The authors designed Stashbird to consolidate conversations into episode records, semantic relations, preference traces, entity communities, and persistent graph state.
Speaker-indexed memory cuts token costs while preserving answer accuracy
Stashbird links conversational evidence to structured memory, enabling efficient retrieval plus provenance-aware updates and deletion.
Big Tech
Chidera Biringa · Lucas Yannul · Xiaowen Wang · Marco Ayala · Nicholas Yi · Alex Moyse · +2 more
Microsoft
Research Digest··2 min read
The authors built a conversational memory system that stores episodes alongside derived relations, preferences, summaries, and graph state, with explicit links back to the source evidence.
Why this paper
From Microsoft
In one line
Stashbird reduces memory token usage by up to 76x while achieving competitive question answering accuracy across long-term conversation benchmarks.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§