MemoryAgentBench (MAB), benchmark for evaluating agent memory systems across four competencies: accurate retrieval, test-time learning, long-range understanding, selective forgetting
2 results
Name Categories Topics References Credibility CreateDate UpdateDate Title RelatedNotes NavigationOrder Eleventy TemplateEngineOverride Created 20260604_agent_memory_characterization_system_implications paper_analysis memory_mechanism , agent_architecture , long_term_memory , llm , evaluation stanford_university , ku_leuven , memory_agent_bench , memgpt , graphrag 95 Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads memgpt_towards_llms_as_operating_systems , memlineage_lineage_guided_llm_agent_memory , calmem_dual_memory_conversational_ai , unlocking_working_memory_latent_reasoning , aip_graph_representation_for_learning_and_governing_agent_skills [object Object] [object Object] md 20260722_supra_cognitive_modes_routed_agent_memory paper_analysis agent_architecture , memory_mechanism , long_term_memory , reasoning , multi_hop_reasoning supra_research , locomo_bench , memory_agent_bench , long_mem_eval 100 Supra Cognitive Modes: A Routed Architecture for Agent Memory memory_os_of_ai_agent , memgpt_towards_llms_as_operating_systems , shared_selective_persistent_memory_agentic_llm [object Object] [object Object] md