Figure 2: Pipeline of Sprout. Three questions about one video are answered in order, building one
memory. Each row shows the rounds of one question: tool calls (circles) and their results (boxes).
Video frames stay in the context for one round only; text results are kept. Q1 watches the first two
chunks, remembers them as coarse nodes, and revisits n at a higher frame rate to add finer child
2
nodes. Q2 reuses the memory: search returns a node and Q1’s answer, and a short revisit adds one
more detail, without watching new video. Q3 finds that the memory does not cover what it asks, so
it watches two more chunks. The last two chunks are never watched. The memory tree (bottom) is
drawn on the same time axis as the video; node colors show which question added each node.