A Field Guide to Agent Shapes: From Long-Horizon to Open-Ended

Agents in 2026 split into a bunch of distinct shapes like externalized context with RLMs, agents messaging each other, harnesses the agent rewrites itself, sandboxes, orchestrators with sub-agents, and brute-force recombination.

This talk goes through what each one helps with, then looks at three real deployments in industries/domains generally lagging in AI adoption that reused some of these patterns.

We finish on where this is heading in 2027 with models that edit their own context, tweak other networks, get trained for exploration earlier, and learn continuously from tasks they generate themselves.