AI agent systems
PulseAugur coverage of AI agent systems — every cluster mentioning AI agent systems across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New ChainWatch framework detects multi-step attacks on AI agents
A new framework called ChainWatch has been developed to detect multi-step attacks targeting AI agent systems that use the Model Context Protocol (MCP). ChainWatch employs a six-stage kill chain model and a Hidden Markov…
-
AI agents could benefit from human-like memory, Gemini Pro update anticipated
A user on Mastodon suggests that human-like memory structures could be a significant advancement for AI agent systems, particularly for maintaining long-term context and state. Another user expresses anticipation for th…
-
New survey frames code as core infrastructure for AI agents
A new survey paper introduces the concept of "code as agent harness," proposing that code should be viewed as the fundamental infrastructure for AI agent systems. This perspective organizes research into three layers: t…
-
OpenAI partners with Apple, Google DeepMind researches agent scaling
OpenAI has announced a partnership with Apple to integrate ChatGPT into iOS, iPadOS, and macOS, enhancing Siri and system-wide writing tools with GPT-4o capabilities. Google DeepMind has published research on scaling AI…