WFM: a Wiki Foundation Model for agent memory in markdown
Retrieval over plain markdown folders is becoming a common pattern for agent memory, and WFM shows link structure itself can carry signal rather than only page text. The 10.5x faster training protocol matters for teams fine-tuning their own retrieval models on private wiki data. Practitioners building agents on file-based memory, RAG pipelines or multi-hop reasoning tasks can test the approach via the paper and the accompanying Chat with Paper tool.
A new paper introduces WFM, a Wiki Foundation Model designed to work with LLM Wikis — agent memory stored as linked markdown pages.
WFM converts the wiki into a graph and retrieves information via message passing conditioned on the query, using page text and link structure together.
The team also built a GPU-to-GPU training protocol that trains 10.5x faster.
The paper reports strong results on five agent memory and multi-hop reasoning benchmarks.It targets agents whose long-term memory is a folder of linked markdown files.
Interesting paper on agent memory stored as a linked markdown wiki. Lots of great ideas and insights if you work with LLM Wikis. Wikis are useful for agents because each page holds dense text and the links between pages hold structure. WFM is a Wiki Foundation Model trained to use both at once. It turns an LLM Wiki into a graph and retrieves from it with message passing conditioned on the query, so the text of each page and the link structure shape the result together. The team also built a GPU-to-GPU training protocol that trains 10.5x faster, and reports strong results on five agent memory and multi-hop reasoning benchmarks. If your agent's long-term memory is a folder of linked markdown files, WFM is designed for that format. Paper: arxiv.org/abs/2609.18182 Chat with Paper: academy.dair.ai/papers/wfm-wik…📊 7 ⚡
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include WFM, agents, RAG, LLM Wikis.
Source attribution: curated from elvis (@omarsar0).