This approach seems interesting, but in my experience, a single "agent" with proper context management is better than a complicated agent graph. Dealing with hand-off (+ hand back) and multiple levels of conversations just leaves too much room for critical information to get siloed.
If you have a narrow task that doesn't need full context, then agent delegation (putting an agent or inference behind a simple tool call) can be effective. A good example is to front your RAG with a search() tool with a simple "find the answer" agent that deals with the context and can run multiple searches if needed.
I think the PydanticAI framework has the right approach of encouraging Agent Delegation & sequential workflow first and trying to steer you away graphs[0]
Single agent with good context management beats a sloppy multi-agent setup every time, I agree. But you hit a wall around 100-120k tokens of accumulated context where the model starts losing the thread. It'll forget a constraint from early in the conversation or subtly contradict a decision it made 50 tool calls ago. That's when you need to split, not because the architecture is elegant, but because the model literally can't hold it all anymore. The question is whether you split into a pre-planned graph or let the agent decide when to split. Both have real tradeoffs.
Maybe, but "really smart" is doing a lot of work there. Even if the model is 10x better, you still need something to manage tool failure, retries, rate limits, cost budgets, human approval gates, and state persistence across long-running tasks. Those aren't intelligence problems, they're infrastructure problems. The framework isn't going away, it's just going to get a lot thinner.
If context window is infinite and performance isn't constrained, the subagent stuff isn't necessary. Until then, harnesses are for context management and parallelism.
cjonas|9 days ago
If you have a narrow task that doesn't need full context, then agent delegation (putting an agent or inference behind a simple tool call) can be effective. A good example is to front your RAG with a search() tool with a simple "find the answer" agent that deals with the context and can run multiple searches if needed.
I think the PydanticAI framework has the right approach of encouraging Agent Delegation & sequential workflow first and trying to steer you away graphs[0]
[0]:https://ai.pydantic.dev/graph/
devonkelley|6 days ago
sdeiley|9 days ago
devonkelley|6 days ago
kimjune01|8 days ago
znnajdla|9 days ago