{"slug": "zero-mem-zero-token-memory-operations-for-llm-agents", "title": "Zero-Mem: Zero-Token Memory Operations for LLM Agents", "summary": "Researchers introduced Zero-Mem, a memory system for LLM agents that performs zero-token memory operations, eliminating LLM calls and token consumption during memory access while preserving original interaction traces. In evaluations on long-memory and long-context question-answering benchmarks, Zero-Mem achieved competitive performance and reduced memory-operation time cost by 57.6% relative to the fastest compared baseline. The system uses an entity-context graph and a temporal hierarchy to organize traces, with only the final question-answering reader invoking an LLM.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 31 Jul 2026]\n\n# Title:Zero-Mem: Zero-Token Memory Operations for LLM Agents\n\n[View PDF](/pdf/2607.29377)\n\n[HTML (experimental)](https://arxiv.org/html/2607.29377v1)\n\nAbstract:LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermediate records and mediating their retrieval adds recurring token and time costs, while omitted or merged details can obscure the original evidence. We ask whether structured memory access requires generation at all. Zero-Mem introduces \\emph{zero-token memory operations}: no step outside final question answering invokes an LLM or consumes LLM input or output tokens; encoder computation is accounted for separately. Zero-Mem preserves original interaction traces as its source of record. It organizes the traces in two complementary ways. An entity--context graph exposes connections across interactions, while a temporal hierarchy preserves conversational locality and session state. For each query, Zero-Mem weighs the two views, retrieves from both, and follows their structure to recover supporting relations or surrounding context. Deterministic calibration first discards conflicting evidence and then keeps the reader's answer grounded in the retrieved traces. Only the final-QA reader invokes an LLM. Across long-memory and long-context question-answering benchmarks, Zero-Mem achieves competitive performance while eliminating LLM calls and LLM-token consumption from memory operations. With the same final-QA reader and context budget, it reduces memory-operation time cost by 57.6\\% relative to the fastest compared baseline. Ablations support the contribution of the two views and their query-dependent coordination. Overall, the results show that structured agent memory need not generate an intermediate representation of the past. After peer review, the code and implementation details will be available at \\textcolor{blue}{[this https URL]}.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/zero-mem-zero-token-memory-operations-for-llm-agents", "canonical_source": "https://arxiv.org/abs/2607.29377", "published_at": "2026-08-05 04:36:44+00:00", "updated_at": "2026-08-05 04:52:28.137066+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["Zero-Mem"], "alternates": {"html": "https://wpnews.pro/news/zero-mem-zero-token-memory-operations-for-llm-agents", "markdown": "https://wpnews.pro/news/zero-mem-zero-token-memory-operations-for-llm-agents.md", "text": "https://wpnews.pro/news/zero-mem-zero-token-memory-operations-for-llm-agents.txt", "jsonld": "https://wpnews.pro/news/zero-mem-zero-token-memory-operations-for-llm-agents.jsonld"}}