arXiv:2608.27101v1 Announce Type: new Abstract: Ontology learning from text remains challenging despite significant progress in Large Language Models…
ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions
arXiv:2608.26991v1 Announce Type: new Abstract: Powerful code agents can execute scripts, call tools, and manage files, yet many important applications…
DSA: Evidence-Aware LLM-Agent Orchestration for Multi-Market Stock Research
arXiv:2608.26990v1 Announce Type: new Abstract: Large language models can summarize financial information, but an operational stock-research system must…
A Multi-Modal AI Framework for Real-Time Queue Prediction, Management and Optimisation in Intelligent Border Control Systems
arXiv:2608.27010v1 Announce Type: new Abstract: In the present work an efficient border control management procedure is proposed. Compared to operational…
Omni-Interactive Universal Embedder
arXiv:2608.27044v1 Announce Type: new Abstract: Multimodal representation learning has been shifting from traditional two-tower architectures to large…
GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory
arXiv:2608.26983v1 Announce Type: new Abstract: Organizing long-term memory for multimodal agents remains challenging because existing methods either…
AI News Brief Hourly Summary 2026-08-28 13h : 12 posts
12 posts published in the last hour 10:33AI agents in Algorithmic Electricity Markets: On the Emergence of Tacit Collusion 10:33From Atomic to Agentic: Towards Interpretable Evaluation of LLMs’ Agentic Mathematical Capabilities 10:33Counterfactual Bias Testing for Application Tracking System 10:32A Table…
AI agents in Algorithmic Electricity Markets: On the Emergence of Tacit Collusion
arXiv:2608.26896v1 Announce Type: new Abstract: As electricity market participants increasingly adopt learning-based agents for their bidding strategies,…
From Atomic to Agentic: Towards Interpretable Evaluation of LLMs’ Agentic Mathematical Capabilities
arXiv:2608.26950v1 Announce Type: new Abstract: Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating…
Counterfactual Bias Testing for Application Tracking System
arXiv:2608.26899v1 Announce Type: new Abstract: Automated candidate-job matching systems are increasingly classified as high-risk AI under emerging…
A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answering
arXiv:2608.26949v1 Announce Type: new Abstract: Answering questions over real-world documents requires processing long inputs that interleave text with…
Learning-Augmented Online Allocation under Unreliable Advice: Robustness, Exposure Fairness, and Distribution Shift
arXiv:2608.26889v1 Announce Type: new Abstract: Learning-augmented algorithms improve online decisions using predictions, but unreliable advice may harm…
BekchiAI: Measuring, Observing, and Controlling LLM Agents in One Click
arXiv:2608.26867v1 Announce Type: new Abstract: Large language model agents reason, call tools, and act autonomously over many steps, but their agentic…
C-Unseen: Weak Signal Detection in Dynamic Temporal Knowledge Graphs via LLM Reasoning
arXiv:2608.26870v1 Announce Type: new Abstract: Weak signals are early, low-visibility indicators that precede significant changes before those changes…
SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers
arXiv:2608.26836v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable proficiency in natural language understanding,…
LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems
arXiv:2608.26849v1 Announce Type: new Abstract: User behavior simulation with large language models~(LLMs) is increasingly used to support multi-agent…
Amazon just tripled its order of Nvidia chips over ‘surging demand’
Amazon is adding another 2 million Nvidia GPU chips to its data centers over the next two years. But this extended partnerships stretches beyond buying…
Evaluating human and LLM screening workflows in a conceptually complex scoping review: Recall–workload trade-offs and run-to-run consistency
arXiv:2608.26885v1 Announce Type: new Abstract: Background. Large language models (LLMs) are increasingly used for screening in evidence synthesis, where…