Memory Harnesses for Long-Running Research Agents — Stefania Druga, Sakana.ai
Source
AI Engineer
Author
AI Engineer
Published
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
It gives a defensible answer to when an AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → memory system earns its cost and which recall policy to reach for first.
videoDesigning Agents (The Floor Is the Frontier) — Ben Hylak, Raindrop
videoImproving Agents is a Data Mining Problem — Vivek Trivedy, LangChain
videoLessons from Studying Every Memory System — Shlok Khemani, Independent
videoBeyond Static Intelligence: Evaluating Continual Learning — Parth Asawa, UC Berkeley
