5 min read
Research COLM 2026 paper InjecMEM shows a single interaction, with no access to the memory store, can plant an optimized record that is later retrieved and steers a research agent's answers. Retrieve-time filters barely helped.
COLM 2026 paper InjecMEM shows a single interaction, with no access to the memory store, can plant an optimized record that is later retrieved and steers a research agent's answers. Retrieve-time filters barely helped.
A cluster of May 2026 research papers formalizes a new attack class against LLM agents: adversarial content planted in one session persists in agent memory or skills and fires in a later, unrelated interaction. Existing same-session defenses don't catch it.