Here's your daily roundup of the most relevant AI and ML news for August 11, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4
arXiv:2607.15509v2 Announce Type: replace-cross Abstract: We present a fully automated closed-loop AutoML framework that uses GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture designers for cross-lingual handwritten optical character recognition. Each large language model inde...
Source: arXiv - Machine Learning | 10 hours ago
2. NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
arXiv:2509.03985v2 Announce Type: replace-cross Abstract: In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety mechani...
Source: arXiv - AI | 10 hours ago
3. MOSAIC: Adversarial Co-evolution of Specialist Heuristics and Problem Instances for LLM-based Automated Heuristic Design
arXiv:2608.07544v1 Announce Type: cross Abstract: Automated heuristic design (AHD) with large language models (LLMs) has produced strong heuristics for combinatorial optimization problems (COPs). Yet existing frameworks optimize for average performance on a small fixed dataset and steer the sear...
Source: arXiv - AI | 10 hours ago
4. BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes
arXiv:2608.08027v1 Announce Type: cross Abstract: Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or external data. Existing detection methods only detect the presence of ...
Source: arXiv - Machine Learning | 10 hours ago
5. Entropy-based Code Adversarial Translation for Real-world Repository Migration
arXiv:2608.09273v1 Announce Type: new Abstract: LLMs have demonstrated strong capabilities in code generation and automated program repair, but migrating an entire repository rarely produces a runnable application because long-horizon translation challenges LLM-based agents' ability to maintain ...
Source: arXiv - AI | 10 hours ago
6. ACEvo: Adversarial Co-Evolution of Problem Distributions and Solvers for Combinatorial Optimization
arXiv:2506.02594v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to synthesize heuristic programs, yet most existing pipelines optimize solvers against fixed benchmark distributions. This static setup can obscure solver weaknesses and limit understanding of ...
Source: arXiv - AI | 10 hours ago
7. Studying People to Study AI: Expert Perspectives on the Epistemic Fit and Barriers of Human Research in AI Safety & Ethics
arXiv:2608.05656v2 Announce Type: replace-cross Abstract: Safety risks of AI are becoming increasingly evident in human interactions with AI technologies. The prominent approaches to evaluating these risks favor technical methods, such as model benchmarks and LLM simulations, often sidelining em...
Source: arXiv - AI | 10 hours ago
8. Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control
arXiv:2605.18414v2 Announce Type: replace-cross Abstract: Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent's context, models select them in adversarial s...
Source: arXiv - AI | 10 hours ago
About This Digest
This digest is automatically curated from leading AI and tech news sources, filtered for relevance to AI security and the ML ecosystem. Stories are scored and ranked based on their relevance to model security, supply chain safety, and the broader AI landscape.
Want to see how your favorite models score on security? Check our model dashboard for trust scores on the top 500 HuggingFace models.