Agents
CoReMem decreases the steps of a coding agent by 17%
The memory keeps only code locations and test commands, and the resolve rate goes from 21.0% to 25.7% on one model.
What matters in AI.
SubscribeNews of the day
2 stories filed under this day.
Agents
The memory keeps only code locations and test commands, and the resolve rate goes from 21.0% to 25.7% on one model.
Agents
GPT-5.6 Sol had 18.1% correct results on path tasks with no change, and 1.3% when conditions changed during the task.