3 papers
cs.CL2024
Sparse Rewards Can Self-Train Dialogue Agents
Barrett Martin Lattimer, Varun Gangal, Ryan McDonald +1
Recent advancements in state-of-the-art (SOTA) Large Language Model (LLM) agents, especially in multi-turn dialogue tasks, have been primarily driven by supervised fine-tuning and…
cs.CL2023
Multi-Step Dialogue Workflow Action Prediction
Ramya Ramakrishnan, Ethan R. Elenberg, Hashan Narangodage +1
In task-oriented dialogue, a system often needs to follow a sequence of actions, called a workflow, that complies with a set of guidelines in order to complete a task. In this pape…
cs.LG2023
SteP: Stacked LLM Policies for Web Actions
Paloma Sodhi, S. R. K. Branavan, Yoav Artzi +1
Performing tasks on the web presents fundamental challenges to large language models (LLMs), including combinatorially large open-world tasks and variations across web interfaces.…