frontier models
One Stale Memory Invalidated the Ones Beneath It
PACMI used provenance edges and a four-state validity lattice to propagate new evidence through long-term agent memory.
Summary
PACMI used provenance edges and a four-state validity lattice to propagate new evidence through long-term agent memory.
Agent memories can stay semantically relevant after becoming wrong, and later notes may silently depend on them. PACMI represents memories and new evidence in a typed provenance graph, assigns each record to a four-state validity lattice and propagates changes to dependent records for retrieval and stale-premise checking. On a diagnostic benchmark of 100 cases and 300 queries, it achieved the highest final-answer accuracy among the tested methods. Removing cascading propagation raised final-answer errors from three to eleven, although that paired difference did not meet the paper's significance threshold. The system preserves old records as history while making their current validity explicit.
Why it matters
PACMI used provenance edges and a four-state validity lattice to propagate new evidence through long-term agent memory.
Limits and context
- Removing cascading propagation raised final-answer errors from three to eleven, although that paired difference did not meet the paper's significance threshold.
Key claims
PACMI used provenance edges and a four-state validity lattice to propagate new evidence through long-term agent memory.
Qualification: Removing cascading propagation raised final-answer errors from three to eleven, although that paired difference did not meet the paper's significance threshold.
Evidence: source-2026-10-06-009
Sources
- arXiv preprint 2610.05732arXiv · primary research
Corrections
No corrections have been recorded for this story.