paper-with-me

Papers

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning

2025-03-26 · Zhaorun Chen, Mintong Kang, Bo Li

Autonomous agents powered by foundation models have seen widespread adoption across various real-world applications. However, they remain highly vulnerable to malicious instructions and attacks, which can result in severe consequences such as privacy breaches and financial losses. More critically, existing guardrails for LLMs are not applicable due to the complex and dynamic nature of agents. To tackle these challenges, we propose ShieldAgent, the first guardrail agent designed to enforce explicit safety policy compliance for the action trajectory of other protected agents through logical reasoning. Specifically, ShieldAgent first constructs a safety policy model by extracting verifiable rules from policy documents and structuring them into a set of action-based probabilistic rule circuits. Given the action trajectory of the protected agent, ShieldAgent retrieves relevant rule circuits and generates a shielding plan, leveraging its comprehensive tool library and executable code for formal verification. In addition, given the lack of guardrail benchmarks for agents, we introduce ShieldAgent-Bench, a dataset with 3K safety-related pairs of agent instructions and action trajectories, collected via SOTA attacks across 6 web environments and 7 risk categories. Experiments show that ShieldAgent achieves SOTA on ShieldAgent-Bench and three existing benchmarks, outperforming prior methods by 11.3% on average with a high recall of 90.1%. Additionally, ShieldAgent reduces API queries by 64.7% and inference time by 58.2%, demonstrating its high precision and efficiency in safeguarding agents.

📄 PDF Abstract BibTeX arXiv:2503.22738

Code (0)

등록된 구현이 없습니다.

Tasks

Logical Reasoning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Library 설명 없음

Similar Papers 제목 키워드 기반

Robust Shielding for Safe Reinforcement Learning

2026-05-29 · Edwin Hamel-De le Court, Thom Badings, Alessandro Abate, Francesco Belardinelli 외 arxiv

Shielding is an effective approach to formally guarantee the safety of reinforcement learning agents in Markov decision processes (MDPs). However, existing shielding techniques typically assume knowledge of the safety-re…

Reinforcement Learning

Safe Multi-Agent Reinforcement Learning via Shielding

2021-01-27 · Ingy Elsayed-Aly, Suda Bharadwaj, Christopher Amato, Rüdiger Ehlers 외

Multi-agent reinforcement learning (MARL) has been increasingly used in a wide range of safety-critical applications, which require guaranteed safety (e.g., no unsafe states are ever visited) during the learning process.…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Approximate Shielding of Atari Agents for Safe Exploration

2023-04-21 · Alexander W. Goodall, Francesco Belardinelli

Balancing exploration and conservatism in the constrained setting is an important problem if we are to use reinforcement learning for meaningful tasks in the real world. In this paper, we propose a principled algorithm f…

Atari GamesSafe Exploration

Compositional Shielding and Reinforcement Learning for Multi-Agent Systems

2024-10-14 · Asger Horn Brorholt, Kim Guldstrand Larsen, Christian Schilling

Deep reinforcement learning has emerged as a powerful tool for obtaining high-performance policies. However, the safety of these policies has been a long-standing issue. One promising paradigm to guarantee safety is a sh…

Deep Reinforcement Learningreinforcement-learningReinforcement Learning

QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems

2025-12-18 · Yiliu Yang, Yilei Jiang, Qunzhong Wang, Yingshui Tan 외 arxiv

Safety risks arise as large language model-based agents solve complex tasks with tools, multi-step plans, and inter-agent messages. However, deployer-written policies in natural language are ambiguous and context depende…