MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems
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 systema...
| Authors | Xinle Deng, Ruobin Zhong, Hujin Peng et al. |
|---|---|
| Primary category | cs.CL |
| Published | 27 May 2026 |
| Last updated at source | 8 October 2026 |
Connected in the knowledge graph
- zjunlp/MemTraceBenchDataset · cited by
Models and datasets referencing this paper
- zjunlp/MemTraceBenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.