3 papers
cs.CR2026
Deep-Research Agents Can Be Poisoned via User-Generated Content
Tingwei Zhang, Harold Triedman, Vitaly Shmatikov
Deep-research agents, i.e., systems that rely on multi-agent pipelines to iteratively retrieve, synthesize, and cite Web content in order to produce structured reports, are rapidly…
cs.CL2026
Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents
Rishi Jha, Harold Triedman, Arkaprabha Bhattacharya +1
Agents operating with computer and Web use inevitably encounter errors: inaccessible webpages, missing files, local and remote misconfigurations, etc. These errors do not thwart ag…
cs.CR2025
Publishing Wikipedia usage data with strong privacy guarantees
Temilola Adeleye, Skye Berghel, Damien Desfontaines +9
For almost 20 years, the Wikimedia Foundation has been publishing statistics about how many people visited each Wikipedia page on each day. This data helps Wikipedia editors determ…