arXiv AI
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 1
UTILMEM: Benchmarking Evidence Utilization in Long-Term Conversational Memory
UTILMEM is a new diagnostic benchmark that tests how conversational agents use long‑term memory, focusing on reasoning over dense histories, spotting implicitly relevant memories, synthesizing distributed evidence, and resisting interference from similar distractors. It contains 1,717 instances across five domains and evaluates a range of retrieval‑based and memory‑augmented systems. The study shows that strong performance on traditional factual recall does not guarantee effective memory utilization, highlighting a gap between retrieving information and integrating it into coherent, task‑oriented outputs.
arXiv AI
Jun 17
MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
arXiv:2606. 17328v1 Announce Type: new Abstract: LLM agents increasingly maintain long-term memory of user facts across sessions.
arXiv AI
Jul 15
MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
arXiv:2607. 12893v1 Announce Type: new Abstract: Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions.
arXiv Machine Learning
Sep 4
MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval
MemoryLACE (MemLACE) is a lightweight memory framework that explicitly models the lifecycle of textual evidence—capturing sparse merge, supersession, and contradiction relations—while preserving atomic natural‑language memories and their provenance. Unlike traditional systems that retrieve memories independently, MemLACE reconstructs relation‑aware evidence units that expose current, historical, supporting, and conflicting evidence for downstream reasoning. In benchmark evaluations (BEAM and StructMemEval) using both open‑weight and proprietary LLM backbones, MemLACE achieves the highest overall performance among same‑backbone comparisons and reduces BEAM runtime by 66.6% compared to the strongest reflective‑memory baseline, Hindsight.
arXiv AI
Aug 6
MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agents
arXiv:2608. 01742v2 Announce Type: replace Abstract: Long-term memory is critical for LLM agents operating over long-horizon interactions.
arXiv AI
Aug 21
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use
arXiv:2608. 20202v1 Announce Type: new Abstract: Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions.