Athena: Safe Autonomous Agents with Verbal Contrastive Learning

Tanmana Sadhu, Ali Pesaranghader, Yanan Chen, Dong Hoon Yi


Abstract
Due to emergent capabilities, large language models (LLMs) have been utilized as language-based agents to perform a variety of tasks and make decisions with an increasing degree of autonomy. These autonomous agents can understand high-level instructions, interact with their environments, and execute complex tasks using a selection of tools available to them. As the capabilities of the agents expand, ensuring their safety and trustworthiness becomes more imperative. In this study, we introduce the Athena framework which leverages the concept of verbal contrastive learning where past safe and unsafe trajectories are used as in-context (contrastive) examples to guide the agent towards safety while fulfilling a given task. The framework also incorporates a critiquing mechanism to guide the agent to prevent risky actions at every step. Furthermore, due to the lack of existing benchmarks on the safety reasoning ability of LLM-based agents, we curate a set of 80 toolkits across 8 categories with 180 scenarios to provide a safety evaluation benchmark. Our experimental evaluation, with both closed- and open-source LLMs, indicates verbal contrastive learning and interaction-level critiquing improve the safety rate significantly.
Anthology ID:
2024.emnlp-industry.84
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
November
Year:
2024
Address:
Miami, Florida, US
Editors:
Franck Dernoncourt, Daniel Preoţiuc-Pietro, Anastasia Shimorina
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1121–1130
Language:
URL:
https://aclanthology.org/2024.emnlp-industry.84
DOI:
Bibkey:
Cite (ACL):
Tanmana Sadhu, Ali Pesaranghader, Yanan Chen, and Dong Hoon Yi. 2024. Athena: Safe Autonomous Agents with Verbal Contrastive Learning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1121–1130, Miami, Florida, US. Association for Computational Linguistics.
Cite (Informal):
Athena: Safe Autonomous Agents with Verbal Contrastive Learning (Sadhu et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-industry.84.pdf
Poster:
 2024.emnlp-industry.84.poster.pdf
Presentation:
 2024.emnlp-industry.84.presentation.pdf
Video:
 2024.emnlp-industry.84.video.mp4