AI News Archive: August 10, 2026 — Part 22

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

• MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts

  Large language model-based multi-agent systems have recently shown strong potential for complex, long-horizon tasks. However, existing methods mainly rely on coarse prompt-level differentiation without parameter adaptation for diverse subtasks, resulting in insufficient inter-agent heterogeneity and...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09251v1
• Failure-Aware Long-Form Translation: Design and Implementation of a Recoverable LLM Translation System

  A long-form translation request can succeed at the API layer and still produce an unusable result. The output may be empty, truncated, filtered, dominated by source or prompt material, or interrupted after producing text worth keeping. This report describes a recovery protocol developed for a deploy...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09187v1
• UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following

  Large language models (LLMs) are increasingly expected to follow long lists of constraints in complex instructions, and synthesizing instructions from a reference document (i.e., back-translation) is a widely used method to measure/enhance LLMs' ability to follow complex instructions. However, this ...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09154v1
• Supamodel

  AI Product Photos at scale for Shopify

  🧰 ToolsAug 10, 2026https://www.producthunt.com/products/supamodel?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+the500feed+%28ID%3A+283491%29
• An Agentic Generative Large Language Model for Treatment Planning of Colorectal Cancer

  Treatment planning in precision oncology requires synthesizing heterogeneous patient information with rapidly evolving clinical guidelines to ensure guideline-concordant care. While large language models (LLMs) show promise in many diagnostic tasks, their adoption for high-stakes treatment planning ...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09142v1
• Beyond Direct Identifiers: Probabilistic Privacy Risk Estimation for Privacy-Conscious LLM Query Delegation

  Recent work on protecting privacy during user-LLM interactions often focuses on direct, explicit identifiers: the personally-identifiable information (PII) captured by standard detectors. One such approach is Privacy-Conscious Delegation (PCD), where a local LLM acts as an intermediary. However, pri...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09140v1
• Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent Game Tournaments

  LLM agents are increasingly deployed in multi-agent social settings where they must cooperate, negotiate, and adapt to other agents. Measuring and improving these social skills is hard because, unlike math or logic, social interaction offers no objective ground truth: evaluations fall back on LLM ju...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09128v1
• LexKairos: Benchmarking Legal Temporal Capabilities in LLMs

  Large language models (LLMs) have demonstrated strong performance across a wide range of legal tasks. In legal practice, time is a critical concept that governs the validity of statutes, the progression of legal cases, and the enforcement of procedural deadlines. However, legal temporal capabilities...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09106v1
• Evo-Bench: Can Language Models Improve Agent Harness?

  Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomously optimize its own operating harness. However, systematically benchmarking thi...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09096v1
• The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora

  How a document's arrangement is written down, its notation, is a training variable that no dataset card records. The field has established that text-extraction choices change model behaviour, and has never once measured the notation of what those choices put into the corpus. We define clean-window s...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09093v1
• When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information

  Large Language Models (LLMs) have achieved strong performance in medical question answering and clinical reasoning tasks. However, their reliability under uncertainty remains poorly understood which raises critical concerns for deployment in high-stakes clinical settings. In such environments, incor...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09080v1
• Tree-of-Experience: Hierarchical Experience Management for Self-Evolving Agents

  Continual self-evolution requires LLM agents to transform environmental interactions into reliable and reusable experience. Existing methods typically refine individual trajectories or abstract shared knowledge from related trajectories, but their experience representations are often disconnected fr...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09044v1
• Structured Phonological Representations for Audio-Articulatory rtMRI Speech Classification

  Real-time MRI makes it possible to observe vocal-tract articulation during speech, but mapping these articulatory patterns to phonetic and phonological categories remains challenging. We investigate whether PhonoQ, an audio-based model trained to recognize structured phonological features, provides ...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09767v1
• REFRAMED: Towards Realistic Audio Description Generation for Movies

  Audio Description (AD) is a verbal narration of key visual content in videos, enabling access for visually impaired audiences. Unlike standard video captioning, AD is a structured editorial task: descriptions must be inserted into gaps in dialogue and must convey only what is needed to understand th...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09765v1
• VeriForge: Mitigating Latent Knowledge Gaps in Narrative Drafting via Mixed-Initiative Scaffolding

  Great fiction earns its verisimilitude through precise details, from how a longsword is gripped to pierce armor gaps to why a bleeding corpse cannot yet smell of decay, weaving domain expertise into the fabric of invented worlds. Current AI writing tools offer limited support for discovering and int...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09698v1
• MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL

  Traditional Text-to-SQL research and benchmarks assume a known target database, overlooking settings in which a query must be routed within a large, heterogeneous database collection. We therefore study schema linking in a multi-database setting, where the system must first locate the target databas...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09588v1
• Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization

  Direct Preference Optimization (DPO) aggregates token-level log-probability ratios via uniform summation, implicitly treating all tokens as contributing equally to the preference signal. However, the contribution of individual tokens to the preference signal varies. We introduce token credit, which ...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09568v1
• Mawqif-v2: An Arabic Benchmark Dataset for Cross-Target Stance Detection

  Publicly available Arabic datasets for target-specific stance detection remain limited, particularly for evaluating cross-target generalization. This paper presents the Mawqif-v2 Extension, consisting of 996 manually annotated Arabic tweets collected from three public targets: Women Driving, E-Cars,...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09539v1
• Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching

  A main promise of looped language models (LMs) is depth-adaptive inference. By iterating a block of shared layers a variable number of times, the model can use less compute for "easy" tokens and more for "hard" ones. However, this adaptivity breaks standard batching: tokens in the same batch now req...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09444v1
• OutageDeck

  One status page for every service your stack depends on

  🧰 ToolsAug 10, 2026https://www.producthunt.com/products/outagedeck?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+the500feed+%28ID%3A+283491%29
• ZetaGPT: A Reference Implementation of Positional--Encoding--Free State--Space--Attention Language Models

  Transformer-based language models rely on self-attention, whose computation is permutation-equivariant and therefore lacks an intrinsic mechanism for representing token order. Existing architectures address this limitation by explicitly incorporating positional information through learned positional...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09432v1
• Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation

  User simulators are widely used as scalable environments for training and evaluating interactive assistants. Generating the next user turn is inherently one-to-many: the same profile and dialogue context may support multiple plausible continuations with different local interaction intents. A fluent ...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09420v1
• Universal or Language-Family-Specific Script Unification for Cross-Lingual Transfer? A Case Study on Turkic Languages

  Closely related languages written in different scripts expose little surface overlap to multilingual models, limiting cross-lingual transfer. We compare two approaches to script unification: the general-purpose uroman romanizer and the family-specific Common Turkic Script (CTS). We train matched fas...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09356v1
• UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers

  Neural language models trained on large crowdsourced corpora frequently exploit spurious surface patterns tied to target labels without true linguistic or causal relevance, boosting benchmark performance while failing on adversarial or out-of-distribution inputs. Existing approaches either require m...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09209v1
• EmoS: A Theory-Grounded Framework for Evaluating and Aligning Emotional Intelligence in Spoken Language Models

  Despite significant advances in instruction-following and auditory comprehension, the evaluation of Emotional Intelligence (EI) in Spoken Language Models (SLMs) remains confined to rudimentary paralinguistic perception, lacking a systematic, theory-driven cognitive framework. We introduce EmoSBench,...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09189v1
• Subjective Multi-Bias Detection with Large Language Models

  In this project, we delved into the pervasive challenge of bias detection within the text content. More specifically, our focus lies on the identification of subjective bias, a type of bias that introduces improper attitudes or portrays a statement at odds with the actual truth. The subjective bias ...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09126v1
• Bridging the Gap Between Semantics and Reconstruction:Unifying Sign Language Translation and Production

  Recent advances in sign language (SL) research have shown a trend toward unifying multiple sign language understanding (SLU) subtasks, such as isolated sign language recognition (ISLR), continuous sign language recognition (CSLR), and sign language translation (SLT), within a single framework, leadi...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09045v1
• Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization

  Users of modern platforms repeatedly need summaries of recent dialogue, but the window rarely contains enough context to be interpreted on its own. We formalize this setting as streaming dialogue summarization, where a system must summarize a current window using selective memory from an unbounded h...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09043v1
• Disentangling Co-Occurring Retinal Pathologies with Saliency-Guided Sparse Expert Routing

  Retinal fundus images frequently exhibit multiple co-occurring pathologies, yet standard deep learning classifiers apply static, identical computation to every image regardless of the underlying disease distribution. We propose a novel architecture that resolves this via sparse conditional computati...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09752v1
• CIFA: Contextual-Intersectional Fairness Auditing for Hidden Subgroup Discovery in Face Analysis

  Fairness evaluation in computer vision commonly relies on aggregate accuracy and demographic subgroup analysis. However, visual models are also sensitive to contextual factors such as illumination, blur, image quality, facial accessories, and appearance attributes. These factors may interact with de...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09669v1
• FactorDrive: Adaptive Multi-Step Reasoning Driven by Planning-Critical Factors for End-to-End Autonomous Driving

  Vision-language models (VLMs) have advanced scene understanding and enabled explicit reasoning in end-to-end autonomous driving. However, existing methods insufficiently integrate spatial-physical evidence into planning reasoning, while reasoning adaptation remains coarse-grained and falls short of ...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09591v1
• TeaMatch: Teachable Cross-Modal Representation Learning for 2D-3D Matching

  Learning reliable correspondences between images and point clouds is fundamental for 2D-3D matching. Despite recent progress in detection-free methods, existing approaches primarily optimize matching within a single model and often struggle to maintain reliable correspondences under challenging cond...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09590v1
• Towards Expressive and Faithful Audio-to-Image Generation: A Unified Multimodal Dataset and Synthesis Framework

  As an important subfield of cross-modal generation, synthesizing static visual content in the form of images from audio, namely audio-to-image (A2I) generation, has attracted increasing research attention in recent years. Nevertheless, despite the remarkable visual quality of modern text-to-image (T...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09529v1
• GeoRoute: Geometry-Aware Hybrid Inference for Traffic Future-Frame Prediction

  Long-horizon future-frame prediction is important for autonomous driving, traffic surveillance, and intelligent transportation systems, yet remains challenging due to temporal ghosting, geometry drift, and inconsistent object motion. Recent latent video diffusion models have achieved impressive visu...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09493v1
• RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation

  Unmanned aerial vehicle vision-language navigation (UAV-VLN) requires agents to translate visual observations and language instructions into reliable flight actions in complex environments. Although recent end-to-end UAV vision-language-action (UAV-VLA) policies reduce reliance on separately designe...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09467v1
• DiffSafeMerge: Mitigating Backdoor Inheritance in Diffusion Model Merging

  Unconditional diffusion checkpoint merging assumes benign sources, yet a compromised public checkpoint can transfer a dormant backdoor while clean generation appears normal. Mitigation is difficult without knowing the compromised source, trigger, or target, and broad sanitization may degrade image q...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09445v1
• NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge

  This paper presents a review of the NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge. The objective of the competition was to merge a set of misaligned smartphone images in the raw domain, captured in low-light conditions, into a single, clean image. Introduced setup simultaneously addres...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09782v1
• C$^2$A: Coupling Spatial Evidence with Clinical Priors via Co-occurrence Aware Class Attention for Multi-Label Chest X-Ray Classification

  Thoracic pathologies rarely occur in isolation, yet standard multi-label classifiers rely on shared global descriptors, discarding \emph{where} findings lie and \emph{how} they co-occur. We propose \textbf{C$\mathbf{^2}$A} (Co-occurrence Aware Class Attention), a classification head that explicitly ...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09774v1
• HandSplatter: Automated Digital Goniometry from Neural Rendering

  Hand and finger disorders are leading contributors to musculoskeletal disability, creating a clinical need for precise methods to quantify joint motion. Range of motion (ROM) serves as the metric for diagnosis, rehabilitation monitoring, and evaluating surgical outcomes. Currently, the goniometer is...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09735v1
• World Tokens: Enhancing Embodied Policies with Training-Time World Modeling

  Vision-language-action (VLA) models are a widely adopted paradigm for embodied policies. They excel at efficient closed-loop control but do not explicitly model how physical scenes evolve as a task unfolds. Recently emerging world-action models (WAMs) leverage pretrained video world models to captur...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09730v1
• LookAgain: Closed-Loop GUI Grounding with Visually Grounded Reflection

  Recent graphical user interface (GUI) grounders have significantly advanced single-shot accuracy on standard benchmarks, yet their performance degrades sharply on small targets, densely packed controls and out-of-distribution interfaces. We attribute this gap to a paradigmatic limitation shared by e...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09723v1
• Diffuse the object, keep its label: curating detector training data from a few unlabeled photographs via VLM-built 3D vegetation scenes

  Labeled images of small objects hidden in vegetation are scarce, and detectors trained on them generalize poorly across sites. Rather than reusing labels collected at another site, we synthesize labeled training images from a handful of unlabeled photographs of the deployment site itself. A vision--...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09691v1
• Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning

  Tool-augmented vision-language models increasingly "think with images": they call crop, zoom, or code tools and reason over the returned pixels. However, recent work using blind tests, gain decompositions, and attention analyses has shown that returned images contribute little, raising the question:...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09682v1
• EgoHieraLoc: A Cortically Inspired Hierarchical Segmentation-Guided Framework for Egocentric Visual Query Localization

  Visual query localization (VQL) aims to retrieve and re-localize a queried object in egocentric videos, yet remains challenging when object boundaries are ambiguous and global context cannot effectively guide fine-grained localization. Human vision handles such ambiguity through a hierarchical proce...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09656v1
• LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection

  Face presentation attack detection (PAD) aims to reliably detect a wide range of presentation attacks. While PAD methods achieve strong performance within individual datasets, their performance degrades under cross-dataset evaluation. Variations in sensors or lighting conditions can reduce the effec...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09633v1
• Unsupervised Domain Adaptation for Multitask Image Analysis in Realistic Context with Extreme Label Shift; Application to the CTAO first Large Sized Telescope

  Unsupervised domain adaptation is a widespread set of methods that leverages the knowledge of a labeled source domain to train a model to perform well on a related unlabeled target domain. They generally introduce an auxiliary adaptation-related task that can be integrated into the multitask paradig...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09630v1
• A Hybrid Neural-Microfacet BRDF Model for Real-Time Rendering

  Over the past decade, microfacet-based BRDF models have formed the foundation of real-time rendering pipelines. Despite their widespread use, they often fail to reproduce subtle appearance effects arising from complex light-surface interactions, which have led to the emergence of specialized physics...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09604v1
• ResemBrick: Brick Reconstruction from Photographs with Perceptual Fidelity and Buildability

  Producing a hand-buildable, colored brick model of a 3D object from a few casual photographs is a clean testbed for a broader challenge: generating 3D content that meets hard physical-assembly constraints under a discrete, budget-limited voxel grid. On a coarse lattice, visual resemblance and struct...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09597v1
• GenTrack3: Hybrid Stochastic-Deterministic Online Multi-Object Tracking with Cluster-Aware Association

  Multi-object tracking (MOT) involves maintaining consistent target identities as objects dynamically enter and leave a scene. Deterministic approaches, such as tracking-by-detection with data association, produce reproducible results and are computationally efficient, but they rely heavily on motion...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09581v1
• You Only Flow Once: Calibrated and Real-Time Radar Pose Estimation with Multi-Hypothesis Normalizing Flows

  Sparse and noisy millimeter-wave radar point cloud observations often correspond to multiple plausible human poses, making deterministic pose estimation fundamentally ill-posed. Yet existing radar methods remain deterministic, collapsing this ambiguity into a single estimate. Diffusion-based alterna...

  📄 ResearchAug 10, 2026http://arxiv.org/abs/2608.09579v1