Artificial Intelligence · 13.08.2026, 05:25 UTC
MMLA: How Memory Lets the Past Shape the Future
| Schweregrad | info |
|---|---|
| Kategorie | Artificial Intelligence |
| Quelle | arXiv cs.CL ↗ |
| Veröffentlicht | 13.08.2026 UTC |
Sicherheitsmeldung mit Schweregrad noch nicht bewertet. Technische Details im Tab „Originaltext“; empfohlene Schritte in der Checkliste.
arXiv:2606.28876v3 Announce Type: replace Abstract: Proposal. Long context can replay history, but it does not decide which completed observations deserve authority. MMLA formalizes a bounded resident memory between transient context and slow weight updates. A completed local segment is eventized; for each event, a target-conditioned constructor proposes semantic content and a trusted assembler produces a complete versioned row; deployment either commits that row atomically or returns NULL. Realized futures may price actions during training, while deployment remains causal and future-blind. Validated components. Controlled studies establish narrower ingredients. Lifecycle execution is exact on 300/300 held-out records for each of three seeds. Calibrated selection with full-archive fallback improves over a weak budget-matched dense baseline by 5.5--16.6 F1 and over BM25 by 4.0--6.2 F1 on held-out multi-hop QA; the original Llama budget execution is retained as failed, while the corrected Qwen packer satisfies the stated per-record caps. Typed anchor--filler transport reaches 240/240 held-out exactness per seed while three same-checkpoint controls obtain 0/240 whole-record successes. Current blocker. The integration loop is not complete. Dense-row, structured-span, and checkpoint-native readers trained from V28, the frozen 352.3M-parameter model-only checkpoint produced by a 50.0M-token native-scaffold pilot, all fail semantic qualification across three seeds. Candidate exactness is 0--45/23,040, query exactness is 10--1,536/9,216, and record-macro Brier remains near the …