An empirical comparison of thirteen control-plane placements in agent memory pipelines identifies three regimes with complementary forgetting recovery on a new 385-case adversarial benchmark, with mutation-time placement achieving 91.7-93.2% overall.
Forgetful but Faithful: A Cognitive Memory Architecture and Benchmark for Privacy-Aware Generative Agents,
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
vstash shows that hybrid retrieval disagreements provide a free training signal to fine-tune 33M-parameter embeddings, yielding NDCG@10 gains up to 19.5% on NFCorpus and matching some larger models on three of five BEIR datasets.
MemLeak benchmark shows retained images enable 12% recovery of deleted facts in multimodal agents (reduced to 2% with content-aware deletion), with 47% of image leaks not text-recoverable.
Soft-deleted HNSW embeddings are reconstructible from raw storage via Vec2Text inversion (up to 100% on structured data), addressed by epoch key rotation that reduces PII recovery to 0%.
A net-value-per-byte curator governs memory lifecycle in on-device LLM agents, cutting memory 2.7x and uplink 2.4x while driving injection success to zero on task-drift benchmarks and Jetson hardware.
citing papers explorer
-
Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations
An empirical comparison of thirteen control-plane placements in agent memory pipelines identifies three regimes with complementary forgetting recovery on a new 385-case adversarial benchmark, with mutation-time placement achieving 91.7-93.2% overall.
-
vstash: Local-First Hybrid Retrieval with Adaptive Fusion for LLM Agents
vstash shows that hybrid retrieval disagreements provide a free training signal to fine-tune 33M-parameter embeddings, yielding NDCG@10 gains up to 19.5% on NFCorpus and matching some larger models on three of five BEIR datasets.
-
MemLeak: Diagnosing Information Leaks in Multimodal Agent Memory
MemLeak benchmark shows retained images enable 12% recovery of deleted facts in multimodal agents (reduced to 2% with content-aware deletion), with 47% of image leaks not text-recoverable.
-
Ghost Vectors: Soft-Deleted Embeddings Remain Reconstructible in HNSW Vector Databases
Soft-deleted HNSW embeddings are reconstructible from raw storage via Vec2Text inversion (up to 100% on structured data), addressed by epoch key rotation that reduces PII recovery to 0%.
-
Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory
A net-value-per-byte curator governs memory lifecycle in on-device LLM agents, cutting memory 2.7x and uplink 2.4x while driving injection success to zero on task-drift benchmarks and Jetson hardware.