Related papers: MADRA: Multi-Agent Debate for Risk-Aware Embodied …
This paper introduces EmbodiedAgent, a hierarchical framework for heterogeneous multi-robot control. EmbodiedAgent addresses critical limitations of hallucination in impractical tasks. Our approach integrates a next-action prediction…
Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these…
Risk mitigation techniques are critical to avoiding accidents associated with driving behaviour. We provide a novel Multi-Class Driver Distraction Risk Assessment (MDDRA) model that considers the vehicle, driver, and environmental data…
In the realm of embodied intelligence, the evolution of large language models (LLMs) has markedly enhanced agent decision making. Consequently, researchers have begun exploring agent performance in dynamically changing high-risk scenarios,…
When combining Large Language Models (LLMs) with autonomous agents, used in network monitoring and decision-making systems, this will create serious security issues. In this research, the MAESTRO framework consisting of the seven layers…
A surge in academic publications calls for automated deep research (DR) systems, but accurately evaluating them is still an open problem. First, existing benchmarks often focus narrowly on retrieval while neglecting high-level planning and…
Intelligent transportation systems require connected and automated vehicles (CAVs) to conduct safe and efficient cooperation with human-driven vehicles (HVs) in complex real-world traffic environments. However, the inherent unpredictability…
Multi-agent debate system (MAD) imitating the process of human discussion in pursuit of truth, aims to align the correct cognition of different agents for the optimal solution. It is challenging to make various agents perform right and…
Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…
With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal task execution are gradually relying on such large…
The increasing use of autonomous and semi-autonomous agents in society has made it crucial to validate their safety. However, the complex scenarios in which they are used may make formal verification impossible. To address this challenge,…
AI systems are increasingly applied to complex tasks that involve interaction with humans. During training, such systems are potentially dangerous, as they haven't yet learned to avoid actions that could cause serious harm. How can an AI…
As reinforcement learning agents become increasingly integrated into complex, real-world environments, designing for safety becomes a critical consideration. We specifically focus on researching scenarios where agents can cause undesired…
Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…
Reinforcement learning (RL) has recently been used for solving challenging decision-making problems in the context of automated driving. However, one of the main drawbacks of the presented RL-based policies is the lack of safety guarantees,…
In edge computing systems, autonomous agents must make fast local decisions while competing for shared resources. Existing MARL methods often resume to centralized critics or frequent communication, which fail under limited observability…
Manufacturing industries are facing increasing product variability due to the growing demand for personalized products. Under these conditions, ensuring safety becomes challenging as frequent reconfigurations can lead to unintended…
Large Language Models are being increasingly deployed as the decision-making core of autonomous agents capable of effecting change in external environments. Yet, in conversational benchmarks, which simulate real-world customer-centric issue…
Recent advances in Large Language Models (LLMs) have significantly improved table understanding tasks such as Table Question Answering (TableQA), yet challenges remain in ensuring reliability, scalability, and efficiency, especially in…
We argue that LLM agent security is fundamentally an agent-human interaction (AHI) problem, not a purely algorithmic one. To substantiate this position, we conduct a systematic analysis of 59 academic papers, 21 production agent systems,…