Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards
arXiv:2608.07535v1 Announce Type: new
Abstract: Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning. However, this architectural shift reshapes the safety landscape of machine learning. Inc...
Data-Driven Fire-Zone Segmentation for Improved Short-Term Wildfire Prediction
arXiv:2608.07472v1 Announce Type: new
Abstract: Wildfire prediction models typically discretize study areas into uniform grids, ignoring the heterogeneous spatial distribution of ignitions. We challenge this paradigm by showing that how data is discretized matters more than which model is used. We ...
Application of Artificial Intelligence for Fraudulent Banking Operations Recognition
arXiv:2608.07471v1 Announce Type: new
Abstract: This study considers the task of applying artificial intelligence to recognize bank fraud. In recent years, due to the COVID19 pandemic, bank fraud has become even more common due to the massive transition of many operations to online platforms and th...
6 mistakes AI leaders keep making with agentic deployments
Agentic AI moved from slide deck to production system faster than most governance committees could schedule a meeting about it. That speed feels thrilling right up until an agent with real credentials makes a judgment call at 2am, and the room realizes the guardrails were still a work in progress…
Every agent evaluation tells you the model picked the wrong tool. Almost none tell you why. A new paper solves that by planting diagnostic "canary" tools inside an agent's toolkit, each one built to expose a specific blind spot, then watching what the agent grabs. The results are brutal...
ADIAS: Automated Design of Interactive Agentic Systems
arXiv:2608.06410v1 Announce Type: new
Abstract: Automated agent design improves agent harnesses through iterative revision, evaluation, and feedback summarization. Existing methods are largely candidate-centric: cross-round experience is organized around candidate agents, which leaves the repair pr...
Interpretable Unsupervised Community Detection with LLM-Symbolized Structured Processes
arXiv:2608.06402v1 Announce Type: new
Abstract: Community detection is a fundamental task in graph analytics that aims to identify cohesive groups of entities with similar behaviors or interests. Classic objective-driven methods struggle with complex graph structures, while deep-learning approaches...
Beyond Routing Weights: Faithful Response-Level Interpretation of Mixture-of-Experts Reward Models via Contribution Contrast
arXiv:2608.06400v1 Announce Type: new
Abstract: Reward models are central to learning from human preferences, yet identifying what drives their predictions remains challenging. Recent sparse Mixture-of-Experts (MoE) reward models seek to improve interpretability by routing prompts to specialized ex...
EntropyMoE: Entropy-Aware Sparse Expert Routing for Tokenizer-Free LLMs
arXiv:2608.06398v1 Announce Type: new
Abstract: Recent byte-level large language models (LLMs) have made tokenizer-free modeling increasingly competitive by grouping bytes into dynamically sized patches. However, existing byte-patch architectures still apply the same dense feed-forward computation ...
Towards Multi-Label Graph Foundation Models: from Single-Vector Representation Learning to Multi-Semantic Basis Learning
arXiv:2608.06394v1 Announce Type: new
Abstract: Multi-label node classification is an important yet challenging task in graph learning, where nodes exhibit multiple semantics simultaneously. Existing methods for multi-label node classification can effectively model multiple labels, while only consi...
Fixed and Adaptive Topological DeepONets: Functional Measurements on Hausdorff Locally Convex Spaces
arXiv:2608.06428v1 Announce Type: new
Abstract: Deep Operator Networks (DeepONets; arXiv:1910.03193) typically encode an input function through point values on a fixed discretization. Building on the Topological DeepONet framework of Ismailov (arXiv:2603.11972), we replace point samples by continuo...
arXiv:2608.06427v1 Announce Type: new
Abstract: Generative models can reproduce an observational distribution while encoding an incorrect causal structure. We study a sequential game in which a structural causal generator proposes observational and interventional distributions, while an adversarial...
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation
arXiv:2608.06422v1 Announce Type: new
Abstract: Giving an LLM judge more compute does not necessarily make it check more requirements. When one call must return many verdicts, some decisions become weakly grounded in the evidence, even when that call receives the same token or tool budget as a pane...
Risk-Aware Decision Policies for Agents Under Noisy Perception
arXiv:2608.06420v1 Announce Type: new
Abstract: Perception in biological systems is inherently noisy, requiring organisms to make decisions under uncertainty where misclassification can be costly or fatal. We present an Artificial Life predator-prey model of foraging under noisy perception, and com...
Latent Fact-Checking: Detecting Misinformation through Activation Engineering
arXiv:2608.06417v1 Announce Type: new
Abstract: The proliferation of misinformation online has driven demand for scalable detection systems. While most existing approaches rely on surface-level linguistic features or external knowledge retrieval, we examine truthfulness as a geometric property of a...
SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse
arXiv:2608.05204v1 Announce Type: new
Abstract: LLM-agent ecosystems are rapidly growing around reusable skills: mixed-modality packages of metadata, natural-language instructions, code, tools, references, and operational workflows. As skills become marketplace artifacts, auditing their reuse is no...
Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models
arXiv:2608.05168v1 Announce Type: new
Abstract: Large language models often fail on reasoning tasks despite possessing the capability to solve them. We argue that many such failures arise from localized reasoning bugs in intermediate steps rather than from global incompetence. We show that these bu...
The Ignition Index: Measuring Global Workspace Dynamics in Language Models
arXiv:2608.05160v1 Announce Type: new
Abstract: We introduce the Ignition Index (I), a validated scalar metric that operationalizes Global Workspace Theory's (GWT) all-or-none ignition prediction in transformer language models. The metric fits a four-parameter sigmoid to per-layer linear probe accu...
Agentic Nesting: A New Methodology for Existing Enterprise Application Integration and Services
arXiv:2608.05159v1 Announce Type: new
Abstract: Enterprise operations extensively rely on multiple heterogeneous business systems and information applications, which also result in severe data silos and process fragmentation. Enterprises have invested considerable financial and material resources i...
arXiv:2608.05242v1 Announce Type: new
Abstract: In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning, rather than jointly acquiring implicit 3D perception and reasoning through large-scale training. Our key observation is th...
Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language
arXiv:2608.05238v1 Announce Type: new
Abstract: Training multimodal models to align time series with language runs into a self-supervision trap. The usual recipe asks an LLM to read a series and write a description, so label quality is capped by the perceptual skill the model is supposed to learn. ...
arXiv:2608.05234v1 Announce Type: new
Abstract: Building reliable applications that leverage large language models (LLMs) remains a significant challenge. While LLMs offer impressive capabilities across diverse tasks, their outputs often lack accuracy and provide no clear measure of confidence. Thi...
When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters
arXiv:2608.05207v1 Announce Type: new
Abstract: Frozen pretrained forecasters often fail in structured, recurring ways that are costly to repair through fine-tuning. We study corrective feature discovery: mining interpretable features of a frozen forecaster's residual to drive a lightweight post-ho...
MS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classification
arXiv:2608.05196v1 Announce Type: new
Abstract: Multiple sclerosis (MS) is diagnosed through clinical assessment, magnetic resonance imaging, laboratory evidence when appropriate, and exclusion of better explanations. Blood RNA expression data may contain disease associated immune signal, but a blo...