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.
By Daniel Ruiz, Luca Luceri, Emilio Ferrara
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.
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.
By Timothy Kassis, Vinayak Agarwal, Yuhuan He, Darshil Patel, Aubrey M. Brueckner
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.
By Priscila Saboia Moreira, Christopher R. Sweet
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.
By Thuwarakesh Murallie
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.
By Jianlyu Chen, Yuyang Hu, Hongjin Qian, Jiawei Liu, Wenqing Wei, Xiaolong Chen, Defu Lian, Zhicheng Dou, Chaozhuo Li, Qiwei Ye, Zheng Liu
arXiv:2609.39050v1 Announce Type: cross
Abstract: As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has e...
By Deema Alnuhait, Gengyu Wang, Muhammad Khalifa, Hao Peng
OpenAI, PerturbAI, and Scripps Research employed distributed AI agents to analyze data from millions of brain cells, uncovering promising research leads. The collaboration leveraged thousands of AI agents to sift through vast biological datasets, identifying new insights that could advance neuroscience research.
Open source communities have been flooded with AI-generated contributions. In defense, they have written contribution rules to regulate coding agents' behavior, spanning from a total ban, mandatory disclosure, to verification gates and human sign-offs.
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills introduces DisCo, a research agent that extracts and verifies operational knowledge from GitHub repositories to create reusable AI skills. The agent produces both task‑agnostic skills—compiled into the AREX‑Skill Library of over 5,000 verified skills from 1,000 repositories—and task‑oriented skills tailored to specific research tasks. When equipped with these skills, the agent achieves significant performance gains across multiple benchmarks, outperforming a skill‑free version by 134.3% on MLE‑bench, 34.4% on PaperBench, 9.2% on FrontierCS, and 14.0% on PassNet.
The paper reports on closed‑loop autonomous synchrotron X‑ray experiments performed on nanoparticle superlattices using a coding‑agent infrastructure. It presents detailed human‑agent and agent‑agent transcripts that allow an audit of decision provenance and the division of cognitive labor. Across three experiments, the study quantifies the proportion of messages involving interpretation, judgment, methodological input, and error corrections, showing how contributions shift as the experiments progress.
By Gunik Luthra, Ronald J. Pandolfi, Benjamin T. Diroll, Ricky Ronquillo, Ruipeng Li, Christopher B. Murray, Marcus M. Noack, Kevin G. Yager, Esther H. R. Tsai
arXiv:2607. 26819v1 Announce Type: cross Abstract: Open source communities have been flooded with AI-generated contributions.
By Wenhao Yang, Runzhi He, Minghui Zhou