Memory Harnesses for Long-Running Research Agents — Stefania Druga, Sakana.ai

Stefania Druga from Sakana.ai tested how AI agents can remember information during extended tasks.

She built a memory system that functions as a write-manage-read loop around the model, rather than a simple database. The key finding was negative: when all information fit within the model's context window, memory made no difference—only increased cost. However, when the answer lay far ahead—at step 124 while the question appeared at step 500—memory became critical. Her best approach was a ranked list of previous decisions, which outperformed both random search and an "oracle" with perfect memory. She ran the experiments on a local computer in Tokyo with fans around it.

More to read

Lumaril, which develops AI software for optimizing industrial production by connecting to existing control systems, raised a $66M Series A at a $400M valuation

Techmeme · 3 h ago

DeepSeek open sources Super-Agent as a research prototype, a proactive coding agent it says can monitor group chats for coding issues and suggest solutions

Techmeme · 3 h ago

Insurance software maker Guidewire agrees to acquire Hyperexponential, which makes AI-powered insurance underwriting and pricing software, for $1.7B in cash

Techmeme · 3 h ago

One word for AI agents in 2027

Nate Herk · 7 h ago