{"slug": "edgemem-llm-free-agent-memory-construction-and-retrieval-via-evidence-preserving", "title": "EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph", "summary": "EdgeMem, a new agent-memory method that preserves original interaction turns in a multi-anchor hypergraph built by lightweight local processing, achieved the highest strict-judge score among seven reproduced systems on the LoCoMo benchmark, scoring 61.01 versus 58.70 under a shared prompt, according to the arXiv paper 2609.05553v1. The method performs construction and retrieval with no generative-LLM calls, reserving LLM use for final answer generation, and also showed strong results on LongMemEval-S. EdgeMem's authors argue that preserving and organizing source evidence offers an effective and efficient foundation for agent memory without generative memory management.", "body_md": "arXiv:2609.05553v1 Announce Type: new \nAbstract: Agent memory allows LLM agents to use earlier interactions when answering new queries. Existing methods often compress interaction histories into summaries or other LLM-generated representations. Repeated generation adds cost and can discard answer-bearing details before the system knows what a future query will require. We propose EdgeMem, an agent-memory method built around a simple principle: preserve original interaction turns and organize them through complementary content, temporal, and episodic cues. EdgeMem realizes this principle with a multi-anchor hypergraph constructed by lightweight local processing. Retrieval directly returns source evidence and reserves LLM use for final answer generation, combining structured access to multi-session histories with faithful retention of the original conversation. Experiments on LoCoMo and LongMemEval-S show strong retrieval and memory-grounded question answering; on LoCoMo, EdgeMem achieves the highest strict-judge score among seven reproduced systems under a shared prompt (61.01 versus 58.70), while construction and retrieval require no generative-LLM calls. Overall, EdgeMem shows that preserving and organizing source evidence provides an effective and efficient foundation for agent memory without generative memory management.", "url": "https://wpnews.pro/news/edgemem-llm-free-agent-memory-construction-and-retrieval-via-evidence-preserving", "canonical_source": "https://www.machinebrief.com/news/edgemem-llm-free-agent-memory-construction-and-retrieval-via-1zpl", "published_at": "2026-09-10 04:00:00+00:00", "updated_at": "2026-09-10 05:52:13.987726+00:00", "lang": "en", "topics": ["ai-agents", "large-language-models", "ai-research", "artificial-intelligence"], "entities": ["EdgeMem", "LoCoMo", "LongMemEval-S", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/edgemem-llm-free-agent-memory-construction-and-retrieval-via-evidence-preserving", "markdown": "https://wpnews.pro/news/edgemem-llm-free-agent-memory-construction-and-retrieval-via-evidence-preserving.md", "text": "https://wpnews.pro/news/edgemem-llm-free-agent-memory-construction-and-retrieval-via-evidence-preserving.txt", "jsonld": "https://wpnews.pro/news/edgemem-llm-free-agent-memory-construction-and-retrieval-via-evidence-preserving.jsonld"}}