the VLM's vision tower, and total compute is not smaller. --- ### A Pinch of SFT, A Dash of RL: When Reinforcement Learning Helps Long-Horizon Advertising Agents Authors: Aakash Kolekar, Sahika Genc, Bunyamin Sisman, Shahriar Shariat, Shree Vandana Kachroo, Avishek Saha, Qianli Wu, Ari Singer, Benoit Dumoulin Published: 2026-08-29 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.22194v1 Enterprise analytics agents solve long-horizon tool-use problems over distributed business data, requiring retrieval, reasoning, API calls, code execution, and adaptation to intermediate observations. Supervised fine-tuning (SFT) calibrates tool syntax and teacher-supported behavior, whereas reinforcement learning (RL) can explore reward-supported behaviors beyond demonstrations; applied uniformly, however, RL can perturb already-calibrated skills. We study how to balance SFT and RL under production-mirroring beta APIs. We observe that, in our controlled experiment, checkpoint trajectories retrospectively separated into three regimes: Imitation, where SFT captured reliable teacher behavior; Lift, where both stages helped; and Discovery, where useful reward-observable behavior lay outside reliable teacher support. We leverage this prospectively, using teacher support and reward-observable headroom to route features to SFT only, SFT then RL, increased RL allocation, or further environment development. Across 18 subsequent feature-specific experiments, the diagnostic predicted 15/18 observed trajectories. On GPT-OSS 120B, targeted SFT then RL produced positive point estimates on 7/8 advertiser skills relative to a frontier Control; five positive gains had paired 95% confidence intervals excluding zero, while one skill had a confidence-supported regression. The largest gain was non-disclosure (+11.27 points; 95% CI (+9.72, +12.82)). A separate SME audit surfaced that targeted RL reduces standard leakage from 11.8% to 2.9% and adversarial leakage from 22.9% to 6.8% relative to SFT while preserving actionability (86.2% to 85.7%). In a matched uniform-versus-targeted comparison with shared rewards and optimization, targeted RL improved the seven-skill mean delta from +1.62 to +3.57 while using 43% less incremental RL compute. --- ### SegTSim: A Big Data Driven Segmented Temporal Simulation Framework for Heterogeneous Multivariate Systems Authors: Xinhang Li, Chenxi Geng, Yujia Sun Published: 2026-08-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.22192v1 Heterogeneous multivariate time-series systems exhibit segment-specific nonlinear dynamics that challenge monolithic forecasting architectures. We propose SegTSim, a big-data-driven segmented temporal simulation framework that integrates segment-specific elasticity modeling with adaptive min-gating, dynamic production relocation optimization, multi-factor data fusion with exchange-rate propagation, and a deep ensemble validation pipeline. The framework is validated on US--Japan automotive trade data from USITC repositories spanning 2015 to 2025, comprising approximately 13000 annual records. Under a 25% perturbation scenario, Japanese import volume declines by 20.4% to 0.93 billion USD, while all output variables maintain coefficients of variation below 3.5% across 1000 ensemble inference runs. --- ### WildfireSpreadBench: The Metric Decides the Model in Wildfire Spread Prediction Authors: Arin Gopakumar, Marco Pannozzo Published: 2026-08-29 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.22191v1 Machine learning is being increasingly used to predict where active wildfires will burn the following day, helping inform evacuation boundaries and containment lines. Most models are evaluated using Average Precision (AP), which summarizes performance across all decision thresholds, although acting on a forecast requires choosing one. We benchmarked five discriminative architectures and one generative model on WildfireSpreadTS using a shared evaluation pipeline and two input configurations. We found that model rankings varied depending on whether performance was measured by AP or by threshold-dependent metrics like F1 and IoU. The highest-AP model flagged 4 to 5 times the area that burned and ranked fifth of six on F1 and IoU, and the most recall-heavy model flagged 16 to 23 times. Models with more usable predictions had AP scores 24 to 37 lower. Across architectures, we identified three distinct prediction profiles: over-predicting, balanced, and under-predicting, which AP alone could not distinguish. Expanding the input from 7 to 23 channels changed AP by 0.03 on average, against a 0.21 to 0.24 spread across architectures. These results show AP alone can favor models whose predictions are poorly suited for operational wildfire forecasting. --- ### Cortex: Content Analysis Support Software, a Resource for Qualitative Research Authors: Ana Julia da Silva Soares, Rafael Coimbra Pinto Published: 2026-08-29 Categories: cs.DL, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2609.11970v1 Qualitative research is widely used in the human and social sciences, characterized by a deep understanding of phenomena through the interpretation of meanings and contexts. Among qualitative data analysis methods, content analysis stands out as a consolidated technique, which allows for the systematic description and interpretation of textual contents. However, as data volume increases, the time required for organization, reading, and categorization becomes a significant challenge, potentially delaying research development. Therefore, this work aimed to develop a web application to support content analysis, based on Bardin's methodology, targeted at academic researchers. The methodology adopted a mixed approach, combining bibliographic research on content analysis with semi-structured interviews with four experienced researchers, aiming to identify real needs and requirements. Based on these inputs, the Cortex software was developed to assist the researcher in the pre-analysis and material exploration stages, generating suggestions for indices, indicators, and categories with full traceability to original documents. The results demonstrate that Cortex is capable of guiding the researcher through the entire methodological workflow, from corpus configuration to results exportation, acting as a methodological collaborator without replacing the researcher's interpretative autonomy. --- ### Evidence-Order Calibration for Selective Visual Reasoning under Progressive Loss of Question-Critical Evidence Authors: Muhamathu Ameer Ali Aacaas Muhamath Published: 2026-08-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.09184v1 Vision-language model (VLM) confidence may change in aggregate when visual evidence is degraded while remaining structurally inconsistent within individual examples. We study answer-level reliability along five-step, question-conditioned evidence-loss trajectories. Using a frozen Qwen2.5-VL-3B-Instruct model, we construct 176 accepted GQA-derived trajectories (880 masking conditions) by progressively masking scene-graph-localized question-critical regions. Native sequence confidence has an evidence monotonicity violation rate (EMVR) of 0.436, and 92.0% of trajectories contain at least one adjacent violation. A matched non-critical-region control shows that full critical masking reduces accuracy by 28.2 percentage points, compared with 0.6 points for equally sized non-critical masks; the paired difference is 27.6 points (95% CI (20.0, 34.7)). We train a lightweight post-hoc reliability head on frozen hidden states, sequence confidence, and entropy. Adding evidence-order supervision to binary cross-entropy (BCE) reduces masking EMVR from 0.330 to 0.303 (paired difference -0.027, 95% CI (-0.044, -0.010)). The same mask-trained objective reduces EMVR from 0.449 to 0.402 on held-out question IDs under unseen local Gaussian blur (difference -0.0468, 95% CI (-0.0739, -0.0199)). AUROC, Brier, and AURC differences between the two learned heads are statistically inconclusive, and native confidence remains stronger for selective-risk ranking. The results separate evidence-order consistency from conventional correctness discrimination rather than establishing generic confidence superiority. --- ### Reliable iToF Depth Sensing via Sensor-Intrinsic Uncertainty Modeling and State-Space Restoration Authors: Yansong Du, Yutong Deng, Yuting Zhou, Zhancong Xu, Yingjia Lu, Mengdi Wang, Feiyu Jiao, Bangyao Wang, Zhaoxiang Jiang, Xun Guan Published: 2026-08-29 Categories: physics.optics, cs.CV arXiv: https://arxiv.org/abs/2609.05507v1 Indirect time-of-flight (iToF) cameras provide compact and cost-effective dense depth measurements, but their ranging accuracy is often degraded by sensor-intrinsic uncertainty under practical imaging conditions. Spatially uniform or range-only Gaussian perturbations cannot accurately reproduce the range-dependent and signal-dependent noise characteristics of real iToF measurements, leading to a synthetic-to-real gap for learning-based restoration. To address this problem, we propose a joint depth-uncertainty modeling and restoration framework for reliable iToF sensing. A sensor-intrinsic depth-uncertainty model is first developed from calibrated tap responses, returned-signal levels, and sensor noise statistics through a depth-oriented weighted least-squares formulation. The resulting pixel-wise uncertainty is used for heteroscedastic depth synthesis and uncertainty-aware restoration supervision. Based on this heteroscedastic data synthesis, we further develop a U-shaped restoration network with Depth Visual State Space (DVSS) blocks, which combine long-range state-space modeling with convolutional spatial-channel refinement for structure-preserving depth recovery. Experiments on synthetic data and measurements captured by an in-house iToF prototype validate the proposed uncertainty model under varying range and returned-signal conditions. Controlled comparisons with fixed and range-aware Gaussian noise, together with evaluations on U-Net, Restormer, and DVSS, further demonstrate that the proposed synthesis consistently benefits different restoration backbones. The complete framework achieves 40.85~dB PSNR and 2.54 mm MAE on the synthetic test set, and 35.42 dB PSNR and 4.87 mm MAE on real iToF measurements. --- ### ECHO: Dyadic 3D Facial Motion Generation with Asymmetric Deterministic Articulation and Stochastic Reaction Authors: Zhuoqiang Cai, Yujie Sun, Chaoyue Niu, Hongyun Yu, Zhiwen Chen, Chengfei Lv, Fan Wu Published: 2026-08-29 Categories: cs.GR, cs.CV, cs.SD arXiv: https://arxiv.org/abs/2609.05506v1 We propose ECHO for dyadic 3D facial motion generation under a strict dual-stream audio-only setting, formulating the problem as an asymmetric task involving speech-constrained articulation and one-to-many listener reactions. To address this asymmetry, ECHO decomposes motion into a deterministic anchor that captures stable speech-correlated structure and a stochastic residual that models the remaining one-to-many interaction dynamics. On top of this backbone, Motion Memory acts as a training-only regularizer during brief late-stage fine-tuning to provide local priors for weakly conditioned listening windows, while semantic-group scaling controls residual injection across expression, jaw, and neck. This design balances speaking-side articulatory fidelity with listening-side realism and diversity in a single generation process. Results from unified, state-wise, and ablation evaluations show that conversational 3D motion benefits from decomposing stable and uncertain components rather than applying stochasticity uniformly. ECHO provides a practical formulation and technical basis for deployable conversational digital humans under strict audio-only conditions. --- ### SciLitBench: Benchmark and Design Principles for LLM-Powered Systematic Literature Reviews Authors: Miguel Zabaleta, Baihan Lin Published: 2026-08-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.05505v1 Systematic reviews require sustained human judgment across thousands of records, yet existing evaluations of large language models (LLMs) typically examine review stages in isolation. We introduce SciLitBench, a multi-stage benchmark spanning title and abstract screening, full-text screening, and schema-guided data extraction, with 42,981 retrieved records, 1,012 full texts, and annotations for 888 included papers. Across 22 open-weight LLMs from six model families, explicit inclusion and exclusion criteria improve title and abstract screening $F_2$ by 28.8\%, while researcher-authored rationales improve full-text screening by 15\%. Data extraction reveals a different reliability regime: performance declines from 0.97 accuracy for publication year to 0.37 Jaccard overlap for computational approach, while the strongest models recover only 30\% of annotated evaluation evidence and 25\% of limitations. SciLitBench identifies a practical boundary between high-recall screening and evidence-complete extraction and provides a reproducible resource for evaluating LLM-assisted evidence synthesis. --- ### Efficient Context-Limited Telescope Bibliography Classification for the WASP-2025 Shared Task Using SciBERT Authors: Madhusudhana Naidu Published: 2026-08-29 Categories: cs.LG, astro-ph.IM arXiv: https://arxiv.org/abs/2609.01647v1 The creation of telescope bibliographies is a crucial part of assessing the scientific impact of observatories and ensuring reproducibility in astronomy. This task involves identifying, categorizing, and linking scientific publications that reference or use specific telescopes. However, this process remains largely manual and resource intensive. In this work, we present an efficient SciBERT-based approach for automatic classification of scientific papers into four categories - science, instrumentation, mention, and not telescope. Despite strict context-length constraints (maximum 512 tokens) and limited compute resources, our approach achieved a macro F1 score of 0.89, ranking at the top of the WASP-2025 leaderboard. We analyze the effect of truncation and show that even with half the samples exceeding the token limit, SciBERT's domain alignment enables robust classification. We discuss trade-offs between truncation, chunking, and long-context models, providing insights into the efficiency frontier for scientific text curation. --- ### trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories Authors: Hadi Mohammadi Published: 2026-08-29 Categories: cs.CL, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.00038v1 Outcome-only evaluation is the production default for LLM agents: show a judge the request and the final reply and ask whether it was handled well. The metric is structurally blind to an agent that reaches the right answer the wrong way. We measure that blind spot where ground truth is known by construction: a deterministic tool-using support-desk environment, a scripted oracle policy that always solves it, and a fault injector that breaks exactly one thing at a known step, stratifying faults by whether the customer-visible outcome survived (silent) or not (loud). Five judges (programmatic rules, outcome-only, step-rubric at two model sizes, and a self-consistency ensemble) are scored on detection, step localisation, fault typing, calibration, and cost over 400 trajectories. The outcome-only judge catches 84% of loud faults but 45% of silent ones while flagging 33% of correct trajectories; a step-rubric judge reaches 77% silent recall with zero false alarms at 3x the cost. No judge reads the final reply: an invented promise appended to an otherwise perfect trajectory evades the rules entirely and the step judge 82% of the time, and self-consistency triples cost while improving nothing. We argue that judge evaluations must stratify recall by outcome survival, and release the environment, the injector, all raw verdicts, and an analysis pipeline that rebuilds every number offline. --- ### A Globally Convergent Algorithm for Total Scaled-Gradient Variation via Cone-Constrained Bilinear Decomposition Authors: Haibin Su, Chunlin Wu, Huibin Chang, Zhifang Liu Published: 2026-08-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.00036v2 The total scaled-gradient variation (TSGV) regularizer, derived from sparse modeling of piecewise-linear structures, has been shown to preserve edges and corners in image restoration. However, its highly nonconvex and nonlinear nature poses severe computational challenges, as existing methods often suffer from parameter sensitivity or lack convergence guarantees. To overcome this, we propose a tailored bilinear decomposition that decouples the nonlinear weighted gradient in the TSGV regularizer. This approach yields an equivalent optimization problem governed by cone or sphere constraints, depending on the chosen scaling function. In particular, the cone constraint plays a central role in characterizing edge- and corner-preserving behavior. We solve this reformulation using the alternating minimization method (AMM) equipped with a majorization--minimization strategy, ensuring a monotonic decrease in energy without step-size tuning. Furthermore, we provide a geometric interpretation of the edge-preserving properties of these constraints by analyzing their asymptotic behavior near image singularities. We establish the global convergence of the proposed method to a critical point within the Kurdyka--Łojasiewicz framework. Extensive numerical experiments on Gaussian denoising and non-line-of-sight (NLOS) imaging show that the proposed method achieves PSNR and SSIM competitive with or superior to representative variational methods, especially at high noise levels, and improves the structural reconstruction under dense and sparse scanning. --- ### Knowledge Distillation under Teacher Misspecification: An Order-Parameter Analysis of the Gap between Teacher Mimicry and Task Performance Authors: Kazuyuki Hara, Hideitsu Hino Published: 2026-08-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.29472v1 Knowledge distillation trains a small student model to reproduce the outputs of a large teacher model, and its progress is typically monitored through the teacher--student discrepancy. The quantity of ultimate interest, however, is the student's error with respect to the true task. We study the relation between these two objectives in a minimal three-party model, a true teacher (generative model), a teacher, and a student, all soft committee machines, in which the true teacher contains a shared latent factor that the teacher cannot represent, with mismatch strength controlled by a single scalar $\dmiss$. Within an order-parameter description of online distillation, and exploiting closed-form (arcsine-type) expressions for all errors under error-function activations, we prove that the learning dynamics and the distillation error $\Ets$ are exactly invariant to $\dmiss$, whereas the true error $\Etzs$ and the gap $Δ=\Etzs-\Ets$ are strictly increasing in $\dmiss$, with a rate that is amplified linearly by the complexity $M_0$ of the true teacher. Numerical phase diagrams over the plane spanned by true-teacher complexity and student capacity confirm the predicted deformation: the contours of $\Ets$ do not move while the landscape of $\Etzs$ rises systematically, and a teacher-miss regime, where mimicry succeeds but the task fails, expands with $\dmiss$. The results give a quantitative warning against evaluating distillation solely through teacher-mimicry metrics and identify the gap $Δ$ as a minimal diagnostic for distinguishing teacher-miss from capacity-limited failure. --- ### Co-Evolutionary Prompt Optimization with Cross-Category Transfer for Zero-Shot Anomaly Detection Authors: Sisi Zhu, Changwei Yu, Renshuai Tao, Zhenliang Ni Published: 2026-08-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29467v1 Zero-shot anomaly detection (ZSAD) has gained significant attention for its practical value in industrial inspection. Recently, CLIP-based approaches have been widely adopted in ZSAD due to their strong vision-language generalization capabilities. However, existing methods commonly employ continuous prompt embeddings for prompt optimization and encode semantics in latent vectors, which lack interpretability and scalability. To this end, we propose CoEvoAD, a co-evolutionary framework for discrete prompt selection. CoEvoAD performs prompt search in the discrete natural-language space using an evolutionary algorithm. Candidate prompts are iteratively generated, evaluated, and selected throughout population evolution, thus preserving the interpretability and composability of natural language. Furthermore, we introduce a Cross-Category Transfer Objective (CCTO), which treats held-out source categories as proxies for unseen categories and scores prompt rules based on their estimated cross-category transferability, effectively improving cross-category generalization. Extensive experiments are conducted to validate the effectiveness of CoEvoAD, and the results show that it achieves state-of-the-art performance across multiple anomaly detection datasets. The code is available at https://github.com/rstao-bjtu/CoEvoAD. --- ### Deciding When to Decide: Testing Operational Suboptimality Under Distributional Shift Authors: Minxing Zheng, Holly Wiberg, Shixiang Zhu Published: 2026-08-29 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2608.29465v1 Deployed decisions are often optimized once and retained because updates impose operational, regulatory, or switching costs. As operating conditions change, when should such decisions be re-optimized? We study this question for stochastic optimization when the objective's functional form is known but the decision maker's trade-offs are encoded by an unknown preference parameter. Standard distribution-shift tests are poorly aligned with this goal: they can flag detectable yet decision-irrelevant changes without determining whether the incumbent decision has become materially suboptimal. We propose \texttt{RADAR} (Regret-based Assessment of Decision Adequacy and Risk), a decision-focused framework that uses inverse optimization to infer latent preferences and tests the deployed decision's optimality gap under the current distribution. By targeting regret, \texttt{RADAR} ignores decision-irrelevant shifts while detecting changes that warrant re-optimization. We develop two-sample and sequential changepoint procedures and establish asymptotic guarantees for Type-I error and power. Across synthetic optimization problems, a semi-synthetic capacity allocation task, and police-zone planning, \texttt{RADAR} more reliably distinguishes harmful from harmless shifts than decision-agnostic alternatives. --- ### Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered Authors: Aryo Pradipta Gema, Neel Rajani, Rohit Saxena, Wai-Chung Kwan, Pasquale Minervini Published: 2026-08-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.29464v2 Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness tests often place explicit bias cues in the user message, while agents may encounter preferences through tool returns or raw artifacts. We introduce FACE-Eval (Faithful Attribution of Cue Effects Evaluation), a 5,100-sample evaluation that varies cue location (user message or tool return) and explicitness (direct summary or raw artifact). We measure verbalized commitment among cue-following answers and unverbalized adoption among all cued samples. We evaluate 15 open-weight models from eight families, with total parameters ranging from 4B to 1.60T. Every model has lower verbalized commitment for tool-return than user-message cues and for implicit than explicit cues. Unverbalized adoption is higher for tool-return cues on all 15 models and for implicit cues in 28 of 30 model-channel comparisons. A source-attribution prompt narrows the channel gap on seven models, sometimes by increasing user-channel unverbalized adoption, while telling models that their reasoning will be monitored does not reliably close the gap. We also use two transcript monitors (GPT-5.6-Luna and GPT-4o-mini) to detect preference adoption in the largest model of each family. Across 32 model-channel-explicitness cells, higher unverbalized adoption is associated with lower detection ability for both monitors (Pearson r=-0.54 and r=-0.78, respectively). These results suggest that CoT monitoring may be less reliable when preference information arrives through tools or must be inferred from raw artifacts, within the single-call, prefilled-tool setting tested here. --- ### Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation Authors: Johanna Angulo, Víctor Yeste, Hector Espinos-Morato Published: 2026-08-29 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.29463v1 A benchmark score is a joint property of the model, the evaluation harness, the elicitation budget, the sampled population, and contamination status. Leaderboards publish the model and the score, so capability and leakage stay observationally equivalent. Existing taxonomies classify contamination for automated detection, not the question a reporter faces at publication: given the mitigations already applied, which validity threats remain open? We introduce a taxonomy organized by the mitigation each type defeats -- direct, derivative, temporal, distributional, and acquired -- spanning training-time and evaluation-time leakage. Holding out a private test set closes the first alone. The fifth is acquired during the evaluation itself; because it is a property of one run, it must be recorded with the reported score rather than with the benchmark release. We operationalize it as a four-field disclosure protocol in which "unknown" is a valid entry, released under CC BY 4.0 with a JSON Schema, a validator, and worked examples. Two coders external to the design team applied a pre-registered instrument to 41 documents. Per-variable linear-weighted $κ$ runs from 0.00 to 0.35 (median 0.21) over 29 main-pass documents against a single-coder test-retest ceiling of 0.84, collapsing under the class skew the registration anticipated; pooling raises it to 0.46 through chance correction rather than better agreement. Two variables fall below the prevalence-robust threshold registered in advance: strata reporting and the acquired type introduced here. Disagreement concentrates on when a variable applies rather than on what a document states. Elicitation budgets are reported in 13% of documents, and no document addresses all five types. The contribution is the taxonomy, the score-side artifact that follows from it, and a pre-registered measurement of instrument reliability and current disclosure. --- ### A Causal Model for Locating and Unlocking Sandbagging in Model Organisms Authors: Hong Kiat Tan, Linh Le, David Williams-King Published: 2026-08-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.29461v1 Sandbagging models strategically underperform on evaluations while retaining the capabilities being measured. The evaluations that guide frontier-model deployment and governance then understate what these models can do. To understand the mechanism, we propose a causal model of how sandbagging is carried in the residual stream. Early layers write the sandbagging intent onto a single axis of the stream, and a later layer reads that axis and commits the answer. We study three instruction-tuned models (Qwen2.5-7B, Llama-3-8B, and Mistral-7B) and four ways of installing a sandbagging lock (prompting, fine-tuning, reinforcement learning, and circuit breaking). Each lock decides from the prompt whether to sandbag, and the fine-tuned and circuit-broken locks answer honestly whenever a password appears. The causal model predicts a window of layers, after the last sandbagging write and before the answer commit, in which a single-layer reference graft of the sandbagging axis to its honest value restores the full capability. The single-layer graft recovers the capability in 28 of the 33 runs of the prompted, fine-tuned, and RL-trained locks, with a median held-out recovery of 96%. The circuit-broken lock rewrites the whole state through a band of layers, and the single-layer graft fails at every layer. We therefore introduce a second intervention, context grafting, which replays the password's cached key/value activations so that every layer's attention reads them as additional context. Context grafting provably and empirically restores the full capability on all three models, and the recovery is surprisingly insensitive to the exact password content. More broadly, an auditor can use this causal model to design interventional auditing techniques for sandbagging models. --- ### Can escalation channels redirect reward hacking toward defect disclosure? Authors: Francesca Gomez Published: 2026-08-29 Categories: cs.AI, cs.CR, cs.CY arXiv: https://arxiv.org/abs/2608.29460v2 When coding agents encounter defective test infrastructure they may reward-hack: hardcoding outputs or editing test files to pass tests they cannot legitimately satisfy, a pattern that has now appeared outside benchmarks, in a coordinated multi-agent intrusion of a major AI platform's production infrastructure. The same capability that lets an agent detect and exploit a defect could let it report one, given the right decision environment. We evaluate escalation channels, structured reporting tools available to the agent at the point of conflict, as a decision-environment intervention that both reduces reward hacking and surfaces the infrastructure defects that trigger it. A $2 \times 2$ factorial separates the contributions of an escalation tool, a standalone anti-reward-hacking policy, and their combination. Across 8 frontier models spanning 5 families, the combined intervention reduces reward hacking from 23.6% to 5.3% (mixed-effects logistic OR = 9.2, 95% CI 5.0--16.8, $p < 10^{-12}$) with no detectable cost or performance overhead, eliminating it entirely for 6 of 8 models. Escalation and hacking are near-perfectly mutually exclusive, with 98.7% of escalations involving no hacking (100% under the combined intervention). Beyond reduction, escalation channels function as diagnostic infrastructure: on top of monitoring, escalation adds +10.1 percentage points of defect detection coverage and is more accurate once it fires (99.4% vs 85.8%). Unlike containment-based approaches that risk outpacing growing model capabilities, escalation channels redirect capability toward disclosure rather than exploitation. --- ### Toward Latent Language Model Skills Steering and Optimization: An Empirical Study Authors: Xunyi Jiang, Junda Wu, Yuxin Xiong, Sheldon Yu, Tong Yu, David Arbour, Ritwik Sinha, Julian McAuley, Hongyi Wen Published: 2026-08-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.29459v1 Skills, as a useful abstraction for the procedural capabilities of large language models (LLMs), capture how models perform structured, multi-step reasoning and program execution. Existing approaches typically treat skills as explicit, surface-level constructs specified through prompts or programs, leaving open the question of how such procedural capabilities are represented inside the model and whether they can be manipulated as structured objects in latent space. In this empirical study, we investigate whether procedural LLM skills can be represented as directions in activation space and whether vector-space operations over these directions can express skill-level behaviors. We find that procedural skills admit a vector-space representation: individual skill directions can be activated to shift model behavior; independently extracted directions can compose to form higher-level skills. Contrastive directions yield context-conditioned algorithmic personalization and optimization trajectories over skill directions evolve non-monotonically, with intermediate states often surpassing fully optimized solutions. These results support a representation-level view of procedural LLM skills: they admit a latent vector-space organization that allows direct manipulation through internal interventions. --- ### Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities Authors: Linh Le, Hong Kiat Tan, David Williams-King Published: 2026-08-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.29458v1 Sandbagging, in which a model deliberately underperforms on an evaluation despite retaining the underlying capability, threatens the safety evaluations that frontier-model governance depends on. The Elicitation Game found that fine-tuning elicits hidden capability from sandbagging model organisms whereas additive activation steering fails. We revisit that verdict with reference-grafting, which sets an activation's coordinate along a contrast direction to the value it takes in an honest reference, at a small set of circuits chosen by active learning. Across eleven fine-tuned password-locked models (1.5-32B, three architecture lineages), it recovers +94 to +101% of the honest-sandbagging gap, matching fine-tuning elicitation without weight updates or training labels; two to five paired examples suffice to fit the direction. Similar recovery holds for reinforcement-learning-induced sandbagging and for password-locked code generation. Grafting works because the fine-tuned lock is a thresholded gate: held-out accuracy stays at the sandbagged level until the grafted coordinate crosses a threshold near the honest reference, which is why additive steering and zeroing the coordinate often fail. The direction tracks how the sandbagging was induced rather than what is withheld -- fit on grade-school science (ARC) it elicits withheld hazardous knowledge (WMDP), yet prompting, fine-tuning, and reinforcement learning each carry a different direction. Circuit-breaking marks the boundary: it reroutes activations on every forward pass, so the fixed edits we test are re-broken downstream and do not restore coherent generation. --- ### Text-Guided Diffusion-Based Adversarial Attacks on Chest X-Ray Images Authors: Basudha Pal, Arjun Narayanan, Neha Ajith, Vikas R Bhat, Muhammad Umair Published: 2026-08-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29456v1 As artificial intelligence is increasingly integrated into chest X-ray (CXR) interpretation, triage, and clinical decision support, understanding its vulnerability to adversarial manipulation is critical for safe deployment. Existing robustness evaluations, however, predominantly rely on pixel-space attacks that introduce numerically constrained perturbations but may not represent plausible radiographic variation. This limitation is particularly important in multi-disease CXR classification, where models simultaneously evaluate multiple overlapping pathologies and adversarial failures may alter several diagnostic predictions. We propose a text-guided diffusion-based adversarial framework that optimizes learnable text conditioning while keeping the diffusion generator and target classifier frozen, enabling adversarial generation through a learned image prior rather than direct pixel manipulation. We evaluate the framework across multiple classifier architectures in both binary atelectasis and multi-disease CXR classification and compare it with FGSM, PGD, and Carlini-Wagner attacks. Our approach consistently produced the greatest degradation in classifier performance, reducing AUROC to 0.3885-0.5646 in binary classification and 0.4441-0.4878 in the multi-disease setting, while achieving superior image fidelity (SSIM 0.9080, LPIPS 0.1670, FID 51.23). Importantly, clinician interpretation remained unchanged for 95.9% of binary and 73.8% of multi-disease adversarial images despite substantial changes in model predictions. These findings reveal a clinically important discrepancy between human and machine interpretation and demonstrate the need to extend medical AI robustness evaluation beyond conventional pixel-space attacks toward generative threat models that can expose failures under visually and clinically plausible image variations. ---