Language Agents: Foundations, Prospects, and Risks

Yu Su, Diyi Yang, Shunyu Yao, Tao Yu

Abstract
Language agents are autonomous agents, usually powered by large language models, that can follow language instructions to carry out diverse and complex tasks in real-world or simulated environments. It is one of the most heated discussion threads in AI and NLP at present with many proof-of-concept efforts, yet there lacks a systematic account of the conceptual definition, theoretical foundation, promising directions, and risks of language agents. This proposed tutorial aspires to fill this gap by providing a conceptual framework of language agents as well as giving a comprehensive discussion on important topic areas including tool augmentation, grounding, reasoning and planning, multi-agent systems, and rissk and societal impact. Language played a critical role in the evolution of biological intelligence, and now artificial intelligence may be following a similar evolutionary path. This is remarkable and concerning at the same time. We hope this tutorial will provide a timely framework to facilitate constructive discussion on this important emerging topic.
Anthology ID:
2024.emnlp-tutorials.3
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Jessy Li, Fei Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
17–24
Language:
URL:
https://preview.aclanthology.org/add_missing_videos/2024.emnlp-tutorials.3/
DOI:
10.18653/v1/2024.emnlp-tutorials.3
Bibkey:
Cite (ACL):
Yu Su, Diyi Yang, Shunyu Yao, and Tao Yu. 2024. Language Agents: Foundations, Prospects, and Risks. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts, pages 17–24, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Language Agents: Foundations, Prospects, and Risks (Su et al., EMNLP 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_missing_videos/2024.emnlp-tutorials.3.pdf
PDF Search Fix data