arXiv:2608.27044v1 Announce Type: new Abstract: Multimodal representation learning has been shifting from traditional two-tower architectures to large…
Category: AI
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 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,…