SOURCE-LINKED INTELLIGENCE

DolphinBench: Mapping the Pareto Frontier of Agent Memory

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Agents today often take real-world actions that depend on long-term memory and context recall over time. However, most current memory benchmarks are built for a conversational question-answer format, where the question itself signals that some fact must be retrieved, and often which one. Moreover, benchmarks rarely require anything beyond accuracy from submissions, allowing memory systems to make unreasonable cost/time tradeoffs to achieve higher scores. We present DolphinBench, a benchmark that evaluates memory directly through an agent's task completion. DolphinBench includes three knowledge

Read original source ↗ Open in workspace

recordType

paper

region

Global