Spaces:
Running
Running
Commit History
-
Rebuild NWKaQIKoGp (PlugMem): GENUINE reproduction on the real LongMemEval benchmark (xiaowu0162/longmemeval, N=60) with Qwen2.5-7B via free HF router. PlugMem beats raw-history baseline at equal budget (26.7% vs 21.7%) at fewer tokens (310 vs 357); 852 semantic + 118 procedural units; task-agnostic across 6 question types. $0, deterministic (cached).
Verified signaturebf5cbdc
-
Claim 1: real-LLM extraction of propositional+prescriptive memory (official extractor)
Verified signature41a9a17
-
Update logbook: Reproducing PlugMem (ICML 2026)
Verified signaturefef7ca6 -
initial commit
Verified signatured257c6f