English
Related papers

Related papers: Discovering Agentic Safety Specifications from 1-B…

200 papers

Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks. Existing agentic memory attacks require privileged access or explicit…

Cryptography and Security · Computer Science 2026-05-20 Kaixiang Wang , Jiong Lou , Zhaojiacheng Zhou , Jie Li

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…

Artificial Intelligence · Computer Science 2025-08-20 Yuzhi Tang , Tianxiao Li , Elizabeth Li , Chris J. Maddison , Honghua Dong , Yangjun Ruan

Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios,…

Cryptography and Security · Computer Science 2026-05-26 Lixing Lin , Juli You , Yue Li , Luyun Lin , Yiqing Wang , Zhen Zhang , Moxuan Zheng

Large Language Models (LLMs) exhibit robust problem-solving capabilities for diverse tasks. However, most LLM-based agents are designed as specific task solvers with sophisticated prompt engineering, rather than agents capable of learning…

Artificial Intelligence · Computer Science 2024-06-10 Wenqi Zhang , Ke Tang , Hai Wu , Mengna Wang , Yongliang Shen , Guiyang Hou , Zeqi Tan , Peng Li , Yueting Zhuang , Weiming Lu

Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…

Machine Learning · Computer Science 2025-02-28 Xiyue Peng , Hengquan Guo , Jiawei Zhang , Dongqing Zou , Ziyu Shao , Honghao Wei , Xin Liu

Training LLM agents in multi-turn environments with sparse rewards, where completing a single task requires 30+ turns of interaction within an episode, presents a fundamental challenge for reinforcement learning. We identify a critical…

Machine Learning · Computer Science 2026-02-11 Wujiang Xu , Wentian Zhao , Zhenting Wang , Yu-Jhe Li , Can Jin , Mingyu Jin , Kai Mei , Kun Wan , Dimitris N. Metaxas

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of reasoning tasks. Recent methods have further improved LLM performance in complex mathematical reasoning. However, when extending these methods…

Artificial Intelligence · Computer Science 2025-11-11 Chen He , Xun Jiang , Lei Wang , Hao Yang , Chong Peng , Peng Yan , Fumin Shen , Xing Xu

LLM agents emit actions, not just text, and once taken, those actions often cannot be undone. Yet today's agent-safety evaluations run greedy or a few sampled rollouts and report a single safe/unsafe rate -- blind to the long-tail…

Cryptography and Security · Computer Science 2026-05-05 Shuyi Lin , Anshuman Suri , Alina Oprea , Cheng Tan

Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training remain largely unexplored. Beyond explicit reward hacking that…

Computation and Language · Computer Science 2026-02-05 Zhexin Zhang , Yida Lu , Junfeng Fang , Junxiao Yang , Shiyao Cui , Hao Zhou , Fandong Meng , Jie Zhou , Hongning Wang , Minlie Huang , Tat-Seng Chua

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

Cryptography and Security · Computer Science 2026-04-02 Anubhab Sahu , Diptisha Samanta , Reza Soosahabi

Retrieval is increasingly moving from one-shot matching toward interactive reasoning, where language agents iteratively inspect evidence, reformulate queries, and search again. Training such agents raises a credit-assignment challenge:…

Computation and Language · Computer Science 2026-05-27 Mingchen Li , Hansi Zeng , Zhuo Qian , Jiatan Huang , Hamed Zamani , Hong Yu

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

RL-based agentic search enables LLMs to solve complex questions via dynamic planning and external search. While this approach significantly enhances accuracy with agent policies optimized via large-scale reinforcement learning, we identify…

Artificial Intelligence · Computer Science 2026-04-22 Shiyu Liu , Yongjing Yin , Jianhao Yan , Yunbo Tang , Qinggang Zhang , Bei Li , Xin Chen , Jingang Wang , Xunliang Cai , Jinsong Su

Long-horizon decision-making tasks present significant challenges for LLM-based agents due to the need for extensive planning over multiple steps. In this paper, we propose a hierarchical framework that decomposes complex tasks into…

Machine Learning · Computer Science 2024-10-07 Qi Zhao , Haotian Fu , Chen Sun , George Konidaris

LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The…

Computation and Language · Computer Science 2026-04-24 Wujiang Xu , Jiaojiao Han , Minghao Guo , Kai Mei , Xi Zhu , Han Zhang , Dimitris N. Metaxas

The personalization of black-box large language models (LLMs) is a critical yet challenging task. Existing approaches predominantly rely on context injection, where user history is embedded into the prompt to directly guide the generation…

Computation and Language · Computer Science 2025-11-10 Teqi Hao , Xioayu Tan , Shaojie Shi , Yinghui Xu , Xihe Qiu

Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn…

Artificial Intelligence · Computer Science 2023-10-11 Noah Shinn , Federico Cassano , Edward Berman , Ashwin Gopinath , Karthik Narasimhan , Shunyu Yao

Contemporary large language model (LLM) agents are remarkably capable, but they still lack reliable safety controls and can produce unconstrained, unpredictable, and even actively harmful outputs. To address this, we introduce…

Cryptography and Security · Computer Science 2025-12-29 Bin Wang , Jiazheng Quan , Xingrui Yu , Hansen Hu , Yuhao , Ivor Tsang

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…

Artificial Intelligence · Computer Science 2025-05-21 Maheep Chaudhary , Fazl Barez

Existing LLM-based policy optimizers see only scalar rewards: that a policy scored 0.45, but not whether the agent got stuck in a loop, fell into a hole on the third step, or performed well on 19 out of 20 rollouts and failed…

Machine Learning · Computer Science 2026-05-12 Rahaf Abu Hara , Vaibbhav Murarri , Claudio Zito
‹ Prev 1 2 3 10 Next ›