# Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions

Source: [Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions](<https://www.sota2.com/research/paper/68fa6fc91e209131cea47672>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:27:18.619Z

Authors: Chad DeChant, Iretiayo Akinola, Daniel Bauer

Published: 2023-06-16T15:47:24.000Z

## Abstract

When robots perform long action sequences, users will want to easily and reliably find out what they have done. We therefore demonstrate the task of learning to summarize and answer questions about a robot agent's past actions using natural language alone. A single system with a large language model at its core is trained to both summarize and answer questions about action sequences given ego-centric video frames of a virtual robot and a question prompt. To enable training of question answering, we develop a method to automatically generate English-language questions and answers about objects, actions, and the temporal order in which actions occurred during episodes of robot action in the virtual environment. Training one model to both summarize and answer questions enables zero-shot transfer of representations of objects learned through question answering to improved action summarization. % involving objects not seen in training to summarize.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.09922>)

[PDF](<https://arxiv.org/pdf/2306.09922.pdf>)