The authors model an agent session as an evolving context graph.
Persistent context graphs cut agent memory costs without extra model calls
ReCAP preserves attention-derived links between past messages, then uses each new request to retrieve a compact, task-relevant history.
Big Tech
Jingbo Yang · Kwei-Herng Lai · Xiaowen Wang · Zhaoxuan Tan · Pei Zhou · Mengting Wan · +3 more
University of California, Santa Barbara · Microsoft · University of Notre Dame
Research Digest··3 min read
Yang et al.
Why this paper
From Microsoft and 2 others · Released code
In one line
Storing attention-derived importance and dependency links in a lightweight persistent context graph reduces memory compaction latency by approximately 95%.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (2 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§