# Research Papers — 2026-08 · bundle page 14 of 240 > Full-text markdown of papers #651–700 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/14 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/13.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/15.md) ### VERA: Authority-Preserving Edge Revocation for Federated AI-Agent Workflows Authors: Lifei Liu, Haoran Yu, Xiaochong Jiang Published: 2026-08-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30091v1 Modern agent frameworks compose planners, tool agents, remote services, and shared specialists into runtime delegation graphs, but their revocation APIs still resemble token or subtree invalidation. When one delegation is withdrawn, the runtime must know which agents lose authority while independently authorized agents keep working. We study this authority consistency problem and introduce VERA (Verifiable Edge Revocation for Agents), a verifier-checkable revocation contract and API emitted by agent-runtime adapters as signed evidence. Under disjunctive authority, revoking edge e invalidates exactly T_intent(e,G) = reach(G) \ reach(G \ {e}), the agents whose every authorizing root path used e. Used as a contract, this target exposes two runtime failures: tree cascades over-revoke shared agents, while deployer-scoped cascades under-revoke cross-domain descendants. In a LangGraph framework-replt cells repeated 20 times yield 500compiled-framework traces and 2,000 valid signed delegation decisions; 13/25 cells contain runtime multi-parsharing and 8/25 contain cross-deployer shies 500/500 target proofs, preserves all320 alternate-parent shared-agent cases that tree cascade revokes, and rejects unauthorized signers and omission attacks. Baseline replay over 1,9that holder/node and tree-style targetscannot express this behavior. We further validate schema portability on A2A, AutoGen, and CrewAI artifacts: nine traces, including five executable Cregned delegation events that pass schema and signature checks. --- ### A Lightweight Phenology-Aware YOLOv5 Framework for Tomato Growth Stage Detection in Resource-Constrained Bhutanese Greenhouse Environments Authors: Sherab Gocha, Sou Nobukawa Published: 2026-08-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30088v1 Accurate detection of tomato growth stages is essential for stage-specific greenhouse management and precision agriculture. In Bhutan, greenhouse cultivation is affected by altitude variability, large diurnal temperature fluctuations, diffuse illumination, limited automation, and a scarcity of locally annotated datasets, limiting the applicability of conventional deep learning models. This work proposes Pheno-Lite + Efficient Channel Attention (ECA), a lightweight, phenology-aware object detection architecture derived from Ultralytics YOLOv5 for tomato growth stage recognition. A balanced dataset of 2,464 annotated images was constructed from locally collected greenhouse images in Bhutan and publicly available tomato images, with augmentation designed to simulate local greenhouse conditions. The dataset includes vegetative (820), flowering (824), fruiting (820), and background (26) samples. The proposed architecture introduces two customized backbone modules: C3 PhenoLite, which enhances spatial and texture feature extraction using depthwise residual refinement, and C3 ECA, which strengthens inter-channel feature interactions through efficient channel attention. The proposed model achieves 90.6% precision, 88.8% recall, and 92.6% mAP@50, with 4.0 million parameters and 10.9 GFLOPs at 640 x 640 resolution. These results demonstrate its potential for real-time and climate-resilient greenhouse deployment in Bhutan. --- ### The Nearest Target Is the Wrong One: Target Separation in Arc2Face Identity Unlearning Authors: Zeynel Tok Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30087v1 Unlearning an identity from a face-conditioned generator by redirecting its conditioning embedding can silently fail if the redirected output is still verified as the original person. We show that this failure depends on a controllable choice of how far the redirection target lies from the forget identity in recognition space, and that the most intuitive target, the nearest neighbour, is the one most likely to cause it. We audit Arc2Face with a locked ArcFace protocol and a projection adapter that redirects identity conditioning before generation. On a hard-neighbour stress test built from the hardest 0.5% of eligible identities, four target-selection policies show a monotonic response: clean forgetting rises from 9/30 groups under the nearest hard target to 30/30 under the least similar one. Mean forget-identity re-identification falls from 51.9 to 0.0 while mean retention stays flat. This reflects successful redirection rather than outputs becoming unverifiable: 710 of 720 least-sim-hard generations arrive at the chosen target, with no leakage to unrelated identities. Re-verifying identical images with an independent recogniser (AdaFace) preserves that trend, correlating at r=0.94, arguing against a verifier artefact. Target separation is thus a first-order, reportable design variable for identity unlearning. --- ### When Does a Classifier Help an LLM? Classifier-Guided Prompting and Hybrid Classifier-LLM Models for Credit-Default Prediction Authors: Rishi Datta, Lavanya Prahallad Published: 2026-08-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.30086v1 Credit-default prediction is an important task in financial decision making. Traditional methods use fitted classifiers such as logistic regression and random forests on tabular features. Large language models (LLMs) have recently been applied to this task through prompting. In this work we study how a fitted classifier and an LLM can be combined for credit-default prediction. We distinguish telling the LLM to imitate a classifier from using the classifier to build the prompt. We hypothesize that a fitted classifier can supply the ranking ability that an LLM prompt lacks. We experiment on the Default of Credit Card Clients dataset, and report recall, F1, and the area under the ROC and precision-recall curves, with bootstrap confidence intervals. We observe that a few-shot LLM has the highest recall (0.47) and F1 (0.50) of any single model but ranks worse than a random forest (AUC-ROC 0.72 against 0.79). Instructing the LLM to imitate a classifier gives no significant change. Pruning the prompt to the classifier's eight most important features raises recall by 0.071 and F1 by 0.032. Adding the classifier's predicted probability to the prompt raises the LLM's AUC-ROC from 0.72 to 0.78, matching the random forest, while keeping 0.118 higher recall than it. The reverse composition, and the use of several classifiers, do not help. We thus recommend a simple classifier-guided prompt for LLM-based credit prediction. --- ### Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models Authors: Rania Briq, Ohad Fried, Michael Kamp, Stefan Kesselheim Published: 2026-08-30 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2608.30081v2 Understanding which training samples influence a generated image is an important problem in generative modeling. In flow matching, training samples influence the generated image through the velocity field along the generation trajectory. Removing samples to examine their counterfactual influence changes the velocity field, and the resulting effect on the final image depends on how the change propagates through the trajectory. Consequently, local changes in the velocity field do not necessarily predict the final counterfactual effect. This work investigates attribution in flow-matching models through a hybrid analytical--learned approach, and uses it to derive trajectory-based attribution scores at the cluster level. We evaluate these attribution scores using independently retrained leave-one-cluster-out (LOCO) models, and compare with several attribution baselines using two different flow-matching latent spaces. Our experiments show that semantic similarity constitutes a strong baseline, while the closed-form trajectory-based attribution is competitive in some metrics without requiring counterfactual retraining or model gradients. Our results show that attribution in flow matching depends not only on semantic similarity to training samples, but also on the latent representation, trajectory dynamics, and how influence is propagated to the final output. --- ### Budget-Aware Compression Pipeline for Single-GPU LLM Inference: Methods, Trade-offs, and Coupling Effects Authors: Hongyu Yu, Yifei Shen Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30076v2 Single-GPU deployment of 70B-parameter language models on an NVIDIA GPU is constrained by device memory, long-context throughput, and engineering integration cost. We cast single-GPU inference as a budget-aware design problem over these three axes and study how pruning, quantization, and KV-cache compression interact under realistic execution. Controlled ablations show that layer-wise pruning makes weight quantization more robust. KV-cache sparsification complements INT8 KV quantization by reducing memory without hurting decoding speed, while static vector quantizers often conflict with dynamic caching. Guided by these coupling results and explicit budget tracking, we assembled a practical pipeline and compressed a 70B model to about 33 GB, sustained about 57 tokens/s on 10k token prompts on a single A40, and kept absolute accuracy within 5% on common and reasoning benchmarks. We contribute design rules and a reproducible evaluation protocol that jointly report quality, memory, and end-to-end speed, and we provide a foundation for automated pipeline search under realistic single-GPU constraints. --- ### Learning Representations through Token Prediction: Geometry, Approximation, and Downstream Guarantees Authors: Shulei Wang Published: 2026-08-30 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2608.30072v1 Token prediction is a central pre-training objective for modern language models. Despite its empirical success, why token prediction learns broadly useful representations remains incompletely understood. We develop a statistical framework connecting token prediction with representation geometry, encoder approximation, and downstream performance. Under a softmax prediction head, we show that accurate token prediction organizes token embeddings according to similarities between the distributions of contexts in which different token types appear, as measured by Hellinger distance, with explicit errors governed by prediction accuracy and token frequency. Meanwhile, the contextual representation provides a low-dimensional coordinate for the conditional distribution of the target token relative to these embeddings. We further introduce a self-consistency principle showing that repeated applications of a shared representation block can progressively refine the contextual representation without introducing additional block parameters. Among representations with the same prediction accuracy, this recurrent construction favors those that can be stably reconstructed from their contexts. Finally, we establish downstream guarantees for token generation, token community recovery, and classification by a linear probe, showing how prediction accuracy and recovered geometry translate into performance beyond the pre-training objective. Together, these results explain how the simple objective of predicting tokens can recover semantic geometry and produce broadly useful representations. A controlled simulation illustrates the theoretical mechanisms. --- ### Selection, Representation, and Execution in Sparse Fourier Neural Operators Authors: Abdul Qadir Ibrahim, Martin Burger Published: 2026-08-30 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2608.30070v1 Sparse representations are often expected to make models smaller and also reduce inference cost. For Fourier Neural Operators (FNOs), these objectives are not equivalent or do not always align: removing parts of the learned operator can leave the underlying transforms and dense computations unchanged, while changing the grid on which the model is evaluated can introduce overhead of its own. We therefore distinguish sparsity in the representation, in the stored parameters, in the theoretical operation count, and in measured runtime, and present an empirical study of several routes toward sparse FNOs that tests each transition between them separately. Coarsening the execution grid reduces the theoretical cost without reducing measured latency, and adding a correction term recovers accuracy at the cost of making the model slower. Even an 83\% parameter reduction remains slower than the dense baseline under ordinary execution. These results motivate a stricter definition of useful sparsity: the deployed operator must preserve solution accuracy and map its reduced support to a genuinely cheaper execution path. --- ### TAKE 85: Testing Audiovisual filmmaKer's intEnt across 85 Hours of Film Authors: Kaishuu Shinozaki-Conefrey, Olivier Pascaud, Robin Courant, Xi Wang, Dimitris Samaras, Vicky Kalogeiton Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30068v2 Films communicate through deliberate creative choices, including lighting, color, composition, editing, dialogue, music, and sound. Humans naturally interpret these signals as directorial intent, yet current multimodal large language models (MLLMs) are evaluated almost exclusively on understanding what happens rather than why it is presented that way. We introduce TAKE 85, the first benchmark for directorial-intent understanding, comprising 398 short films (85 hours) with expert-verified question-answer pairs spanning global and fine-grained visual and audio intent. Through controlled modality ablations, TAKE 85 enables systematic evaluation of multimodal reasoning. Experiments on state-of-the-art MLLMs reveal a substantial gap between perceptual recognition and intentional understanding: while models accurately describe events and narratives, they consistently fail to infer the communicative role of filmmaking decisions. Our results establish directorial intent as a previously overlooked dimension of multimodal understanding: even the strongest model reaches only 58 out of 100, and our ablations show that no input modality is sufficient on its own. All code, Q&As, and models are publicly available from https://github.com/KaiShinozakiConefrey/Take-85 --- ### How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account Authors: Ruize Xu, Xiao Yu, Yujin Tang, Chenming Shang, Nikhil Singh Published: 2026-08-30 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.30067v1 How do LLM agents come to both understand environments they act in and master tasks set within them? Through controlled experiments combining world-model training (next-state prediction) and policy training (reward maximization), we investigate this question. We dissect the resulting models through their additive parameter updates. Geometrically, we find effective world-model updates are low-rank and share an input-feature subspace with policy updates while writing to nearly orthogonal output directions, whether trained separately or sequentially. However, we find that, in projection interventions, the sequential update induces more robustness than separate policy RL when removing the world model's leading input directions, suggesting that it has learned alternative input pathways. Behaviorally, we find the sequentially trained agent explores a wider range of states and actions. Based on this, we ask: does policy training preserve world knowledge as well as it could? We probe this with training-free merging built on the geometrically motivated input basis plus an online world-model loss during policy RL, and show both improve over the untreated baseline. Our findings suggest world knowledge and task-directed ability can be learned in geometrically complementary forms, and that future post-training pipelines should consider how best to engineer the interface between them. --- ### Pak3H: Evaluating the Cost of Cultural Mismatch in LLM Alignment with a Human-Contextualized Urdu Benchmark Authors: Abdullah Hashmat, Usman Naseem, Agha Ali Raza Published: 2026-08-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.30065v1 Large language models (LLMs) demonstrate strong Helpfulness, Harmlessness, and Honesty (3H) alignment in English-centric settings, but these gains transfer poorly to low-resource languages due to cultural mismatches. Existing multilingual 3H benchmarks rely predominantly on automated translation or LLM based synthesis, propagating source-language biases while sacrificing local relevance. To address this gap, we introduce Pak3H1, the first human-validated, culturally contextualized Urdu benchmark suite for 3H alignment, comprising PakAlpaca (helpfulness), PakBeaverTails (harmlessness), and PakTruthfulQA (honesty). Our multi-stage pipeline integrates manual cultural adaptation and dictionary-guided post editing to prioritize native speaker judgment, ensuring both semantic fidelity and contextual authenticity. Zero-shot evaluations across multiple open and proprietary LLM architectures reveal systematic cross-lingual alignment gaps: helpfulness win rates decline under localized contexts, harmlessness guardrails break down against regional safety risks, and composite honesty metrics degrade substantially due to localized factual constraints. These findings expose structural limitations in current alignment approaches, underscoring the necessity of human-guided localization for equitable multilingual evaluation. --- ### Game-Agnostic Value Functions through Automatic JSON Feature Extraction Authors: Dien Nguyen, Diego Perez-Liebana Published: 2026-08-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30056v1 JSON Bag-of-Tokens (JSON-Bag) is a recently proposed method to generically represent game trajectories by tokenizing their JSON descriptions. We introduce JSON-Bag VF, a game-agnostic approach to training value functions for game-playing agents using JSON-Bag prototypes. We show that this approach can be enhanced with Random Forest-based feature selection and a method to select game-stage-specific features. We evaluate JSON-Bag VF with One-step-look-ahead (JSON-Bag OSLA) on six tabletop games over different combinations of prototype-tokenization and feature selections. JSON-Bag OSLA outperforms baseline OSLA agents in most games. Our analysis also shows that feature selection significantly improves JSON-Bag VF and that feature selection is the most important factor in JSON-Bag VF performance, over prototype-tokenization. --- ### When 3D Gaussian Splatting Recovers Real Surfaces Authors: Songhe Wang, David Johnathan Miller Published: 2026-08-30 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2608.30054v1 When does 3D Gaussian Splatting (3DGS) recover the true scene surface rather than just overfitting view-dependent appearance? We answer this by developing a mathematical framework based on a first-hit rendering abstraction that cleanly isolates geometry from appearance. We prove that geometric misalignment forcefully converts spatial textures into high-frequency angular signals via parallax. This establishes a strict identifiability window: if angular capacity is bounded, surface-consistent solutions are mathematically preferred; if unrestricted, the same images can be perfectly explained by an incorrect, opaque billboard geometry. Experiments on synthetic stress tests confirm this prediction, showing billboard failures emerge precisely at high angular capacities. Conversely, in the real-world datasets we evaluate under standard capture protocols, reconstructions remain surface-consistent even at high SH degrees, which is consistent with the prediction that rich spatial texture can push billboard solutions outside the tested angular-capacity range. --- ### The Language of the Question Selects the Market: Query Language and Exit IP as Separable Factors in Commercial Recommendations from a Generative Search Interface Authors: Dmitrij Żatuchin Published: 2026-08-30 Categories: cs.IR, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2608.30052v1 When a generative search interface answers a commercial question, which market's products it names is decided before the model reasons about the products. We report a controlled probe of 234 runs against the logged-out ChatGPT web interface and the OpenAI API, collected on 29 and 30 August 2026 across four exit countries and six query languages, with six identical runs per cell. Three results. First, the top recommendation is unstable: it changed across six identical runs on four of six prompts, and that rate was identical in the browser interface and in the API with web search both enabled and disabled, so instability is a property of the system and not of the surface. Second, query language, and not location, decides whether local suppliers appear at all. Where the query language matched the country, a global brand won 1 of 24 runs; asked in English on the same connections, local brands took 0 of 6 runs in Estonia and Turkiye. Third, language and location are separable and act on different things: holding the query language fixed and moving only the exit IP moves the market whose brands are named while the answer stays in the query language. We show this on two unrelated pairs, Turkish asked from Berlin and Russian asked from Tallinn, and in both the answer names the resident country's suppliers. A minority language occupies a middle tier: Russian asked from Estonia names an Estonian supplier in 4 of 6 runs and a global one in all six, where Estonian names a local supplier in every run and English names none. A negative control in a second category, coded with the same instrument, shows no language effect at all, and disconfirms our own expectation: that category does have domestic suppliers and none was named in any language, which points the explanation at whether a category is nationally regulated rather than at whether it is nationally supplied. --- ### Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide Authors: Taejong Joo, Diego Klabjan Published: 2026-08-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.30051v1 Process reward models (PRMs) provide dense step-level guidance for search-based reasoning, enabling inference-time compute to be allocated toward promising partial solutions. However, recent evidence suggests that PRM-guided search can over-optimize imperfect process rewards, pruning viable trajectories while expanding spurious ones. In this work, we theoretically show that directly leveraging PRM score is vulnerable to verifier noise through an extreme-value effect: non-viable prefixes become more likely to receive spuriously high scores as reasoning depth increase. Therefore, we formulate the PRM-guided search as a robust optimization problem over plausible reward perturbations, termed maximin PRM-guided search, leading to a training-free robust process supervision method that preserves promising alternatives when step-level scores are noisy. Maximin PRM-guided search mitigates this failure mode by reducing sensitivity to over-optimized PRM outliers. Without fine-tuning or online adaptation, maximin search consistently improves the PRM-guided search by 17-35\% on average, outperforming outcome- and step-level baselines in 14 out of 16 settings. Our source code is available at https://github.com/tjoo512/maximin-search. --- ### Spec2Twin-Chain: Orchestrating Bi-Level Optimization with LLMs for Blockchain Digital Twin Construction Authors: Haoting Zhang, Haoxian Chen, Jiayuan Sheng, Donglin Zhan, Zeyu Zheng, David D. Yao, Wenpin Tang Published: 2026-08-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30050v1 Building a blockchain digital twin largely requires translating domain knowledge and specific system descriptions into a simulator architecture, calibrating its parameters against behavioral evidence, and validating the constructed twin. These steps are commonly performed through application-specific modeling efforts that can be difficult to reuse across systems and downstream decision problems. We consider automating this process through Spec2Twin-Chain, a framework that formulates blockchain digital-twin construction as a bi-level optimization problem. At the upper level, a large language model proposes and revises structurally admissible architectures using system specifications, behavioral evidence, and feedback from evaluated designs. At the lower level, a simulation-based optimizer calibrates the architecture-conditioned parameters under explicit objectives and guardrail constraints. The two levels iterate. The evaluated candidates at lower levels are retained in a global archive and used to guide subsequent proposals at upper levels. We conduct controlled experiments involving twin calibration, feedback-driven recovery, stress analysis, downstream policy optimization, and policy updating. The results demonstrate that the framework can construct behaviorally accurate twins, improve initial designs through iterative feedback, and reuse calibrated twins to support downstream decisions. --- ### Can LLM Agents Discover? Evaluating Creativity on ML Engineering Tasks Authors: Shitanshu Bhushan, Yunxiang Zhang, Lu Wang Published: 2026-08-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30047v1 Recent AI systems promise autonomous scientific discovery, claiming to discover algorithms and produce research papers, yet understanding whether they exhibit creativity, the capacity to produce solutions that are both novel and useful, remains an open question. We present a framework for evaluating multi-turn LLM research agents' creativity using ML engineering tasks as a testbed, through three dimensions: P-Creativity (psychological novelty: novel relative to the agent's own prior solutions within a run), H-Creativity (historical novelty: novel relative to the corpus of human solutions), and Usefulness (task performance). Evaluating two agent frameworks, AIDE and AIRA-Dojo, on 10 Kaggle-style machine learning tasks from MLE-Bench, we develop an LLM-as-a-Judge pipeline and verify its strong correlation with human creativity judgments, providing a reliable automated metric for P-Creativity evaluation at scale. Applying this pipeline to agent trajectories, we find: (1) all agents exhibit declining P-Creativity as they transition from exploration to exploitation; (2) LLMs exhibit greater H-Creativity than medal-winning humans, yet achieve lower performance. Our findings reveal that current agents can explore novel regions of the solution space but lack the capacity to convert this novelty into improved task performance. --- ### Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction Authors: João L. P. Santana, Filipe R. Cordeiro Published: 2026-08-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.30046v1 Noisy labels remain a critical challenge for training deep neural networks, since memorizing incorrect labels degrades generalization. Once noisy samples are identified after training, the standard solution is to retrain the model from scratch on the cleaned dataset, which is increasingly expensive as datasets and models grow. Machine Unlearning (MU) has recently emerged as a computationally efficient alternative, but the relative effectiveness of different MU strategies for noisy-label correction remains poorly understood. In this work, we conduct a comparative empirical study of five MU methods (NegGrad, Fine-Tuning (FT), Random Labeling (RL), SalUn, and MUNBa) across symmetric, asymmetric, instance-dependent, and open-set noise on CIFAR-10, CIFAR-100, and the real-world noisy dataset Food-101N. Our central finding is that the appropriate unlearning strategy is conditioned on the noise structure. Simple FT is a strong baseline across most closed-set scenarios; RL and SalUn are the most consistently robust methods and, under instance-dependent noise, approach retraining accuracy at a fraction of the computational cost; MUNBa shows advantages mainly under extreme symmetric noise. Under open-set noise, in contrast, we show that retraining on the cleaned subset degrades accuracy relative to the noisy baseline, so approximating the retrained model is not an adequate objective in this regime. On Food-101N, all MU methods remain competitive and achieve accuracies close to retraining despite reducing runtime by an order of magnitude. These findings provide practical guidelines for selecting MU strategies for post-training noisy-label correction. --- ### Balance of Benchmarks: Semantic Density Reweighting for Task-Conditioned Model Comparison Authors: Jhen-Ke Lin, Hong-Yun Lin Published: 2026-08-30 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.30044v3 Model comparison increasingly relies on large collections of publicly reported benchmark scores, yet common aggregation strategies trade off evidence coverage against control over capability weighting. Manually curated suites leave potentially informative evaluations unused, while uniform averaging retains them but gives greater influence to capabilities that happen to be benchmarked more densely. We introduce Balance of Benchmarks (BoB), a framework that retains eligible benchmark evidence while adapting its influence for task-conditioned model comparison using only public aggregate scores. BoB combines semantic density weighting, score equating across benchmarks of different difficulty, and task-relevant residual pooling. We evaluate it on 605 configurations across 14 Artificial Analysis benchmarks and on WildScores, a collection of 148 developer-reported benchmarks evaluated with held-out source-lineage families. On WildScores, BoB-Support raises family-mean Spearman correlation from 0.764 under uniform standardized averaging to 0.823, reduces MAE from 6.19 to 5.10 normalized score points, and increases three-model shortlist hit rate from 65.3% to 72.6%. BoB-Constant reaches a Spearman correlation of 0.831 and a hit rate of 74.6%. Separately, density weighting reduces average ranking changes when benchmarks are repeated, including as paraphrased copies. BoB-Support also reduces retrospective three-model shortlist regret from 2.08 to 1.67 normalized score points. BoB makes benchmark inclusion, redundancy, and task relevance explicit and testable measurement choices, allowing existing benchmark evidence to be used more fully while moderating the influence of benchmark proliferation. --- ### Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection Authors: Wujie Xiong, Rabimba Karanjai, Yang Lu, Weidong Shi, Lei Xu Published: 2026-08-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.30041v1 Large language model agents place outputs from external skills into their execution context, allowing attacker-controlled data to influence later privileged actions. Existing defenses mainly classify untrusted content or authorize proposed operations. They do not directly address how an agent's future authority should change once untrusted data enters its state. We present SkillGuard, a harness-level enforcement layer that treats this event as contamination and restricts future capabilities to disconnect the resulting state from deployer-defined forbidden states. Given sound skill summaries and policies, SkillGuard represents security-relevant transitions with a Skill Impact Graph, specifies admissible control over skill parameters via steerability signatures, and mediates invocations with an inline reference monitor. Following contamination, it computes weighted capability restrictions using binary, fractional, or fractional-flow strategies without auxiliary language-model inference. We evaluate SkillGuard on four AgentDojo suites with two backend LLMs, Gemini 2.5 Flash and Llama3.3-70B, against an LLM-only No Defense baseline and three defenses at different system layers: Spotlighting, CaMeL, and AttriGuard. We construct a compositional attack benchmark in which each attack combines observations individually insufficient to induce target violation and evaluate the same baselines on it. Under AgentDojo's Tool Knowledge attacks, SkillGuard eliminates attack success on three of four suites for both backends and reduces it to 4.8% and 14.3% on Slack. Against compositional attacks, it outperforms every baseline on Llama and matches the strongest baseline on Gemini at higher benign utility. Fractional-flow restriction preserves substantially more capabilities than binary restriction at the same attack success rate. Across both settings, SkillGuard adds no model calls or token overhead. --- ### A Deep Latent Variable Framework for Jointly Modeling Missingness, Measurement Error, and Heterogeneity Authors: Yasin Khadem Charvadeh, Grace Y. Yi, Mithat Gönen, Pouya Faroughi Published: 2026-08-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.30040v1 Missing data, measurement error, and population heterogeneity are pervasive challenges in analyzing data arising from modern observational studies and machine learning applications. Although these problems frequently coexist and interact, they are often treated separately in existing works. We propose a unified probabilistic framework that jointly addresses these issues utilizing deep latent variable representation. The proposed method integrates a novel hierarchical tree-routed variational autoencoder with pattern-aware latent representations and calibration-based denoising. The framework accommodates missing data mechanisms, including MCAR, MAR, and MNAR, while simultaneously learning subgroup-specific and globally shared latent structure. The introduced reconvergent routing mechanism enables selective parameters to be shared across related subpopulations, which offers flexibility as well as improved statistical efficiency. Simulation studies demonstrate substantial improvements over existing deep generative imputation approaches under complex heterogeneous missingness and measurement-error settings. The proposed framework provides a principled approach for learning from noisy and incomplete data in modern healthcare and other high-dimensional applications. --- ### Beyond Uncertainty: Multi-Solver Disagreement Rewards for Self-Evolving Reasoning Curricula Authors: Vinoth Selvendran, Zhanming Zhang Published: 2026-08-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.30035v1 Self-evolving reasoning frameworks train a Challenger to generate questions exposing a Solver's weaknesses, creating adaptive curricula without human data. However, existing approaches use a single solver's sampling uncertainty as the Challenger's reward. This creates a fundamental bottleneck: as the solver grows confident on the Challenger's question distribution, all sampled answers converge identically, collapsing the reward to zero and starving the Challenger of learning signal. Critically, this single-model reward cannot distinguish genuinely easy questions from those that merely align with one solver's learned biases. We propose a multi-solver disagreement reward using a heterogeneous ensemble varying in model capacity and sampling temperature. A normalized Shannon entropy over the ensemble's per-question plurality answers explicitly rewards questions where solvers produce conflicting solutions---capturing difficulty as inter-model divergence rather than intra-model sampling variance. This richer gradient enables the Challenger to discover questions targeting true capability boundaries, producing a curriculum that forces downstream Solvers to develop robust reasoning strategies generalizing across problem types. Our approach is a drop-in reward function replacement requiring no framework modifications or additional data. Experiments with Qwen3-4B show that Solvers trained on disagreement-Challenger questions achieve +1.34 points average improvement on competition-math benchmarks (MATH-500, AMC, Olympiad), suggesting that multi-solver disagreement provides a complementary and scalable signal for curriculum generation in self-play reasoning systems. --- ### Input-Adaptive Gating of a Dehazing Front-End for On-Device Perception in Smoke-Obscured Environments Authors: Seongjun Kang, Ishaan Garg, Vishnu Bharadwaj Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30034v1 Two-stage vision pipelines often place an enhancement network before a task network, on the assumption that a cleaner input produces a better output. We evaluate this in a firefighter assistance pipeline, where a dehazer precedes an edge detector that renders smoke-filled rooms as structural outlines. Both were designed for a Raspberry Pi 4, at 355K and 23K parameters, and quantized to UINT8 via TensorFlow Lite. The float dehazer reaches 18.60 dB peak signal-to-noise ratio (PSNR) on held-out real smoke against 13.60 dB unprocessed and 17.08 dB for an AOD-Net trained on the same data, and the edge detector reaches an F-measure at optimal dataset scale (ODS) of 0.738, outperforming an optimized Canny's result of 0.692. Dehazing improves edge extraction under dense smoke but degrades it on clear and lightly hazed frames, where the dehazer discards more detail than the haze obscures. We therefore run the dehazer only when a dark channel haze estimate exceeds a threshold, a 10.1 ms test that lets the pipeline save 469.6 ms on the dehazing stage. Averaged over four haze levels, gating is more accurate than either fixed decision, at 0.675 mean ODS against 0.664 for always dehazing and 0.630 for never dehazing. It reduces the mean per-frame time on the Raspberry Pi from 569 ms to 321 ms, and on clear frames increases the frame rate fivefold, from 1.8 to 9 frames per second. --- ### "Act Like a 5th Grader" is Not Enough: Bounding Knowledge in LLM-Based User Simulators Authors: Krisztian Balog, Arild Michel Bakken Published: 2026-08-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.30033v1 Large language models (LLMs) are increasingly used to simulate human behavior but frequently fail to exhibit realistic cognitive constraints, suffering from a "superhuman bias." Using a dataset of over 71,000 reading comprehension responses from 2,359 primary-school students (grades 4--6), we demonstrate that standard persona prompting yields near-perfect, deterministic performance, failing to capture the natural variance of developing readers. To address this, we introduce the Cognitively Bounded User Simulator (CBUS), an architectural framework that explicitly models the restricted working memory of young readers through an episodic bottleneck. Within this framework, we formalize two distinct test-taking strategies to emulate different reading behaviors. Our evaluation shows that explicitly modeling cognitive bounds significantly narrows the simulation gap across multiple LLM backbones, demonstrating that enforcing architectural constraints is more effective for high-fidelity simulation than simply scaling raw model capabilities. --- ### Multiclass Linear Perceptrons with Multiplicative Margins Authors: Dmitri Rachkovskij, Evgeny Osipov, Olexander Volkov, Daswin De Silva, Denis Kleyko Published: 2026-08-30 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2608.30028v1 This paper introduces a family of multiclass linear Perceptron classifiers with a multiplicative margin mechanism (MMPerc), as an alternative to standard margin-free and additive margin Perceptrons. The multiplicative formulation enforces classification confidence by requiring the true class score to exceed that of competing classes by a specified fraction of itself, rather than by a fixed additive threshold. This avoids dependence on score magnitudes arising from varied norms of data and class weight vectors. We propose several architectural and algorithmic variants of MMPerc, derive associated loss functions and mistake bounds for both linearly separable and non-separable data, and analyze key design considerations, including bias, margin threshold selection, and training modes. Extensive experiments on synthetic and real datasets show that MMPerc classifiers typically outperform the standard Perceptron, as well as classic baselines such as Support Vector Machines and Ridge classifiers. Owing to their simplicity, minimalistic design, and computational efficiency, MMPerc classifiers are promising candidates for conventional machine learning tasks, linear evaluation of Deep Neural Networks, integration with Hyperdimensional Computing / Vector Symbolic Architecture representations, and deployment in resource-constrained applications. --- ### Interpreting and Steering for Safe and Correct Code Generation Authors: Hao Yan, Ziyu Yao Published: 2026-08-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30025v1 Large language models (LLMs) frequently generate source code containing vulnerabilities, yet little work studies the internal mechanisms that distinguish safe from vulnerable generation in them. In this work, we systematically perform a mechanistic interpretation of LLMs, aiming at both understanding how code safety-vs-vulnerability is represented or driven by components in an LM and turning the insights into actionable steering strategies to encourage safer code generation. To this end, we introduce CodeSec-Pairs, a dataset of 9,342 Python safe-and-vulnerable contrastive code pairs, sampled from Llama-3.1-8B-Instruct. Utilizing the dataset, we explore approaches to localize layers and attention heads that relate to code safety, and further experiment with different steering strategies for inference-time vulnerability reduction. In particular, we propose DuoSteer, a double-steering approach that simultaneously applies safety and code-correctness steering to attention heads. In experiments over five vulnerability types, DuoSteer leads to an average of -26.9% vulnerability rate reduction and +7.5% functional correctness improvement, which outperforms not only other steering variants but also prompting and supervised fine-tuning baselines. The advantage also replicates on Qwen-2.5-Coder-7B-Instruct with another 2,500 contrastive pairs sampled from that model. --- ### Demand-Side Measurement for Generative Engine Optimization: Constructing and Validating a Million-Persona, Intent-Annotated Buyer Corpus Authors: Dmitrij Żatuchin, Daniil Dzemesjuk Published: 2026-08-30 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2608.30023v1 Generative engines such as ChatGPT, Gemini, and Perplexity answer buyer questions directly and name a shortlist of brands inside the answer. Studying how brands enter or fail to enter that shortlist requires demand-side data: what buyers in a category ask, what information they need, and which sources they trust. Existing large persona corpora are built for training-data diversity and carry neither a staged search-intent label nor a preferred-sources field, so they cannot be joined to supply-side recommendation measurements. We built and validated PersonaGen-1M, a corpus of 1,031,732 synthetic buyer personas spanning 511 industry labels and 4 market contexts, carrying 19,416,821 structured behavioral attributes, 5,160,046 of them search queries. Each persona carries a single primary_intent label covering its query set (78.3% informational, 17.4% commercial, 4.3% transactional) and a preferred_sources field naming the source types that buyer would trust. The corpus was built from roughly 40 million raw persona descriptions drawn from four public datasets through GPU-accelerated MinHash LSH plus semantic deduplication, then enriched to a fixed schema. The intent field selects the commercial-evaluation personas whose queries drive recommendation, and the preferred_sources field pairs against citation-provenance data; that join is the primary intended use, and its controlled empirical estimate is future work. Among million-scale persona corpora surveyed in August 2026, one other carries a source-preference attribute, as a six-value media-channel enum; PersonaGen-1M pairs named per-persona source lists with a staged commercial search-intent label and an attached query set. The full corpus is shared on request for non-commercial research; a stratified subset is published openly so the protocol, the schema and the validation can be inspected and reused without asking us. --- ### Automatic Conversion of NICE Guidelines to an Executable Computational Model Using Large Language Models Authors: Ashvin Gupta, Denys Prociuk, Alessandra Russo, Brendan C. Delaney Published: 2026-08-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30022v1 Introduction: NICE guidelines provide evidence-based recommendations for clinical care but remain largely in unstructured natural language. Existing approaches to converting them into computable representations often focus on individual diseases, require substantial manual encoding, and do not scale. Large language models (LLMs) may enable much of this translation to be automated. Methods: We present an end-to-end approach that converts textual clinical guidelines into executable models capable of generating explainable, patient-specific recommendations. A stepwise LLM-based transformation with in-context examples produces human-inspectable intermediate artifacts. We apply the approach to NICE pancreatic and lung cancer guidelines, use expert review to assess rule alignment, and evaluate the executable pancreatic cancer model on 20 patient vignettes. Results: Expert review showed strong alignment between the source guidelines and generated executable models. Most discrepancies were partial omissions rather than incorrect logic, while hallucinated or fundamentally incorrect rules were rare. On the patient vignettes, the executable model achieved an F1 score of 82.5%. Conclusion: LLMs can transform natural-language NICE guidelines into interpretable, executable models that preserve guideline structure, support transparent inspection and modification, and generate patient-specific recommendations. These findings demonstrate the feasibility of scalable automated generation of computable clinical guidelines. --- ### Error Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models Authors: Hermione Warr, Harry Anthony, Lilli J Freischem, Yasin Ibrahim, Daniel R McGowan, Konstantinos Kamnitsas Published: 2026-08-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.30021v2 Errors in radiology reports can adversely affect patient treatment, yet automated report quality assurance remains challenging because errors are often subtle and require domain expertise to detect. Although large language models (LLMs) have recently been proposed for radiology report verification, their ability to detect clinically meaningful errors beyond chest X-ray datasets remains under-explored. To this end, we present the first systematic evaluation of language models for PET/CT report error detection, comparing compact domain-specific models with SOTA open-weight LLMs. We collected 30,633 oncology FDG PET/CT reports from 23 radiologists over 10 years. We trained domain-specific BERT models to detect clinically motivated synthetic reporting errors and evaluated alongside zero-/few-shot Qwen3-32B, Gemma-3-27B and Llama-3.3-70B on a held-out benchmark of 11,500 reports. A 15M-parameter model achieved 94.4% balanced accuracy with a 5.8% false-positive rate, compared with 84.0% for the strongest prompted LLM. Task-specific adaptation of Llama-3.3-70B closed this performance gap (94.4%) but retained substantially greater computational requirements. Our results suggest that domain-specific training matters more than model scale for PET/CT report error detection, supporting compact models as an accurate and computationally efficient approach to automated radiology report quality assurance. --- ### Small Language Models as Judges for Rubric-Based Reinforcement Learning Authors: Fengyu Xie, Yilun Zhao, Bingsen Chen, Arman Cohan, Chen Zhao Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30005v1 Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring responses against instance-specific criteria. However, this makes reward computation expensive: training requires repeated rubric judging, often with proprietary APIs or local generative LLM judges with 7B parameters or more. We study whether smaller language models can serve as efficient and reliable rubric-based judges. To make this question measurable, we construct PointRubric and RaR-Science-Static, two pointwise rubric-based evaluation datasets with instance-specific criteria and itemwise satisfaction labels. We compare three ways of extracting criterion-level judgments from small models: Generative verdicts, Yes/No Logprob margins, and Probe judges. Across both datasets, the Qwen3-1.7B Probe judge achieves the strongest criterion-level agreement among these methods, outperforming Generative and Logprob judges. Used as a GRPO reward model, it trains a policy from 0.232 to 0.643 on RaR-Science rubric score, compared with 0.594 for an 8B Generative judge baseline, while the baseline requires 10.7$\times$ more reward-judge time. Task and domain transfer experiments further suggest that Probe judges preserve criterion-level reward structure across settings. --- ### OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification Authors: Ilán Carretero, Gustavo Jesús Angulo, Rocío del Amor, Valery Naranjo Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30003v1 Prototypical part-based models provide explainable predictions by comparing input regions to learned prototypes. However, current approaches are burdened by complex, multi-stage training pipelines and heavily rely on auxiliary regularization to prevent prototype collapse. To overcome these limitations, we introduce Orthonormal Prototype Alignment Learning (OPAL), a single-stage, end-to-end framework that simplifies interpretable classification. Our approach anchors the latent space using predefined orthonormal bases, embedding each class within a dedicated subspace spanned by fixed part-prototypes. To achieve precise part localization, OPAL enforces spatial competition across feature maps. This mechanism isolates sparse, discriminative regions, directing each prototype to consistently attend to the same semantic concept across different images. By framing classification as a direct representation alignment task, our method eliminates the need for auxiliary losses. Extensive experiments on fine-grained benchmarks demonstrate that OPAL outperforms both its non-interpretable counterparts and state-of-the-art part-prototype methods, delivering granular visual explanations by explicitly revealing the specific image regions driving every prediction. Code is available at https://github.com/ilancarretero/OPAL. --- ### TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models Authors: Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh, Utathya Aich, Ramani Duraiswami, Dinesh Manocha Published: 2026-08-30 Categories: cs.SD, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.29999v1 Large audio-language models (LALMs) describe audio at the clip level but cannot assign timestamps to the events, speakers, or sounds they identify. Despite being essential for downstream tasks like speech recognition and dense audio captioning, timestamping remains a key limitation of most LALMs. We present TEMPO (Temporally-grounded Multi-task Post-training), the first unified model to handle audio, speech, and music timestamping tasks. Our core contribution is a supervised fine-tuning (SFT) stage built on three innovations: atomic timestamp tokens, a time-aware projector that injects sinusoidal wall-clock encodings into audio frame embeddings, and a distance-aware Gaussian loss. Our training is based on a synthetic-to-real curriculum. We further introduce, to our knowledge, the first application of reinforcement learning to unified audio timestamping, using GRPO with verifiable temporal rewards that directly optimize the evaluation objectives. Rather than serving as the primary source of performance gains, GRPO acts as a refinement stage on top of the SFT checkpoint, providing modest additional improvements. To support this work, we build a training dataset containing 119K samples and an evaluation benchmark containing 10K samples, drawn from established corpora across five tasks. On this benchmark, TEMPO outperforms Audio Flamingo Next and Qwen3-Omni, two state-of-the-art LALMs explicitly trained on timestamped data. Experiments confirm that SFT delivers most of these gains, with GRPO providing consistent but moderate refinements. --- ### The Intervention Gap in Latent World Models Authors: Donna Vakalis Published: 2026-08-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.29998v1 Planning-time intervention fidelity is a distinct, measurable property of a learned world model: whether the model's own open-loop transitions move task variables the way matched environment interventions do. In the settings we test, it is neither revealed by reward fit nor ensured by task-anchored training. Across released TD-MPC2 checkpoint sizes, episode return falls as an operator-error diagnostic on task observables grows, while reward-prediction error stays small and nearly flat, and a self-supervised world model trained without task signal preserves the same operator substantially better than a task-anchored model on the shared task. A capture-gated matched-intervention audit then localizes what fails. On Cheetah, three LeWorldModel checkpoints capture the current task query and support decodable real intervention effects; however, their imagined five-step effects are worse than predicting no effect and worse than an environment-endpoint oracle. The failure is task-direction rotation with excess gain, not feature collapse. This severe pattern is conditional: five PreJEPA seeds retain an oracle-relative deficit without it, Finger Spin experiments extend the deficit beyond locomotion with heterogeneous severity across seeds, and shared-bank effect geometry is both candidate- and support-dependent. We also test practice-side questions. In DreamerV3 the posterior distribution, not its sample, carries the current query; ensemble disagreement ranks error only near training support; and a frozen support-aware score degrades held-out error ranking in both tested transfer directions while native disagreement remains informative in both. We conclude that intervention fidelity must be audited directly, capture-first, on the model's native interface. --- ### Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation Authors: Xing Xie, Jiawei Liu, Shijun Zhou, Huijie Fan, Zhi Han, Yandong Tang, Liangqiong Qu Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29997v1 We propose Discrete Diffusion Bridges (DDB), a novel framework designed to resolve the fundamental spatiotemporal misalignment of standard discrete diffusion in image translation and generation. By corrupting data into a pure mask state via a random schedule, the conventional forward process induces a twofold misalignment: spatially, this pure-mask destination entirely discards the rich structural priors of the source image; temporally, the random masking order inherently contradicts the ``easy-first, hard-last'' decoding mechanism used during inference. To address this, DDB constructs a direct and efficient trajectory between domains. Spatially, we introduce a hybrid absorption mechanism that redefines the absorbing state to a stochastic mixture of mask and source tokens, effectively injecting source prior as spatial anchors into the latent space. Temporally, we design an information-guided noise schedule that quantifies semantic variation to prioritize the corruption of high-information regions at earlier timesteps. This ensures the model learns to resolve difficult semantic changes using robust context from invariant regions. Extensive experiments validate the versatility and robustness of our framework across diverse generative paradigms. DDB effectively balances edit alignment with structural fidelity across both text-guided semantic manipulation and pure structural image translation, while inherently complementing text-to-image generation and guaranteeing robust high-quality decoding under extremely low sampling steps. Code and models are available at \href{https://github.com/HKU-HealthAI/DDB}{https://github.com/HKU-HealthAI/DDB}. --- ### Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models Authors: Aditi Sarker, Nazreen Shah, Rafi Ibn Sultan, Rhongho Jang, Dongxiao Zhu, Prashant Khanduri Published: 2026-08-30 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.29996v1 Large Vision-Language Models (LVLMs) achieve strong performance across many multimodal tasks; however, they often exploit spurious object-background correlations, resulting in predictions driven by contextual shortcuts rather than object-relevant visual evidence. Despite growing interest in hallucination and robustness evaluation, existing benchmarks provide limited control over whether model predictions are grounded in the target object or induced by correlated background cues. In this work, we introduce PURGE (\underline{P}artition-aware \underline{U}nlearning for \underline{R}emoving spurious-correlation \underline{G}enerated \underline{E}rrors), a framework for constructing, benchmarking, and mitigating spurious-correlation-induced failures in LVLMs. The framework consists of: -- (1) Structured dataset construction wherein we develop three complementary structured data construction strategies that partition examples by object-relevant evidence and spurious background cues, enabling controlled diagnosis of shortcut reliance; and -- (2) Partition-aware unlearning, which uses these partitions to selectively remove spurious object-background associations while preserving object-based reasoning. We evaluate the \algo~framework across multiple LVLMs, including LLaVA-1.6-7B, Qwen3-VL-8B-Instruct, and Qwen3.5-9B, together with CLIP as a vision-language encoder, on a diverse suite of benchmarks, including CHAIR, POPE, Causal-HalBench, MM-SpuBench, AMBER, MMHal, and Waterbirds. Our results show that PURGE consistently reduces hallucinations and spurious-correlation-driven errors while maintaining or improving overall performance in most evaluated settings, providing both a reusable evaluation protocol and an effective mitigation framework for more reliable LVLMs. --- ### Generating Clinical Vignettes that Preserve Cognitive Formulations Authors: Amit Oren, Nimrod Hertz-Palmor, Dean Ariel, Guy Laban Published: 2026-08-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.29995v1 Large language models can generate fluent clinical case vignettes, but fluency alone does not ensure fidelity to a specifiable clinical structure. We introduce FORMA, a theory-grounded framework that compiles a cognitive model of a disorder into a directed weighted graph, samples a person-specific configuration of that graph, and validates whether the generated vignette preserves the specified components and causal links. We instantiate FORMA on Posttraumatic Stress Disorder using the Ehlers and Clark cognitive model, generating 16,500 vignettes across 500 personas, 11 generation models, and three ablation conditions. Evaluation combines an external edge-recovery probe, two clinical experts, a scaled LLM judge, and a clinician user study with 100 licensed practitioners. The cognitive graph is recoverable from full-condition vignettes (MCC = +0.41, AUC = 0.70) but not from zero-shot generation (MCC = +0.01, AUC = 0.50). Experts rate full vignettes substantially higher than zero-shot alternatives, and clinicians perceive them to be human-written 85% of the time, compared with 22% for zero-shot. FORMA also reduces demographic disparity in perceived quality by 1.5-7x. These results show that cognitive formulation can serve as an auditable specification for scalable synthetic clinical text generation. A repository with the data and code is available online: https://github.com/Amit-Oren/FORMA. --- ### SVI2LoD3: Agent-Driven Reconstruction of LoD3 Facade Openings in Semantic 3D City Models from Volunteered Street View Imagery using Large Language and Visual Models Authors: Elmehdi Kanna, Lukas Arzoumanidis, Huynh Duc An Son Nguyen, Youness Dehbi Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29992v1 This paper presents an end-to-end, agent-driven pipeline for the LoD3 reconstruction of facade openings in 3D city models, producing directly usable CityGML-conform outputs. In contrast to existing approaches that rely on supervised semantic segmentation and therefore require large amounts of manually annotated training data, the proposed method employs a zero-shot segmentation strategy. This substantially reduces the annotation effort while still achieving strong performance in our benchmark on the eTRIMS dataset. A further key contribution is the enforcement of correct partonomic hierarchies, thereby producing CityGML-conform LoD3 building models. Beyond the reconstruction pipeline itself, this work also introduces a novel evaluation metric for facade reconstruction, termed Facade Feature Distance (FFD). Unlike conventional metrics such as mIoU or FRDS, which assess similarity primarily through pixel-wise overlap, FFD measures distance in a high-level feature space derived from a vision transformer. In doing so, it captures both semantic correctness and architectural layout, providing a more suitable assessment of facade reconstruction quality. The proposed pipeline and evaluation strategy together offer a practical and scalable contribution toward the automated generation and analysis of semantically enriched 3D city models. The developed code is published at: https://github.com/hcu-cml/citydb-SVI2LoD3-ai. --- ### Beyond Fluency: A Rubric-Based Benchmark for Evaluating Saudi Dialect and Cultural Competence in Large Language Models Authors: Ghassan Al-Sumaidaee, Sajjad Abdoli, Ahmed Rashad, Maxim Legg Published: 2026-08-30 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.29990v1 Large language models are increasingly deployed in Arabic-speaking markets, yet standard benchmarks overwhelmingly reward Modern Standard Arabic (MSA) fluency while leaving dialectal and culturally grounded competence unmeasured. This gap is consequential: everyday Arabic is largely dialectal, and dialect encodes social meaning that MSA-centric evaluation cannot capture. We present a rubric-based benchmark for the Saudi dialect, comprising 31 expert-authored prompts spanning idiomatic, pragmatic, lexical, and culturally-embedded phenomena, each paired with an expert-established ground truth. Our methodology separates evaluation into a model-agnostic phase, in which atomic, MECE positive criteria are derived solely from the ground truth, and a model-specific phase, in which four state-of-the-art systems -- Claude Opus 5, Gemini 3.7, GPT-5.6, and Kimi K3 -- are scored against those criteria and penalised for errors they actively introduce. Across 124 model-prompt evaluations we catalogue 466 error instances under a nine-category taxonomy. The four systems cluster within a narrow macro-average band (42.7%-53.1%), with no model exceeding 55% and every model recording at least one negative-scoring prompt, confirming that Saudi dialectal competence remains broadly unsolved. Notably, Ambiguous Framing is the dominant failure mode (37.3% of errors) while outright Hallucination accounts for only 11.2%, indicating that models fail less by stating falsehoods than by distorting register and flattening pragmatic nuance. We further observe a consistency-versus-ceiling trade-off and model-distinctive error signatures. We release the full prompt set, ground truths, and scored rubrics to support reproducible dialectal evaluation. --- ### AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning Authors: Hanjun Luo, Qiushi Liu, Jingya Zhang, Haihong Pang, Jiaheng Wen, Yifei Ma, Yu Yao, Chengxi Zhang, Hanrong Zhang, Yankai Chen, Hanan Salam Published: 2026-08-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.29988v1 Large language models (LLMs) achieve strong reasoning performance, which depends critically on inference-time decisions. Yet these decisions are commonly handled by static, one-size-fits-all policies, limiting adaptation to diverse tasks and reasoning stages. Recent adaptive methods partially address this limitation, but they primarily adapt either decoding stochasticity (how the model explores) or reasoning compute (how long the model reasons) in isolation, leaving their interaction within a single reasoning trajectory unmodeled. To address this challenge, we shift toward a within-trajectory joint control view, and instantiate it in AutoCRAT, a decoder-side controller for frozen backbones. Using only signals available during decoding, AutoCRAT jointly adjusts sampling stochasticity and reasoning budget during generation. AutoCRAT operates over a discrete action space and updates control decisions only at semantic boundaries, improving stability while remaining responsive to the evolving reasoning process. Comprehensive evaluation across 6 benchmarks demonstrates that AutoCRAT (I) uses 13.8-52.7% fewer inference tokens on average than recommended static configurations, (II) surpasses recommended static and adaptive baselines by 1.5-4.5% in relative accuracy, and (III) enjoys strong cross-backbone transferability. --- ### Robust Broad Learning System with Wave Loss for Classification under Data Uncertainty Authors: Mushir Akhtar, A. Varshney, A. Quadir, A. Rahaman, M. Tanveer, Mohd. Arshad Published: 2026-08-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.29983v1 Broad Learning System (BLS) offers an efficient alternative to deep architectures by enabling fast learning through randomized feature mapping and closed-form solutions. However, its reliance on squared error loss makes it highly sensitive to noise, outliers, and corrupted labels, limiting its reliability in real-world scenarios. To address this limitation, we propose Wave-BLS, a robust broad learning framework that integrates the wave loss function, which is asymmetric, bounded, and smooth, enabling controlled penalization of large errors. The proposed formulation replaces the standard least-squares objective with a wave-loss-based optimization problem, solved efficiently using a Nesterov accelerated gradient (NAG)-based scheme without requiring matrix inversion, thereby improving scalability. Extensive experiments on 30 UCI benchmark datasets demonstrate that Wave-BLS consistently outperforms classical BLS and several robust variants. Statistical validation using Friedman and Nemenyi post-hoc tests confirms the significance of the observed improvements. Furthermore, robustness evaluations under controlled noise and outlier injection reveal that Wave-BLS exhibits substantially slower performance degradation compared to BLS, even in challenging contamination settings. These results establish Wave-BLS as a stable and robust alternative to existing broad learning models for learning under data uncertainty. --- ### FIS-OT: Feature-Induced Optimal Transport for Unsupervised Action Segmentation Authors: Linxiang Peng, Xinyao Qin, Jinhan Li, Di Yang, Jiangtao Wang Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29980v1 Unsupervised action segmentation is a challenging task. It involves finding action categories and boundaries in videos without labels. Existing Optimal Transport (OT) methods use global constraints. This causes them to overlook the use of local information. Furthermore, existing Optimal transport architectures are prone to confirmation bias because they overly trust the pseudo-labels they generate. This causes models to learn from noise in the early training stages. To address these issues, we propose FIS-OT. It is a novel Feature-Induced Structured Optimal Transport framework. First, we introduce a Feature Enhanced Generator (FEG) module. It serves as an internal regularizer. By using triplet loss, FEG captures local consistency. It provides robust supervision that is independent of noisy pseudo-labels. Second, we propose a Feature-Induced Residual Structural Prior. This combines a fixed temporal backbone with dynamic feature similarities. This design ensures temporal continuity. It also allows the solver to adapt to complex action structures. Finally, we establish a cyclic optimization loop. This aligns local feature learning with global structural alignment. Extensive experiments on the three datasets show the effectiveness of our method. --- ### Evolutionary Soups: Evolving Mixture-of-Experts for Multi-Objective LLM Alignment Authors: Lingxiao Kong, Steffen Staab, Cong Yang, Oya Beyan, Zeyd Boukhers Published: 2026-08-30 Categories: cs.CL, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2608.29978v1 Large language models are increasingly required to generate responses that satisfy multiple competing objectives. Since optimal trade-offs depend on both user preferences and input prompts, controllable multi-objective generation must dynamically adapt models at inference time without retraining. To address this, we propose Evolutionary Soups, a mixture-of-experts framework for fine-grained generation control, with gating networks trained via an evolutionary algorithm. The per-layer gating networks dynamically produce expert-merging coefficients from hidden-state representations, while the evolutionary algorithm incorporates greedy hypervolume contribution for effective evolution of these gating networks, achieving consistent improvements on large and noisy training datasets and broader coverage of the non-convex Pareto front. Experiments across three tasks demonstrate the effectiveness of Evolutionary Soups over baselines: it achieves the best hypervolume, linear utility, and Tchebyshev utility (~20% improvement) among controllable methods on all tasks. --- ### SpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models Authors: Amanuel Gizachew Abebe, Yasmin Moslem Published: 2026-08-30 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2608.29974v1 Detecting hallucinations in Large Vision-Language Models (LVLMs) requires both accurate span localization and well-calibrated confidence scores. Fine-tuned generative VLMs excel at identifying hallucinated text spans but suffer from overconfidence and high inference latency. Discriminative sequence taggers offer deterministic speed and superior calibration but exhibit conservative span recall. We present SpanCalib-VLM, a hybrid dual-system for the SHROOM-Visions Shared Task that combines a multimodal sequence tagger, consisting of XLM-RoBERTa-Large fused with a SigLIP vision encoder via cross-attention, with our fine-tuned generative VLM (Qwen3.5-4B-SHROOM-SFT). Through a Union-Calibrated Fusion strategy, candidate spans from the generative model are re-scored with calibrated probabilities from the sequence tagger. On the SHROOM-Visions English evaluation split, our ensemble achieves a Pearson calibration correlation of 0.41 and an overall IoU of 0.39, with a clean-response IoU of 0.91} and overall detection accuracy of 70.7%. We make our model weights and code publicly available. --- ### An Open-Source, Event-Driven Pipeline for Cryptocurrency Market Data: Ingestion, Forecasting, and On-Chain Fraud Detection Authors: Basil Sajid Shaikh, Melrick Mascarenhas, Nuzhat Faiz Shaikh Published: 2026-08-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.29973v1 Cryptocurrency markets generate high-frequency, multi-source data that is expensive to work with unless a team already has commercial-grade streaming and warehousing infrastructure in place. This paper describes a fully open-source pipeline that reproduces the behavior of a cloud-native, event-driven system -- file arrival triggering a message, a message triggering compute -- entirely on commodity hardware, using Apache Kafka and a filesystem-watching poller in place of managed cloud triggers. The pipeline partitions historical Gemini exchange data into hourly and minutely files, ingests them asynchronously through two independently grouped Kafka consumers (one for audit logging, one for Spark-triggered ETL), and lands cleaned output in a PostgreSQL warehouse with historical and aggregated schemas plus asset-specific data marts. We use the resulting Bitcoin data mart to compare a seasonal ARIMA model against a single-layer LSTM network for price forecasting, and separately apply Random Forest and Gradient Boosting classifiers, with additional engineered features, to the public Ethereum fraud detection benchmark introduced by Farrugia et al. We report the architecture, the modeling methodology, and the resulting metrics, and we are explicit about the limitations of comparing forecasts issued at different horizons and of evaluating fraud detection on a static, already-labeled dataset. --- ### EDGE: Engine for Deterministic Graph Evaluation through Conversation Simulation from Graph Structured DSL Configuration Authors: Ram Kulathumani, Regunathan Radhakrishnan, Anupam Tripathi, Xiangbo Mao, Roshanak Omrani, Keshav Somani, Shwet Kamal Mishra, Shayna Lurya Published: 2026-08-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.29971v1 As agentic systems evolve into complex multi agent orchestration workflows, there is a growing and critical need for systematic frameworks that measures an agent's behavioral consistency and determinism. In this paper, we introduce a formal evaluation methodology that is grounded in AgentGraph, a planner powered by a domain specific language that represents agent reasoning through a dynamically adjustable directed graph. We leverage this structural formalism and utilize graph traversal algorithms that exhaustively enumerate conversational paths, forming a comprehensive evaluation set that captures the agent's complete behavioral space. We then systematically replay these reproducible trajectories to compare observed outputs and state transitions against the intended DSL specification. To quantify reliability, we define novel metrics that measure response and trajectory determinism, structural adherence and semantic consistency across both exact replays and their linguistic variants. Our system's results demonstrate that agents configured using frameworks like AgentGraph and LangGraph with explicitly structured node transitions show superior determinism over agents that are not configured with controlled transitions. --- ### Confidence-Aware Ensemble and Long-Word Refinement for Artistic Text Recognition Authors: Lucas A. Dias, Henrique A. Schulz, Rafaela de Miranda, Guilherme L. Peres, Pedro L. Bittencourt, Rayson Laroca Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29970v1 Artistic Text Recognition (ATR) remains challenging because word images often combine decorative fonts, curved layouts, object-like characters, clutter, and severe distortions. This paper studies WordArt-V1.5 as a standardized benchmark for this setting and evaluates recent scene and artistic text recognizers under a common protocol. We propose a confidence-aware ensemble that combines SVTRv2, PARSeq, and MAERec after fine-tuning on the official training split. The ensemble selects predictions using the minimum confidence over disagreement positions, emphasizing characters that separate competing hypotheses. For long words, where a single character error can invalidate the whole prediction, we add a targeted refinement stage based on Needleman-Wunsch alignment and lexicon-guided correction. On the WordArt-V1.5 Test B split, the proposed system reaches 89.90% Word Recognition Accuracy, improving the best individual fine-tuned model by 1.77 percentage points. The long-word refinement produces a modest global gain, but improves the targeted long-word subset by 2.72 percentage points. Finally, an error analysis of all remaining mistakes shows that 48.8% are associated with labeling issues, visual ambiguity, or illegible samples, highlighting the value of diagnostic reporting for future ATR benchmarks and models. Our source code is available at https://github.com/lucas-azdias/Artistic-Text-Recognition/. --- ### Training-Free Action Correction for VLA Model Failures via Language Feedback Authors: Owen Kwon, Pablo Ortega-Kral, Arthur Bucker, Jean Oh Published: 2026-08-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.29967v1 Vision-Language-Action (VLA) models demonstrate strong semantic understanding yet exhibit systematic failures during deployment. The conditions under which these failures occur, and whether they can be corrected without retraining, remain poorly understood. In this paper, we take steps toward addressing this gap. We present CorrectVLA, a framework that translates task-level natural language corrections into additive action magnitude adjustments without modifying policy weights. A human provides a single task-level correction, applied uniformly across all rollouts without per-episode intervention. In simulation, CorrectVLA recovers execution misalignment failures across both in-distribution and OOD tasks. In real-robot experiments on a UFactory xArm7 under environment shift, CorrectVLA restores near-perfect success where the base policy almost entirely breaks down, generalizing across object locations and identities. Through a taxonomy of failure modes on LIBERO-90, we find that execution misalignment failures, where the policy reaches the correct target but miscalibrates action magnitudes, represent the correctable subset, while other failure modes where semantic comprehension itself breaks down are not amenable to this approach. The approach succeeds when policies possess strategic correctness and fails when fundamental comprehension is absent, establishing a practical operational boundary for inference-time correction. --- ### DataFoundry: Evolving Data Preparators via Recursive Self-Improvement Authors: Cehao Yang, Xiaojun Wu, Xueyuan Lin, Chengjin Xu, Xuhui Jiang, Hui Xiong, Jian Guo Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29966v1 Domain adaptation of large language models increasingly depends on constructing high-quality training data, yet existing data-preparation pipelines typically address quality only after generation through post-hoc filtering. This creates a fundamental mismatch: data-quality issues often originate from the construction process itself, while quality control is applied only to its outputs. We introduce \textsc{DataFoundry}, a framework for \textbf{evolving data preparators through recursive self-improvement} before large-scale data production. \textsc{DataFoundry} represents a data preparator as an evolvable runtime specification and instantiates its evolution with a \textsc{Skills-as-Modules} architecture, in which a central \textsc{Controller} orchestrates modular skills to compile executable runtimes, diagnose deficiencies on small pilot sets using domain-appropriate criteria, and translate diagnostic feedback into adapters that revise individual preparation components while preserving stable interfaces. We evaluate \textsc{DataFoundry} on DataPrep-Bench across mathematics, finance, law, and medicine, and find that recursively evolved preparators produce training data with higher downstream utility than baselines. Experiments across different backbones further demonstrate that these improvements are not tied to a particular model, while analyses and case studies further reveal the framework's optimization dynamics and illustrate how its evolution unfolds in practice. --- ### Review Before Trust: Source-Grounded Integrity Gates for AI-Assisted Personal Health Records Authors: Nora Girda, Adrian Groza Published: 2026-08-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.29965v1 Large language models can convert medical documents into structured data, but plausible output may still be unsupported by the source. Persisting such output in a longitudinal health record, a record that accumulates patient information over time, therefore creates an integrity risk: unverified data may influence later summaries, trends, or preventive-care computations. We introduce an evidence-gated trust-promotion model that keeps generated data provisional until a deterministic monitor verifies it against the source document. The monitor admits a candidate for a specified downstream use only when the source contains a unique supporting quotation, the relevant fields occur within the same laboratory row, and the required provenance is preserved. The generator cannot approve its own output, missing or ambiguous evidence causes refusal, and refused candidates remain available for human review rather than being silently discarded. We implement the model in Medical DataCloud, a personal health-record application, and evaluate it through automated tests and a replay of saved extraction outputs. All 22 conformance and mutation tests pass. The replay covers nine historical laboratory PDF reports containing 102 manually labelled rows. The reports produce 97 numeric candidates: schema validation accepts all 97, an earlier packet-level evidence check accepts 94, and the hardened quotation- and row-level policy admits 72 while retaining 25 for review. The study evaluates system integrity rather than clinical correctness or clinical safety. The results demonstrate the technical feasibility of an enforceable boundary that prevents generated claims from authorizing their own reuse in a longitudinal health record. --- ### Generative vs. Encoder Models for Multilingual NER: A Comprehensive Empirical Study on Naamapadam Authors: Jakkala Mahesh, Jatavath Shravan Kumar, Komalla Shivani, Sujoy Sarkar Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29959v1 Language is humanity's most consequential technology, yet for over a billion speakers across India's twenty-two constitutionally recognised languages, its digital layer remains structurally incomplete. Named Entity Recognition (NER), the foundational step in transforming raw text into machine-interpretable knowledge, has been studied exhaustively for English but remains largely unsolved across most Indic languages. This paper presents a rigorous comparative study of generative and encoder-based neural architectures for NER on all eleven languages of the Naamapadam benchmark. We evaluate five classic model families spanning sequence-to-sequence transformers and multilingual encoders; four decoder-only large language models (LLMs) fine-tuned with LoRA and 4-bit NF4 quantisation; and nine generative models in zero-to-5-shot inference. Under strict CoNLL span-level evaluation, encoder-based models (mBERT and XLM-R, both F1=0.675 on Hindi) substantially outperform every generative architecture in ten of eleven languages, with gaps of 7.5-40 percentage points against the strongest competitor (Gemma-2-2B: avg F1=0.427). The best few-shot result reaches only 28% of the encoder baseline. We identify three language clusters--encoder-dominant, partial-coverage, and failure-zone; and provide actionable deployment guidelines grounded in transfer learning and low-resource NLP principles. ---