Agents
AgentFlow: when the agent's workflow learns
For two years, the field has gotten very good at training models, and it still hand-wires the agents around them. Whether an agent plans, searches, calls a tool, or checks its own work before answerin
For two years, the field has gotten very good at training models, and it still hand-wires the agents around them. Whether an agent plans, searches, calls a tool, or checks its own work before answering is decided by a developer in prompts and orchestration logic. That hand-built workflow never learns, and as tasks get longer and tools multiply, it's where agents start to break.
Related
- Deep Agents now supports dynamic subagents. Instead of invoking subagents with tool calls, the main agent writes orchestration code to coord…
- Hermes Agent now has multi-agent via the Kanban, new in v0.12.0. Agents claim tasks from a board, work in parallel, and hand off when blocke…
- Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual Streams
- How cheap models changed multi-agent economics
Source: Lambda Labs | 2026-08-25