# T-Mem

In long-running multi-party chats, the same issue is proposed, revised and overturned repeatedly, so semantically similar messages can describe conflicting states. T-Mem treats temporal structure as the core memory representation: retrieved messages act as temporal anchors, the discussion episodes where they cluster are reopened to recover evidence that global ranking missed, and the recovered messages are organized into a query-conditioned evidence forest with Update and Expand relations before low-information spans are compressed. On GroupMemBench and EverMemBench it reaches the highest overall accuracy under both GPT-5.5 and Deepseek-V4-Flash, beating the strongest baseline by 6.50 to 8.59 percentage points.

In long-running multi-party chats, the same issue is proposed, revised and overturned repeatedly, so semantically similar messages can describe conflicting states. T-Mem treats temporal structure as the core memory representation: retrieved messages act as temporal anchors, the discussion episodes where they cluster are reopened to recover evidence that global ranking missed, and the recovered messages are organized into a query-conditioned evidence forest with Update and Expand relations before low-information spans are compressed. On GroupMemBench and EverMemBench it reaches the highest overall accuracy under both GPT-5.5 and Deepseek-V4-Flash, beating the strongest baseline by 6.50 to 8.59 percentage points.