MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory
MemoryDojo is a benchmark for tracing how poisoned information propagates through LLM agent memory systems across sessions and measuring its influence on later agent behavior. It comprises 155 multi-session long-horizon trajectories spanning four domains and supports five different memory systems. The authors report that all evaluated memory systems are susceptible to memory poisoning, with substantial variation in downstream effects across architectures. They also propose a memory-aware poison optimization process that increases poisoning efficacy, highlighting differences between memory architectures.
It gives agent builders a concrete benchmark and early evidence that memory architectures differ materially in how poisoned content propagates, which matters for designing safer long-horizon agents.
Comments & Questions (0)
No comments yet
Be the first to comment!