Wang et al. (2025)

Agent Workflow Memory

arXiv

Find It

DOI

In Summary

Language model agents struggle with long-horizon tasks involving complex action trajectories, whereas humans solve such tasks by learning reusable routines from past experience and applying them to future actions. The authors introduce Agent Workflow Memory, a method for inducing commonly reused routines and selectively supplying them to guide subsequent generation, applicable both offline from training examples and online from test queries. On two web navigation benchmarks covering more than 1000 tasks across more than 200 domains, the method improves baseline success rates by 24.6% and 51.1% relative on Mind2Web and WebArena respectively while reducing the number of steps taken, and generalizes across tasks, websites, and domains as the train-test distribution gap widens.

Reference

Wang, Z. Z., Mao, J., Fried, D., & Neubig, G. (2025). Agent workflow memory. In Proceedings of the 42nd International Conference on Machine Learning (PMLR 267, pp. 63897-63911).

What Rests on This

1 mechanism cites this source. Each finding below is quoted as it appears on that mechanism's own page.

Schema Formation Representational Structures

Measured in AI

Saved memory: Agent Workflow Memory has a GPT-4-based web agent distil reusable routines from its past tasks and store them for later use, raising task success on the WebArena benchmark from 23.5% to 35.5%; this is schema-like induction under another name, with no human comparison