Related papers: RoboSafe: Safeguarding Embodied Agents via Executa…

Code agents have gained widespread adoption due to their strong code generation capabilities and integration with code interpreters, enabling dynamic execution, debugging, and interactive programming capabilities. While these advancements…

Vision--Language Models (VLMs) show significant promise for Medical Visual Question Answering (VQA), yet their deployment in clinical settings is hindered by severe vulnerability to adversarial attacks. Standard adversarial training, while…

Safety reasoning is a recent paradigm where LLMs reason over safety policies before generating responses, thereby mitigating limitations in existing safety measures such as over-refusal and jailbreak vulnerabilities. However, implementing…

The dawn of embodied intelligence has ushered in an unprecedented imperative for resilient, cognition-enabled multi-agent collaboration across next-generation ecosystems, revolutionizing paradigms in autonomous manufacturing, adaptive…

As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that exploit extended user-agent-environment interactions to pursue malicious objectives…

With the widespread deployment of Computer-using Agents (CUAs) in complex real-world environments, prevalent long-term risks often lead to severe and irreversible consequences. Most existing guardrails for CUAs adopt a reactive approach,…

LLM-based multi-agent systems excel at planning, tool use, and role coordination, but their openness and interaction complexity also expose them to jailbreak, prompt-injection, and adversarial collaboration. Existing defenses fall into two…

Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process. This hinders the application of RL to real-world control problems, especially…

Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents capable of perceiving, reasoning, and acting in dynamic, open-ended environments. These large-model agents mark a paradigm shift from static…

Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous driving and robotic manipulation. Recent research has…

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that enables iterative…

While Deep Reinforcement Learning (DRL) has achieved remarkable success across various domains, it remains vulnerable to occasional catastrophic failures without additional safeguards. An effective solution to prevent these failures is to…

Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to…

Operating robots in open-ended scenarios with diverse tasks is a crucial research and application direction in robotics. While recent progress in natural language processing and large multimodal models has enhanced robots' ability to…

A key limitation of learned robot control policies is their inability to generalize outside their training data. Recent works on vision-language-action models (VLAs) have shown that the use of large, internet pre-trained vision-language…

Multimodal Large Language Models (MLLMs) are susceptible to the implicit reasoning risk, wherein innocuous unimodal inputs synergistically assemble into risky multimodal data that produce harmful outputs. We attribute this vulnerability to…

Recent advances in Large Vision-Language Models (LVLMs) have showcased strong reasoning abilities across multiple modalities, achieving significant breakthroughs in various real-world applications. Despite this great success, the safety…

Assuring the safety and trustworthiness of autonomous systems is particularly difficult when learning-enabled components and open environments are involved. Formal methods provide strong guarantees but depend on complete models and static…

Embodied Chain-of-Thought (ECoT) reasoning enhances vision-language-action (VLA) models by improving performance and interpretability through intermediate reasoning steps. However, its sequential autoregressive token generation introduces…