MemoryAgentBench
An evaluation benchmark for memory-oriented agents, used to measure the capabilities of memory systems in retrieval, temporal reasoning and abstention.
Timeline (last 90 days)
On LongBench v1/v2 and MemoryAgentBench, NoteBank also reported improvements, covering everything from three 1.3B research models up to Mamba-2-8B and a trained Qwen3.5-9B.
LoCoMo, LongMemEval, and MemoryAgentBench provide measurable R@k, temporal reasoning, and abstention metrics; OWASP Agentic ASI06 specifically targets memory and context poisoning.
All Facts (2)
On LongBench v1/v2 and MemoryAgentBench, NoteBank also reported improvements, covering everything from three 1.3B research models up to Mamba-2-8B and a trained Qwen3.5-9B.
50%UnverifiedLoCoMo, LongMemEval, and MemoryAgentBench provide measurable R@k, temporal reasoning, and abstention metrics; OWASP Agentic ASI06 specifically targets memory and context poisoning.
50%