MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

Researchers propose MemTrace, a framework that converts large language model memory pipelines into executable evolution graphs for fine-grained error tracing. They introduce MemTraceBench, a benchmark covering systems like Long-Context and RAG, and an automatic attribution method that identifies root causes of memory failures, enabling prompt optimization that boosts performance by up to 7.62%.

arXiv:2605.28732v3 Announce Type: replace-cross Abstract: Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dynamic evolution is crucial to understand how information is synthesized, propagated, or corrupted over time. In this work, we study the new problem of error tracing and attribution in LLM memory systems. We propose a novel framework that transforms memory pipelines into executable memory evolution graphs, enabling fine-grained tracing of operational information flow. We then construct MemTraceBench, a benchmark collected from representative memory systems such as Long-Context, RAG, Mem0, and EverMemOS, to systematically study memory failure modes. We further introduce an automatic attribution method that iteratively traces operation subgraphs to pinpoint the root cause of any failed case. Our analysis reveals that memory failures are systematic, stemming from operation-level issues like information loss and retrieval misalignment. Crucially, we leverage these fine-grained attribution signals to guide downstream prompt optimization, establishing a closed-loop system that automatically corrects faults and boosts end-task performance by up to 7.62%. Code will be released at https://github.com/zjunlp/MemTrace.