arXiv:2608. 13574v1 Announce Type: new Abstract: LLM agents increasingly operate as execution systems that invoke tools, modify local state, use persistent memory, and interact with external protocols.
By Bo Jin, Qiang Jiao, Xin Tong
The paper introduces the Symbolic Guidance Taxonomy (SGT) to regulate the autonomy of large language model agents in distributed multi‑agent coordination. By providing symbolic guidance—ranging from open‑ended reasoning to fully prescriptive algorithmic steps—the authors find that intermediate levels of autonomy consistently outperform both unguided agents and fully prescriptive specifications. These results suggest that carefully controlling agent autonomy is a crucial design principle for effective LLM‑based coordination.
By Ben Rachmut, Ning Zhang, Yevgeniy Vorobeychik, William Yeoh
The paper introduces a hierarchical feedback framework that guides large language models (LLMs) to produce executable plans for cyber‑physical systems (CPSs) from natural language commands. It prompts LLMs to generate both a structured task plan and signal temporal logic (STL) constraints, then uses a sound algorithm to detect contradictions and provide feedback for plan revision. At execution time, diagnostic information from failed control synthesis—such as violated constraints and conflicting component assignments—is fed back to the LLM to enable task replanning, achieving an 87.9% success rate on seven heterogeneous CPS scenarios.
By Jinglin Dai, Jiawan Wang, Ruiqi Hong, Lei Bu
SecureGARD is a dynamic ontology‑guided governance framework designed to secure tool‑using large language model agents. It grounds heterogeneous tool calls in a shared semantic representation, using an executable ontology combined with episode‑level task state to make deterministic ready, waiting, and forbidden decisions. The system evolves its ontology offline from verified training executions, ensuring logical consistency and protecting entailments, and achieves a 0% attack success rate across multiple benchmarks while improving task utility under attack.
By Guoqin Xiong, Shengtao Wen, Xiang Chen, Xinyi Zeng, Zhaoxin Fan, Wei Ye, Xiaofeng Cao, Sheng-Jun Huang
arXiv:2604.08567v3 Announce Type: replace
Abstract: Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing system...
By Shu Yang, Shenzhe Zhu, Hao Zhu, Jos\'e Ram\'on Enr\'iquez, Di Wang, Alex Pentland, Michiel A. Bakker, Jiaxin Pei
ActGov is a runtime enforcement framework that validates each action proposed by a large language model (LLM) agent before it interacts with external tools, ensuring that actions stay within task‑scoped authorization boundaries and comply with dynamically constructed policies. It builds policies from tool specifications, benign tasks, and failure traces, verifying updates via SMT‑based counterexample checking. In evaluations on AgentDojo and AgentDyn benchmarks, ActGov consistently reduces indirect prompt‑injection attack success while maintaining task utility, outperforming existing defenses.
By Kaiyuan Zhang, Yuke Peng, Ke Jiang, Yinqian Zhang