DolphinBench: Mapping the Pareto Frontier of Agent Memory
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…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
