Comment by bob1029
4 months ago
The model can call a copy of itself as a tool (i.e., we maintain actual stack frames in the hosting layer). Explicit tools are made available: Call(prompt) & Return(result).
The user's conversation happens at level 0. Any actual tool use is only permitted at stack depths > 0. When the model calls the Return tool at stack depth 0 we end that logical turn of conversation and the argument to the tool is presented to the user. The user can then continue the conversation if desired with all prior top level conversation available in-scope.
It's effectively the exact same experience as ChatGPT, but each time the user types a message an entire depth-first search process kicks off that can take several minutes to complete each time.
How is this different from a standard tool-call agentic loop, or subagents?
Each stack frame has its own isolated context. This pushes the token pressure down the stack. The top level conversation can go on for days in this arrangement. There is no need for summarization or other tricks.
Is this related to the paper on Recursive Language Models? I remember it mentioned something similar about "symbolic recursion", but the way you describe it makes it sound too simple, why is there an entire paper about it?
1 reply →
This is just subagents.