Zhiwei Deng
Zhiwei Deng is a Research Scientist at Google Deepmind. He was a Postdoc at the Computer Science Department of Princeton University. He earned his PhD at Simon Fraser University in Computer Science.
He is generally interested in building intelligent learning agents with System 1&2. Recently, he is drawn by reparameterizing knowledge in neural networks through Input-Output memories, and building perceptual world model using self-supervised representation learning.
Authored Publications
Sort By
Preview abstract
In this work, we introduce a novel approach that equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks. Our approach prompts LLM agents to decompose a given task into manageable subtasks (i.e., to make a plan), and to continuously introspect upon the suitability and results of their actions.
We implement a three-fold introspective intervention:
1) anticipatory reflection on potential failure and alternative remedy before action execution,
2) post-action alignment with subtask objectives and backtracking with remedy to ensure utmost effort in plan execution, and
3) comprehensive review upon plan completion for future strategy refinement.
Deploying this methodology within WebArena for practical tasks in web environments, our agent demonstrates superior performance over existing zero-shot methods.
Experimental results suggest that our introspection-driven approach not only enhances the agent's ability to navigate unanticipated challenges through a robust mechanism of plan execution, but also improves efficiency by reducing the number of reflection and plan revision.
View details
