Papers
arxiv:2312.07540

diff History for Neural Language Agents

Published on Dec 12, 2023
Authors:
,
,

Abstract

Neural Language Models (LMs) offer an exciting solution for general-purpose embodied control. However, a key technical issue arises when using an LM-based controller: environment observations must be converted to text, which coupled with history, results in long and verbose textual prompts. As a result, prior work in LM agents is limited to restricted domains with small observation size as well as minimal needs for interaction history or instruction tuning. In this paper, we introduce diff history, a simple and highly effective solution to these issues. By applying the Unix diff command on consecutive text observations in the interaction histories used to prompt LM policies, we can both abstract away redundant information and focus the content of textual inputs on the salient changes in the environment. On NetHack, an unsolved video game that requires long-horizon reasoning for decision-making, LMs tuned with diff history match state-of-the-art performance for neural agents while needing 1800x fewer training examples compared to prior work. Even on the simpler BabyAI-Text environment with concise text observations, we find that although diff history increases the length of prompts, the representation it provides offers a 25% improvement in the efficiency of low-sample instruction tuning. Further, we show that diff history scales favorably across different tuning dataset sizes. We open-source our code and data to https://diffhistory.github.io.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2312.07540 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2312.07540 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.