Hugging Face Blog
MosaicLeaks: Can your research agent keep a secret?
Read the original on Hugging Face Blog →The Flow has not summarised this story yet — read it at Hugging Face Blog.
Related stories
arXiv Computation and Language
Oct 23
Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
The paper investigates how large language model agents can inadvertently leak confidential information by combining data from multiple documents—a phenomenon termed the "mosaic effect." Using 30 synthetic cybersecurity, medical, and military scenarios, the authors generate 10,800 simulated and 1,440 live answers from three LLM agents, finding that even the best model discloses forbidden composites in over 7% of simulated responses. While visible classification headers and aggregation rules reduce disclosure rates, unsafe disclosures remain in roughly one third of simulated answers, and increased refusals do not fully prevent leakage of prohibited conclusions.
OpenAI Blog
Feb 2, 2025
Introducing deep research
An agent that uses reasoning to synthesize large amounts of online information and complete multi-step research tasks for you. Available to Pro users today, Plus and Team next.
arXiv AI
Sep 2
Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents
The paper introduces Scientific Agent Skills, an open library of 163 procedural knowledge modules across 16 scientific domains such as genomics, cheminformatics, medical imaging, study design, and scientific communication. Each skill is organized as a directory containing a versioned, human‑readable instruction file, reference material, and runnable scripts, allowing a language‑model agent to load the appropriate procedure only when needed. The library is publicly licensed and hosted on GitHub, but the authors report no task‑level evaluation or host selection rate.
arXiv AI
Jul 29
Beyond Memory: A Templated Substrate for Heterogeneous Collaborative Knowledge Work with LLM Agents
arXiv:2607. 24759v1 Announce Type: new Abstract: Research projects, educational efforts, and adjacent knowledge work accumulate findings, decisions, and reasoning that future collaborators rarely recover.
Towards Data Science
Oct 10
How Can AI Agents Read Untrusted Sources Safely?
The article discusses implementing architectural guardrails to ensure AI agents safely read and utilize untrusted sources within their workflows. It outlines strategies for protecting agents from unreliable or malicious information while maintaining functional integration. The focus is on designing robust safeguards that prevent the propagation of errors or harmful content.
arXiv AI
Sep 3
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
The paper introduces Repo-To-Skill, a method for converting GitHub repositories into reusable AI skills. By distilling operational knowledge from over 1,000 machine‑learning repositories, the authors build the AREX‑Skill Library with more than 5,000 verified skills across 20 areas. Integrating these skills into a research agent—DisCo—yields significant performance boosts on multiple benchmarks, demonstrating the value of reusable, task‑agnostic knowledge.