Here's your daily roundup of the most relevant AI and ML news for June 20, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. LLM agent safety, multi-turn red-teaming, jailbreak benchmarks, adversarial robustness, safety-critical systems
arXiv:2606.20408v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized. We present NRT-Bench, a benchmark...
Source: arXiv - AI | 10 hours ago
2. "Important You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems
arXiv:2606.03090v2 Announce Type: replace-cross Abstract: The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the strong instruction-following capabilities and broad prior knowledge of LLMs, educ...
Source: arXiv - AI | 10 hours ago
3. Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies
arXiv:2505.22829v2 Announce Type: replace-cross Abstract: This paper bridges distribution shift and AI safety through a comprehensive analysis of their conceptual and methodological synergies. While prior discussions often focus on narrow cases or informal analogies, we establish two types conne...
Source: arXiv - AI | 10 hours ago
4. The Autonomy Tax: Defense Training Breaks LLM Agents
arXiv:2603.19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against pr...
Source: arXiv - AI | 10 hours ago
5. FFinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming
arXiv:2606.19887v1 Announce Type: cross Abstract: Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks. Financial LLMs face regulatory compliance violations, fraud facilitation, and systemic trust erosion that require targeted evaluation. We introduce F...
Source: arXiv - AI | 10 hours ago
6. A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition
arXiv:2606.19747v1 Announce Type: new Abstract: Quran Automatic Speech Recognition (ASR) aims to convert Quranic recitation into text, enabling applications such as aided memorisation tools and Quranic search engines. However, existing ASR models often exhibit high Word Error Rates (WER) on user...
Source: arXiv - AI | 10 hours ago
7. FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines
arXiv:2606.19605v1 Announce Type: cross Abstract: Multi-step LLM pipelines fail through interactions among retrieval, reasoning, and formatting steps, so prompt-only optimization can miss bottlenecks in the chain. We present FAPO (Fully Autonomous Prompt Optimization), a framework that lets Clau...
Source: arXiv - AI | 10 hours ago
8. SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures
arXiv:2602.07628v2 Announce Type: replace Abstract: While the shift toward unified foundation models has revolutionized many deep learning domains, sleep medicine remains largely restricted to task-specific models that focus on localized micro-structure features. These approaches often neglect t...
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.