analiza aiqbench
This paper identifies "state-semantic injection" as a critical security vulnerability where attackers can manipulate the internal state of LLM-driven embodied agents, causing them to execute unintended physical actions. As robotics increasingly rely on large language models for high-level planning and decision-making, this research highlights that the integration of AI with hardware creates new attack surfaces beyond traditional software exploits. The findings underscore an urgent need for robust adversarial training and verification protocols before deploying autonomous systems in uncontrolled environments.
When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents
arXiv:2608.16806v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated capabilities in in-context learning, task decomposition, step-by-step reasoning, and code generation, driving their gradual evolution from text generation models into the core of agents capable of perceiving environments, invoking tools, and executing tasks. Traditional LLM Agents typically obtain information through webpages, documents, databases, or external tools and generate corresponding invocation sequences according to user goals; when this technology is further integrated with robotic systems, large language models begin to undertake functions such as task understanding, high-level planning, and behavioral decision-making. SayCan combines the task reasoning capability of language models with the affordances of robotic skills, while Code as Policies and ProgPrompt generate robot task plans through policy code and programmatic prompting, respectively, and VoxPoser uses language models and vision-language models to construct three-dimensional value maps to guide robotic manipulation \cite{6,7,8,9}. Vision-language-action models such as PaLM-E, RT-2, and GR00T N1 further strengthen the connection among language, visual perception, and robotic actions \cite{10,11,12}. In such LLM-driven embodied agents, the model not only needs to understand user instructions, but also needs to combine scene states, object attributes, spatial relations, and execution feedback to complete task grounding, and then hand the generated action plan to skill libraries, motion planners, or controllers for execution.
Abstract:Large Language Models (LLMs) have demonstrated capabilities in in-context learning, task decomposition, step-by-step reasoning, and code generation, driving their gradual evolution from text generation models into the core of agents capable of perceiving environments, invoking tools, and executing tasks. Traditional LLM Agents typically obtain information through webpages, documents, databases, or external tools and generate corresponding invocation sequences according to user goals; when this technology is further integrated with robotic systems, large language models begin to undertake functions such as task understanding, high-level planning, and behavioral decision-making. SayCan combines the task reasoning capability of language models with the affordances of robotic skills, while Code as Policies and ProgPrompt generate robot task plans through policy code and programmatic prompting, respectively, and VoxPoser uses language models and vision-language models to construct three-dimensional value maps to guide robotic manipulation \cite{6,7,8,9}. Vision-language-action models such as PaLM-E, RT-2, and GR00T N1 further strengthen the connection among language, visual perception, and robotic actions \cite{10,11,12}. In such LLM-driven embodied agents, the model not only needs to understand user instructions, but also needs to combine scene states, object attributes, spatial relations, and execution feedback to complete task grounding, and then hand the generated action plan to skill libraries, motion planners, or controllers for execution.
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2608.16806 [cs.RO]
(or arXiv:2608.16806v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2608.16806 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 301 cuvinte
Subiecte conexe
Article: Securing MCP in Production: Defense-in-Depth beyond the Gateway
InfoQ · 29 iul. 2026
Article: An Evolutionary Architecture Pattern for Managing AI’s Pace of Change
InfoQ · 27 iul. 2026
The payload: the semantic layer, memory, and the loop that fills it
Neo4j · 10 aug. 2026
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
arXiv · 10 iun. 2026