paper-with-me

Papers

Understanding Cognition-Induced Risks in Agentic AI Systems

2026-08-15 · Guanchu Wang, Qinuo Li, Mengnan Du, Xia Hu, Bowen Zhou hf

Frontier agentic systems powered by large language models (LLMs) exhibit human-like patterns of cognition. As these systems become deeply integrated across different domains, their cognitive engagement raises critical concerns for human society that remain insufficiently studied. To address this gap, we systematically analyze risks induced by expanding cognitive capabilities, following a three-level framework defined by their cognitive scope, from physical cognition to social cognition, and finally to self-referential cognition. We study their potential risks to human agency, autonomy, and control capability, corresponding to each cognitive level. We finally propose strategies to mitigate these risks and enhance the controllability of agentic AI systems, ensuring their long-term safe development.

📄 PDF Abstract BibTeX arXiv:2608.15304

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution

2026-01-21 · Chen Qian, Peng Wang, Dongrui Liu, Junyao Yang 외 arxiv

Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more autonomous and are deployed at scale, un…

The Perils of Agency: How Developers Perceive, Prioritize, and Address Risks in Agentic AI Products

2026-06-13 · Hao-Ping Lee, Jessica He, David Piorkowski, Thomas Serban von Davier 외 arxiv

Agentic AI systems act autonomously, use tools, adapt to context, and operate in complex real-world environments. However, these same characteristics can create or exacerbate product risks. We studied how industry develo…

SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions

2026-03-07 · Saroj Mishra, Suman Niroula, Umesh Yadav, Dilip Thakur 외 arxiv

Retrieval-Augmented Generation (RAG) systems are increasingly evolving into agentic architectures where large language models autonomously coordinate multi-step reasoning, dynamic memory management, and iterative retriev…

With Great Capabilities Come Great Responsibilities: Introducing the Agentic Risk & Capability Framework for Governing Agentic AI Systems

2025-12-22 · Shaun Khoo, Jessica Foo, Roy Ka-Wei Lee arxiv

Agentic AI systems present both significant opportunities and novel risks due to their capacity for autonomous action, encompassing tasks such as code execution, internet interaction, and file modification. This poses co…

Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework

2026-03-12 · Chingkwun Lam, Jiaxin Li, Lingfei Zhang, Kuo Zhao arxiv

Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong multimodal learning, and sophisticated reasoning. However, as memory syst…