Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction

• URL: http://arxiv.org/abs/2505.11063v2
• Date: Mon, 19 May 2025 06:52:59 GMT
• Title: Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction
• Authors: Changyue Jiang, Xudong Pan, Min Yang,
• Abstract summary: Internal reasoning process significantly influences tool usage and subsequent actions.<n>Minor deviations in the agent's thought may trigger cascading effects leading to irreversible safety incidents.<n>Thought-Aligner corrects each high-risk thought on the fly before each action execution.<n>The corrected thought is then reintroduced to the agent, ensuring safer subsequent decisions and tool interactions.
• Score: 20.7755316818041
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: LLM-based autonomous agents possess capabilities such as reasoning, tool invocation, and environment interaction, enabling the execution of complex multi-step tasks. The internal reasoning process, i.e., thought, of behavioral trajectory significantly influences tool usage and subsequent actions but can introduce potential risks. Even minor deviations in the agent's thought may trigger cascading effects leading to irreversible safety incidents. To address the safety alignment challenges in long-horizon behavioral trajectories, we propose Thought-Aligner, a plug-in dynamic thought correction module. Utilizing a lightweight and resource-efficient model, Thought-Aligner corrects each high-risk thought on the fly before each action execution. The corrected thought is then reintroduced to the agent, ensuring safer subsequent decisions and tool interactions. Importantly, Thought-Aligner modifies only the reasoning phase without altering the underlying agent framework, making it easy to deploy and widely applicable to various agent frameworks. To train the Thought-Aligner model, we construct an instruction dataset across ten representative scenarios and simulate ReAct execution trajectories, generating 5,000 diverse instructions and more than 11,400 safe and unsafe thought pairs. The model is fine-tuned using contrastive learning techniques. Experiments across three agent safety benchmarks involving 12 different LLMs demonstrate that Thought-Aligner raises agent behavioral safety from approximately 50% in the unprotected setting to 90% on average. Additionally, Thought-Aligner maintains response latency below 100ms with minimal resource usage, demonstrating its capability for efficient deployment, broad applicability, and timely responsiveness. This method thus provides a practical dynamic safety solution for the LLM-based agents.

Related papers

• Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use [6.622648583261088]
  Agentic language models must plan, call tools, and execute long-horizon actions where a single misstep can cause irreversible harm.<n>We introduce MOSAIC, a framework that aligns agents for safe multi-step tool use by making safety decisions explicit and learnable.<n>We show that MOSAIC reduces harmful behavior by up to 50%, increases harmful-task refusal by over 20% on injection attacks, cuts privacy leakage, and preserves or improves benign task performance.
  arXiv  Detail & Related papers  (2026-03-03T17:59:35Z)
• Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents [68.20752678837377]
  We propose a principled taxonomy that transforms single-turn harmful tasks into multi-turn attack sequences.<n>Using this taxonomy, we construct MT-AgentRisk, the first benchmark to evaluate multi-turn tool-using agent safety.<n>We propose ToolShield, a training-free, tool-agnostic, self-exploration defense.
  arXiv  Detail & Related papers  (2026-02-13T18:38:18Z)
• AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security [126.49733412191416]
  Current guardrail models lack agentic risk awareness and transparency in risk diagnosis.<n>We propose a unified three-dimensional taxonomy that categorizes agentic risks by their source (where), failure mode (how), and consequence (what)<n>We introduce a new fine-grained agentic safety benchmark (ATBench) and a Diagnostic Guardrail framework for agent safety and security (AgentDoG)
  arXiv  Detail & Related papers  (2026-01-26T13:45:41Z)
• ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback [53.2744585868162]
  Monitoring step-level tool invocation behaviors in real time is critical for agent deployment.<n>We first construct TS-Bench, a novel benchmark for step-level tool invocation safety detection in LLM agents.<n>We then develop a guardrail model, TS-Guard, using multi-task reinforcement learning.
  arXiv  Detail & Related papers  (2026-01-15T07:54:32Z)
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)
• AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents [8.290987399121343]
  We propose AgentSpec, a lightweight language for specifying and enforcing runtime constraints on LLM agents.<n>With AgentSpec, users define structured rules that incorporate triggers, predicates, and enforcement mechanisms.<n>We implement AgentSpec across multiple domains, including code execution, embodied agents, and autonomous driving.
  arXiv  Detail & Related papers  (2025-03-24T13:31:48Z)
• SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents [42.69984822098671]
  Existing benchmarks predominantly overlook critical safety risks, focusing solely on planning performance.<n>We present SafeAgentBench-the first benchmark for safety-aware task planning of embodied LLM agents in interactive simulation environments.<n>SafeAgentBench includes: (1) an executable, diverse, and high-quality dataset of 750 tasks, rigorously curated to cover 10 potential hazards and 3 task types; (2) SafeAgentEnv, a universal embodied environment with a low-level controller, supporting multi-agent execution with 17 high-level actions for 8 state-of-the-art baselines; and (3) reliable evaluation methods from both execution and semantic perspectives.
  arXiv  Detail & Related papers  (2024-12-17T18:55:58Z)
• AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents [84.96249955105777]
  LLM agents may pose a greater risk if misused, but their robustness remains underexplored.<n>We propose a new benchmark called AgentHarm to facilitate research on LLM agent misuse.<n>We find leading LLMs are surprisingly compliant with malicious agent requests without jailbreaking.
  arXiv  Detail & Related papers  (2024-10-11T17:39:22Z)
• AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases [73.04652687616286]
  We propose AgentPoison, the first backdoor attack targeting generic and RAG-based LLM agents by poisoning their long-term memory or RAG knowledge base. Unlike conventional backdoor attacks, AgentPoison requires no additional model training or fine-tuning. On each agent, AgentPoison achieves an average attack success rate higher than 80% with minimal impact on benign performance.
  arXiv  Detail & Related papers  (2024-07-17T17:59:47Z)
• MIDAS: Multi-agent Interaction-aware Decision-making with Adaptive Strategies for Urban Autonomous Navigation [22.594295184455]
  This paper builds a reinforcement learning-based method named MIDAS where an ego-agent learns to affect the control actions of other cars. MIDAS is validated using extensive experiments and we show that it (i) can work across different road geometries, (ii) is robust to changes in the driving policies of external agents, and (iv) is more efficient and safer than existing approaches to interaction-aware decision-making.
  arXiv  Detail & Related papers  (2020-08-17T04:34:25Z)
• Safe Reinforcement Learning via Curriculum Induction [94.67835258431202]
  In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly. Existing safe reinforcement learning methods make an agent rely on priors that let it avoid dangerous situations. This paper presents an alternative approach inspired by human teaching, where an agent learns under the supervision of an automatic instructor.
  arXiv  Detail & Related papers  (2020-06-22T10:48:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.