# Athena: Safe Autonomous Agents with Verbal Contrastive Learning

arXiv: https://arxiv.org/abs/2408.11021 · HTML: https://mlsanity.com/paper/2408.11021/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [R-Judge: Benchmarking Safety Risk Awareness for LLM Agents](https://mlsanity.com/paper/2401.10019/) (2024)
- [OpenAGI: When LLM Meets Domain Experts](https://mlsanity.com/paper/2304.04370/) (2023)

## Built on by (most cited first, 5 of 5)

- [Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction](https://mlsanity.com/paper/2505.11063/) (2025)
- [Generalizability of Large Language Model-Based Agents: A Comprehensive Survey](https://mlsanity.com/paper/2509.16330/) (2025)
- [When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent](https://mlsanity.com/paper/2601.07263/) (2026)
- [Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense](https://mlsanity.com/paper/2606.05743/) (2026)
- [OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution](https://mlsanity.com/paper/2608.00677/) (2026)

## Abstract (arXiv)

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.