AI News Archive: August 12, 2026 — Part 16

Sourced from 500+ daily AI sources, scored by relevance.

• Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Models

  Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural elements. However, DML construction typically relies on expert interpretation of technical documentation, limiting scalability for complex systems. ...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12304v1
• Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence

  Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows. Their inherent stochasticity causes minor variations in textual prompts or hyperpa...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12290v1
• VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies

  Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation. We introduce VAKRA (e\textbf{V}aluating \textbf{A}PI and \textbf{K}nowledge \textbf{R}etrieval \textbf{A}gents), a benchmark of over $...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12282v1
• A Neighborhood Attention Transformer Network for Enhanced 3D Segmentation of the Left Anterior Descending Artery

  Background: Accurate segmentation of the Left Anterior Descending (LAD) artery in 3D free-breathing, non-contrast CT is critical for cardiac dose sparing in thoracic radiotherapy. The LAD is extremely small, has poor soft-tissue contrast, and varies substantially across patients; even manual contour...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12274v1
• How Organizations Use AI: Evidence from ChatGPT

  We study how organizations use frontier generative AI by linking ChatGPT Enterprise account records to usage, worker roles, task classifications, and public-company financial data through March 2026. These linked data enable a privacy-preserving analysis of adoption, worker roles, and message-level ...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12236v1
• Few-Shot Ordinal Learning for Day-Wise Freshness Estimation with Hyperspectral Fish Images

  Non-destructive food quality assessment has increasingly benefited from hyperspectral imaging (HSI), which captures spectral signatures linked to biochemical changes during storage. Estimating day-wise freshness, however, remains challenging owing to strong inter-fillet variability and scarce labell...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12230v1
• Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge

  Large language models are increasingly trained and deployed with long contexts that span documents, code repositories, and interaction histories. This scaling reflects the implicit assumption that training on longer contexts will only help the model by exposing it to richer evidence. We challenge th...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12218v1
• HYDRA: Hyperbolic Dynamic Representation Architecture for Kolmogorov-Arnold Networks

  Kolmogorov-Arnold Networks (KANs) enhance nonlinear function approximation by replacing scalar weights with learnable univariate functions. However, assigning an independent function to every connection results in substantial parameter redundancy, limiting their scalability and efficiency. To reduce...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12194v1
• How to Spend Your Oracle Budget: Practical Guidance for Protein Structure Prediction Models

  Foundation models for protein structure prediction remain unreliable on certain targets. External oracles can flag and correct these failures, but biological oracles are expensive, making oracle budget a critical constraint. Existing guidance methods, such as FK-steering, DPO, and Best K-of-N sampli...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12192v1
• HSTGFormer: Hyper Spatial-Temporal Graph Transformer for 3D Human Pose Estimation

  Transformer-based methods have achieved strong performance in monocular 3D human pose estimation, but most existing approaches organise spatial and temporal reasoning as separate stages, which may weaken unified spatial-temporal interdependencies inherent in human motion and compress frame-level str...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12187v1
• Co-constructing sociotechnical AI governance: participatory system mapping using algorithm registers

  Algorithm registers have been championed as a means of providing transparency on the use of algorithms in public services. Yet potential publics differ in their expectations of what should be made transparent and how, as well as in their interest in and ability to parse the information currently pub...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12166v1
• Adversarial Resilience of Poisson-Process Submodular Maximization over Matroids: From Robust Offline Optimization to Full-Bandit Learning

  We study nonnegative submodular maximization subject to a general matroid when the offline algorithm is given an arbitrary controlled value oracle. Our main result is an adversarial resilience theorem for the Spiteful Greedy Swap Poisson Process (SGS-Poisson): without modifying its Poisson intensity...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12134v1
• No One to Blame: A Framework of Constitutive AI Unaccountability

  The increasing deployment of autonomous, agentic AI systems challenges traditional accountability mechanisms. Existing research predominantly frames AI accountability gaps as barriers that can be overcome through better standards, transparency, and institutional reform. We argue that this framing is...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12104v1
• Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models

  Learning world models from offline trajectories enables agents to accomplish different tasks through planning. Object-centric (OC) representations, which decompose a scene into a set of slots that bind to its objects, have been proposed as an inductive bias for world models that are more sample-effi...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12078v1
• Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations

  Developing dialogue systems capable of engaging in multi-turn, goal-oriented conversations remains a significant challenge, especially in specialized domains with limited data. This research proposes a novel framework called Preference Tree Optimization (PTO), designed to iteratively improve agent m...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12062v1
• Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

  AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly understood. As AI development becomes faster and increasingly automated, mechanistic exploration remains largely manual, widening the gap betw...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12036v1
• How Far from Clinical Deployment? Evaluating the Complete Unsupervised Domain Adaptation Pipeline in Medical Imaging

  Deploying unsupervised domain adaptation (UDA) in clinical practice requires choosing which algorithm to use and which of its trained models to ship. However, the deployment (target) domain is unlabeled, so models cannot be evaluated directly on it, leaving it unclear which to select. We address thi...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12035v1
• LoSA: Near-Lossless Sparse Attention for Training-Free Video Diffusion Acceleration

  Video diffusion transformers are costly to sample: every denoising step applies self-attention over a long 3D token sequence, a quadratic cost that dominates as resolution and duration grow. Sparse attention reduces this cost without retraining, but existing methods pursue aggressive sparsity, where...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12032v1
• Uncertainty-Aware Probabilistic Constrained Clustering from Entangled Pairwise Supervision

  Pairwise constrained clustering typically relies on hard must-link/cannot-link labels, whereas realistic pairwise supervision may be real-valued and entangle intrinsic ambiguity, expert judgment, and stochastic corruption. Existing deep constrained clustering (DCC) methods mainly target hard, expert...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12027v1
• CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations

  Agents are increasingly considered for automating network operations and maintenance, where engineers must diagnose network faults, optimize configurations to enhance services, and reduce operational costs while acting under strict constraints. However, existing evaluations fail to accurately model ...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12002v1
• AVA-Encoder: Towards Agent-Native Video Representation Learning

  Creative agents still lack an effective way to learn from high-quality human films, limiting their ability to produce cinematic-grade videos. A key challenge is the absence of a structured video representation that is both faithful to film content and directly usable for agentic reasoning and manipu...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12313v1
• tash

  The investment platform for trading cards

  🧰 ToolsAug 12, 2026https://www.producthunt.com/products/tash?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+the500feed+%28ID%3A+283491%29
• Large Language Model-Driven Small-Capitalization Trading: Integrating Financial News Sentiment, Macroeconomic Indicators, and Technical Signals

  Large language models can extract richer signals from financial news than fixed sentiment lexicons, and recent work has explored feeding such signals into portfolio construction. We study an uncertainty-aware construction that feeds model-predicted risk -- decomposed into aleatoric and epistemic com...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12283v1
• A Cascaded Unsupervised-Supervised NLP Pipeline for Detecting Accusatory Language in Public Procurement

  Public procurement involves the allocation of substantial financial resources; therefore, continuous oversight through audits, controls, and monitoring mechanisms is essential. However, stakeholder comments and publicly available government data are often underutilized, despite their potential to re...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12269v1
• Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus

  We present the first systematic study of Massive activations (MAs) in layer-interleaved HLA LLMs and uncover two architecture-aligned morphologies: MAs consistently spike immediately before full attention layers, forming pre-attention spikes (PAS), and can persist through intervening linear attentio...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12149v1
• SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges

  While retrieval-augmented generation (RAG) has proven effective at giving LLMs access to external knowledge, mainstream dense-retrieval implementations remain inherently limited in handling structured constraints and multi-hop reasoning. Graph-based methods address this by constructing knowledge gra...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12129v1
• Structuring the Space of Perspectives

  The same event can be reported from different perspectives depending on the experiences, background, and beliefs of the writer or speaker. A variety of NLP areas engage with perspectives, spanning from text analysis to algorithm optimization. A wide range of operative concepts (such as stances, sent...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12113v1
• RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation

  We present RT-SEMamba, a fully causal speech enhancement (SE) model built upon causal time-frequency Mamba blocks. Unlike Transformer-based architectures that rely on a growing key-value cache, Mamba propagates a fixed-size recurrent state per layer, enabling memory- and bandwidth-efficient long-for...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12099v1
• Poly-Dialectal Neural Machine Translation System for Bangla Regional Dialects

  Regional dialectal variation poses a fundamental challenge to natural language processing (NLP) in Bangla, where over 240 million speakers communicate across diverse regional variants that diverge significantly from Standard Colloquial Bangla (SCB) in phonology, morphology, and lexicon. Contemporary...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12018v1
• Asymptotic Risk Calibration for Selective Question Answering

  Large language models (LLMs) may generate fluent but incorrect answers, making uncertainty quantification important for reliable question answering. However, heuristic uncertainty scores cannot perfectly distinguish correct predictions from incorrect ones, and directly applying a fixed uncertainty t...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.12008v1
• Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed

  Small Language Models (SLMs) have emerged as a more efficient alternative to traditional Large Language Models (LLMs), offering promising potential in resource-constrained scenarios. Existing approaches to building SLMs typically follow two paths: training compact models from scratch, or compressing...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11981v1
• Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill

  Turning a research idea into a complete paper requires more than text generation: the system must retrieve literature, design and execute experiments, revise claims according to evidence, produce publication-ready figures, and maintain consistency across a long generation process. We present Spark-t...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11924v1
• LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured -- Reinforced Polarizer Keeps a Frozen LLM from Being Confidently Misled by the Wrong Evidence

  Predictive-distribution entropy makes a strong selection rule in retrieval-augmented question answering: across five QA benchmarks, keeping the candidate answer that a frozen respondent LLM produces with the lowest answer-token entropy lifts mean answer $F_1$ from 0.4769 to 0.5148 over the retriever...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11922v1
• LazyTrain: Limited-resource Allocation toward Zero-waste Yield Optimization in Large Language Model Training

  Training large language models on limited hardware is increasingly a scheduling problem across GPU compute, host memory, PCIe transfer, and storage bandwidth. Existing offloading systems reduce GPU residency, and MegaTrain shows that a CPU-master layer-streaming executor can train large models on a ...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11919v1
• DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation

  Prompting-based (\textit{i}.\textit{e}., non-fine-tuning) Text-to-SQL methods, where underlying large language model parameters are not changed for the task, face three problems: (\textit{i})~relying on coarse-grained schema information that may not reveal the fine-grained relationships needed to di...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11889v1
• ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents

  Large language model (LLM) agents integrated with external tools are vulnerable to indirect prompt injections embedded in environmental states. However, existing studies largely rely on manually implemented or reused environments, stochastic LLM-based tool simulation, and predefined injection locati...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11878v1
• Quantifying the Relationship Between Clinical Safety and Environmental Impact in Therapeutic LLMs

  The deployment of large language models (LLMs) in mental health contexts raises questions about the relationship between clinical safety and environmental cost. In this paper, we examine this relationship by combining K-Bench clinical safety scores with EcoLogits life-cycle assessment estimates acro...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11830v1
• Tatbith

  Make your hifdh firm

  🧰 ToolsAug 12, 2026https://www.producthunt.com/products/tatbith-quran-memorization?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+the500feed+%28ID%3A+283491%29
• Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling

  On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning. It is commonly believed to enable the student model to distill knowledge from a stronger teacher model, thereby expanding capabilities beyond the pre-OPD base model. In this study, we examine...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11829v1
• How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment

  State-aligned distortion has been documented in China-origin text-based large language models (LLMs), but whether, and in what form, it arises in multimodal systems has not been systematically examined. We construct a balanced benchmark of 200 core entries spanning ten politically sensitive topics, ...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11816v1
• TELLME: Test-Enhanced Learning for Language Model Enrichment

  Continual pre-training (CPT) has been widely adopted as a method for domain adaptation in large language models. However, CPT has consistently been accompanied by challenges, such as the difficulty of acquiring large-scale domain-specific datasets and high computational costs. In this study, we prop...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11788v1
• GRPO for Financial Advice Generation: Outperforming Commercial LLMs under CATE Evaluation

  Generating actionable financial advice from business records demands that models integrate numerical reasoning, domain knowledge, and sound judgment, while avoiding recommendations that could harm the business. Direct supervision is difficult: historical decisions are not necessarily optimal, and hi...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11787v1
• The Sleeping Agent: What Gist-Based Context Compression Loses and Why

  Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood. We use Salience-Weighted Consolidation (SWC), a biologically-...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11775v1
• Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library

  When a language model answers an interventional question, the computation it must perform depends on the type of evidence the query requires. We report a decoupling in how a transformer organizes causal knowledge: slot-by-type structure induced by type-level supervision organizes routing, yet remain...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11767v1
• AWARe: Mitigating Catastrophic Forgetting via Activation-Weighted Adaptive REtention

  Multimodal Large Language Models (MLLMs) exhibit strong generalization and reasoning abilities due to large-scale multimodal pre-training. However, fine-tuning these models on downstream tasks often leads to catastrophic forgetting, where newly learned task-specific knowledge degrades previously acq...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11758v1
• Locating and Controlling Implicit Personalization in Large Language Models

  Large language models (LLMs) often shift their outputs in response to implicit demographic cues even when users never state a demographic identity. Previous work has documented this behavior, but the connection between these behavioral changes and the model's internal activations remains unclear. Us...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11735v1
• When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use

  The reliability of Large Language Models (LLMs) for API calling degrades in multilingual settings. A common failure occurs when a model selects the correct tool but generates argument values in an inconsistent language, which we term Argument Language Mismatch (ALM). Although semantically correct, s...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11715v1
• The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance

  A benchmark score comes from a single phrasing of each problem. That single phrasing is treated as if it stood for the whole space of ways the same problem could be asked, but it does not. We show that rephrasing a problem while keeping its meaning and answer fixed routinely flips a model's answer i...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11694v1
• Claim-Level Reliability Assessment for Efficient Test-Time Reasoning

  We propose claim-level falsification as a principle for test-time scaling and instantiate it through Claim-Level Reliability Assessment (CLR), a training-free framework that reallocates test-time compute from additional solution sampling to targeted verification. Since whole-trace evaluation often o...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11994v1
• Accuracy and Order Sensitivity Diverge Under Label-Free Strategies

  Multiple-choice benchmarks are widely used to evaluate large language models, but MCQ scores conflate knowledge with sensitivity to option order, which makes them unreliable measures of model knowledge. In this paper, we test whether preventing a model from seeing option labels while committing to a...

  📄 ResearchAug 12, 2026http://arxiv.org/abs/2608.11947v1