Self-Improving Memory for Agents (6 minute read)
Summary
Perplexity Brain is a memory system that builds a persistent context graph across tasks, projects, decisions, files, and sources, enabling agents to start with relevant context instead of from scratch, improving answer correctness and reducing task costs.
Similar Articles
PREPING: Building Agent Memory without Tasks
Presents PREPING, a framework for constructing agent memory before any task-specific experience using proposer-guided synthetic practice, achieving competitive performance with reduced deployment costs.
Proactive Memory for Long-Horizon Agents (16 minute read)
This paper introduces a proactive memory agent that operates alongside a standard action agent to selectively inject memory-grounded reminders during long-horizon tasks, mitigating behavioral state decay. Experiments on Terminal-Bench and τ²-Bench show significant improvements in pass@1, and the approach is demonstrated with both weak and strong action agents.
For those creating personal assistants locally - how has short/long term memory impacted your experience?
A developer shares their experience building a local autonomous agent with long-term and short-term memory using Qwen 3.6 27B, noting that memory dramatically improves the agent's usefulness and realism. They invite others building similar agents to discuss memory techniques and potential agentic meetups.
SelfMem: Self-Optimizing Memory for AI Agents
SelfMem introduces a self-optimizing memory framework for AI agents that allows them to explore, evaluate, and refine their own memory strategies through memory tools and feedback signals, achieving significant improvements over baselines on the BEAM benchmark across large conversation scales.
@omarsar0: // AutoMem // I quite like this idea of metamemory. (bookmark it) This new research from Stanford treats agent's memory…
This Stanford research paper introduces AutoMem, a framework that treats agent memory management as a trainable skill. By optimizing memory structure and proficiency separately, AutoMem improves base agent performance 2x-4x on long-horizon tasks, enabling a 32B open-weight model to compete with frontier systems like Claude Opus 4.5 and Gemini 3.1 Pro Thinking.