Understand this story
The English summary is being updated. See the reporting timeline below.
Latest development · Report
TencentDB Agent Memory Adapts to the JEV Decision Model: Letting Agents Call on Team Experience as NeededDevelopments
1 confirmed developments
- Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 14
Tencent Cloud Developer Community
TencentDB Agent Memory Adapts to the JEV Decision Model: Letting Agents Call on Team Experience as Needed
TencentDB Agent Memory introduces a pluggable decision service and adapts to the JEV decision model, delegating "whether to recall, which candidate assets to select, and whether to trigger a memory update" to an independent interface for judgment. In Skill recall tests, the input tokens repeatedly injected by the main model dropped from 24.96M to 15.04M, a reduction of nearly 40%, while the task success rate remained essentially flat; the number of long, difficult problems passed on SWE-bench Pro rose from 30% to 40%. On the memory generation side, total cost fell by 13.8%, L3 generation calls decreased by 39.7%, and JEV judgment cost accounted for only 0.72% of total cost.