ENTITY
AgentCIBench
AgentCIBench
PulseAugur coverage of AgentCIBench — every cluster mentioning AgentCIBench across labs, papers, and developer communities, ranked by signal.
Total · 30d
2
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
2
2 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D
1 day(s) with sentiment data
RECENT · PAGE 1/1 · 2 TOTAL
-
New benchmark reveals high privacy risks in AI computer-use agents
A new benchmark called AgentCIBench has been developed to evaluate the contextual integrity of computer-use agents (CUAs). These agents, which operate across personal applications like email and calendars, pose a privac…
-
New research tackles safety and efficiency in computer-use agents · 6 sources tracked
Recent research is exploring the safety and efficiency of computer-use agents (CUAs). One paper introduces MisActBench and a guardrail called DeAction to detect and correct misaligned actions, significantly reducing att…