Tag
Argues that using LangGraph-style orchestration for procedural agent tasks is less effective than simply embedding the full procedure in the system prompt.
DuoMem is a dual-space distillation framework that transfers procedural problem-solving from large language models to compact student models via context-space and parameter-space distillation, achieving high performance with minimal additional parameters and improved inference speed. It boosts a 4B model from 4.3% to 77.9% task success rate on ALFWorld.
This paper demonstrates that compiling agentic workflow procedures into the weights of a small fine-tuned model achieves near-frontier quality at 128–462× cost reduction compared to in-context baselines, addressing perceived barriers of quality, cost, and flexibility.
The author questions whether many so-called AI agents are better described as workflows, arguing that for repeatable browser tasks, defined workflows may be more reliable than agents that reinterpret steps each time.