← Back to all news
arXiv Computation and Language By Ming Wu, Pengyuan Zhu

Agent Zero Memory: Provenance-Aware Long-Term Memory for LLM Agents

Read the original on arXiv Computation and Language →

Agent Zero Memory is a provenance‑aware long‑term memory system for large language model agents that distills user interactions into three parallel memory structures: an episodic timeline, an associative entity‑event knowledge graph, and a semantic, citation‑locked hierarchical documentary memory. Retrieval is performed via an intent gate, source router, and concurrent searches across the three systems, producing integrated, cited answers that exclude fabrication and require evidence the reader has opened. The system achieves state‑of‑the‑art performance on LongMemEval (95.60%) and LoCoMo (93.60%) while offering a favorable accuracy‑cost‑latency trade‑off across multiple backbone LLMs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Jul 21

Accurate and Efficient Long-Term Memory for LLM Agents

arXiv:2607. 16211v1 Announce Type: new Abstract: LLM agents augmented with persistent memory can recall past interactions, but existing systems suffer from two limitations: flat, unstructured storage loses relational context needed for multi-hop and temporal reasoning, and reliance on expensive LLM-based classification makes them impractical for latency-sensitive deployment.

By Zicheng Zhao, Xinyang Guo, Luyao Lv, Menghan Wang, Ming Li, Shuaicheng Li
llmsagents
More like this →
arXiv Computation and Language
4d ago

Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge

The paper introduces ElephantBench, a closed‑book knowledge probe with 1,094 multi‑account factual questions generated via an auditable graph‑based pipeline that pulls documents from a low‑exposure web corpus and identifies naturally occurring disagreements. Across 32 large language models, even the best model only recovers both divergent accounts on 52.4% of questions, and most models recall one account while omitting the other, indicating persistent epistemic myopia. The study shows that scaling model size and inference‑time reasoning improves recall but does not eliminate incompleteness, and that exposure imbalance in the corpus biases models toward the dominant account.

By Zhuoshi Pan, Junru Lu, Yan Qian, H. Vicky Zhao, Di Yin, Xing Sun
llmsnlpbenchmarks
More like this →