665 citations · 2.3k across the 48 of their papers we have counts for
5 papers · 1 filter
CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks
Ping Yu, Jack Lanchantin, Tianlu Wang +6
We propose CoT-Self-Instruct, a synthetic data generation method that instructs LLMs to first reason and plan via Chain-of-Thought (CoT) based on given seed tasks, and then generat…
Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
DiJia Su, Sainbayar Sukhbaatar, Michael Rabbat +2
In cognition theory, human thinking is governed by two systems: the fast and intuitive System 1 and the slower but more deliberative System 2. Analogously, Large Language Models (L…
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Lucas Lehnert, Sainbayar Sukhbaatar, DiJia Su +4
While Transformers have enabled tremendous progress in various application settings, such architectures still trail behind traditional symbolic planners for solving complex decisio…
Planning with Arithmetic and Geometric Attributes
David Folqué, Sainbayar Sukhbaatar, Arthur Szlam +1
A desirable property of an intelligent agent is its ability to understand its environment to quickly generalize to novel tasks and compose simpler tasks into more complex ones. If…
Composable Planning with Attributes
Amy Zhang, Adam Lerer, Sainbayar Sukhbaatar +2
The tasks that an agent will need to solve often are not known during training. However, if the agent knows which properties of the environment are important then, after learning h…