{"slug": "dmf-a-deterministic-memory-framework-for-conversational-ai-agents", "title": "DMF: A Deterministic Memory Framework for Conversational AI Agents", "summary": "Researchers have developed the Deterministic Memory Framework (DMF), a CPU-first memory system for conversational AI agents that replaces generative large language model compression with a fully deterministic pipeline using classical NLP analysis and mathematical scoring. DMF assigns each interaction a Survival Score based on content signals and conversational cues, achieving comparable accuracy to existing memory layers while using zero tokens for memory preparation and 5x to 242x fewer tokens overall. The framework eliminates LLM calls from the memory-management loop, reducing token costs to nearly zero and enabling deterministic memory systems for AI agents.", "body_md": "# Computer Science > Artificial Intelligence\n\n[Submitted on 2 Jun 2026]\n\n# Title:DMF: A Deterministic Memory Framework for Conversational AI Agents\n\n[View PDF](/pdf/2606.03463)\n\n[HTML (experimental)](https://arxiv.org/html/2606.03463v1)\n\nAbstract:Conversational AI agents require memory systems that are both scalable and semantically coherent across long interaction horizons. Existing approaches rely predominantly on large language model (LLM)-based summarisation at write time, which introduces non-determinism, escalating token costs, and opacity in pruning decisions. We present the Deterministic Memory Framework (DMF), a CPU-first approach that replaces generative memory compression with a fully deterministic pipeline grounded in classical NLP analysis, vector geometry, and mathematical scoring. DMF assigns each conversational interaction a Survival Score $\\Omega$ computed from deterministic content signals, conversational cues, and structured provenance, combined through a logistic projection. An interaction-count decay law, denoted as $\\Omega_{\\mathrm{eff}}(\\Delta n)$, governs how relevance evolves as new turns arrive, where $\\Delta n$ is the number of newer interactions rather than wall-clock time, preserving full determinism. We present the mathematical formulation of DMF, its structured recall pipeline, the pruning decision procedure, and the evaluation protocol. Experiments are conducted on a purpose-built benchmark using the LoCoMo and LongMemEval datasets. We compare DMF against Mem0, a popular memory layer for AI agents. DMF achieves comparable accuracy while using zero tokens to prepare the memory context and 5x to 242x fewer tokens over the entire conversation. These results show that it is possible to eliminate LLM calls from the memory-management loop, reducing token costs to nearly zero and enabling deterministic memory systems for conversational AI agents.\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/dmf-a-deterministic-memory-framework-for-conversational-ai-agents", "canonical_source": "https://arxiv.org/abs/2606.03463", "published_at": "2026-06-03 11:07:43+00:00", "updated_at": "2026-06-03 11:48:08.355171+00:00", "lang": "en", "topics": ["artificial-intelligence", "natural-language-processing", "ai-agents", "large-language-models", "ai-research"], "entities": ["DMF", "LoCoMo", "LongMemEval"], "alternates": {"html": "https://wpnews.pro/news/dmf-a-deterministic-memory-framework-for-conversational-ai-agents", "markdown": "https://wpnews.pro/news/dmf-a-deterministic-memory-framework-for-conversational-ai-agents.md", "text": "https://wpnews.pro/news/dmf-a-deterministic-memory-framework-for-conversational-ai-agents.txt", "jsonld": "https://wpnews.pro/news/dmf-a-deterministic-memory-framework-for-conversational-ai-agents.jsonld"}}