Research Collections
Curated reading lists for key Zone III topics, plus your personally saved papers.
Zone III Essentials
The 8 most important papers for understanding Zone III autonomous enterprise AI. Start here.
ReAct: Synergizing Reasoning and Acting in Language Models
We explore the use of LLMs to generate both reasoning traces and task-specific actions in an interleaved manner. ReAct allows LLMs to interact with external too…
Reflexion: Language Agents with Verbal Reinforcement Learning
We present Reflexion, a framework to reinforce language agents not by updating weights, but instead through linguistic feedback. Reflexion converts binary or sc…
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
We introduce Tree of Thoughts (ToT), a framework that generalizes over the popular Chain of Thought approach to prompting language models, and enables explorati…
Cognitive Architectures for Language Agents
We draw on the rich history of cognitive science and symbolic AI to propose CoALA, a conceptual framework for language agents. CoALA organizes memory, action, a…
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
We introduce semantic uncertainty, an entropy-based uncertainty measure for free-form natural language generation. Semantic uncertainty accounts for the fact th…
Communicative Agents for Software Development
We present ChatDev, a virtual chat-powered software company with multi-agent collaboration. ChatDev uses role-playing to simulate different software development…
Scalable Oversight: Supervising AI Systems That Exceed Human Capabilities
We discuss the challenge of providing oversight to AI systems that may exceed human capabilities in some domains. We propose scalable oversight as a research ag…
Neuro-Symbolic AI: The 3rd Wave
We survey the history and current state of neuro-symbolic AI, identifying three waves of development. The third wave combines deep learning with symbolic reason…