Tag
A Google paper introduces Procedural Graphs, an editable workflow structure for LLM agents that improves performance on long tasks by evolving from execution feedback, outperforming baselines in most benchmarks.
The article discusses how AI agent performance degrades over long sessions due to context window clutter from raw history, tool outputs, and repeated reasoning, and suggests solutions like summarizing old turns and trimming tool outputs to extend useful run length.
Stagent is a tool that enables Claude Code to handle long tasks it would otherwise abandon.