Agent Memory Watch Content Archive

13 posts · Page 1 of 1

1. What moved in agent memory: poisoning, live records, and longer evals2026-08-19
2. Agent memory shifts from storage to control: five developments, June 20–August 19, 20262026-08-19
3. Four new tests for agent memory: state drift, write decisions, harmful reuse, and reliability, August 20–21, 20262026-08-21
4. Agent memory becomes a control plane: five developments, August 22–28, 20262026-08-28
5. Five agent-memory papers, August 29–September 4: lifecycle, poisoning, and context contracts2026-09-04
6. Five agent-memory papers, September 5–11: write probing, poisoning bounds, eviction audits, and cleared contexts2026-09-11
7. Five agent-memory papers, September 12–18: poisoned writes, stale majorities, replay audits, and evidence sets2026-09-18
8. Five agent-memory papers, September 19–25: what memory costs, when it pays, and how far its evidence reaches2026-09-25
9. Five agent-memory papers, September 26–October 2: the record stays whole and the decision moves to read time2026-10-02
10. Five agent-memory papers, October 3–9: a plan written as fact, a superseded value, another user's memory in the index — and the check each pipeline skips2026-10-09
11. Five agent-memory papers, October 10–16: the record's life after the write — consolidation order, repeated exposure, deletion requests, and a store score sixteen points from the answer2026-10-16
12. Five agent-memory papers, October 17–23: the raw record won — a naive retriever first in six of seven settings, and a build that needs 372 questions to pay back2026-10-23
13. Five agent-memory papers, October 24–30: every operation promises more than it delivers — a preference stored on the wrong user, and an evidence budget that lowers accuracy as it grows2026-10-30

Explore more channels on Discover