Megadose AI progress, ranked and analyzed.

Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization

· HF Daily Papers ·
The paper argues that streaming summaries fail when memory misses the old evidence assumed by the current dialogue window.

Min and Song define the task as summarizing a live window with selective memory from an unbounded prior conversation. Their benchmark separates two checks: whether memory retrieves the missing evidence, and whether the summary uses it. ReMEMBER retrieves against unresolved dependencies, then compresses chunks into evidence-dense memory within a fixed budget. In tests with histories up to 160K tokens, it improves memory recall and gap-resolution completeness over baseline memory methods. HF Daily Papers' note

score 5

Categories: Research