Agent Workflow Memory
Agents that learn the recipe, not the run: induce reusable workflows from past trajectories — offline from a training set, or online with no labels at all — feed them back into memory, and solve new tasks in fewer steps.
Wang et al. · arXiv 2024 · Reasoning & RL. Read the paper ↗
A free, interactive, animated visual explainer of Agent Workflow Memory — every exhibit computed from the real formulas, with verbatim quotes from the source.
Questions
- What is Agent Workflow Memory?
- Agents that learn the recipe, not the run: induce reusable workflows from past trajectories — offline from a training set, or online with no labels at all — feed them back into memory, and solve new tasks in fewer steps.
- Who published Agent Workflow Memory, and where?
- Wang et al. — arXiv 2024 (arXiv:2409.07429).
- Where can I find a visual explainer of Agent Workflow Memory?
- Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.
Related explainers
- DeepSeek-R1
- ZeRO: Zero Redundancy Optimizer
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Training language models to follow instructions with human feedback
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Constitutional AI: Harmlessness from AI Feedback