English
Related papers

Related papers: What Makes a Good LLM Agent for Real-world Penetra…

200 papers

Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verified conclusions, and acting on them without grounding in observable evidence leads to compounding…

Software Engineering · Computer Science 2026-04-14 Jugal Gajjar

We study how runtime enforcement against unsafe actions affects end-to-end task performance in multi-step tool using large language model (LLM) agents. Using tau-bench across Airline and Retail domains, we compare baseline Tool-Calling,…

Cryptography and Security · Computer Science 2026-03-23 Tanmay Sah , Vishal Srivastava , Dolly Sah , Kayden Jordan

Despite the rapid progress, LLMs for sequential decision-making (i.e., LLM agents) still struggle to produce diverse outputs. This leads to insufficient exploration, convergence to sub-optimal solutions, and becoming stuck in loops. Such…

Computation and Language · Computer Science 2026-04-21 Priya Gurjar , Md Farhan Ishmam , Kenneth Marino

While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often rectifiable via backtracking, tool-use failures frequently induce…

Artificial Intelligence · Computer Science 2026-03-17 Shengda Fan , Xuyan Ye , Yupeng Huo , Zhi-Yuan Chen , Yiju Guo , Shenzhi Yang , Wenkai Yang , Shuqi Ye , Jingwen Chen , Haotian Chen , Xin Cong , Yankai Lin

Agentic systems for business process automation often require compliance with policies governing conditional updates to the system state. Evaluation of policy adherence in LLM-based agentic workflows is typically performed by comparing the…

Computation and Language · Computer Science 2026-05-15 Ella Rabinovich , David Boaz , Naama Zwerdling , Ateret Anaby-Tavor

We aim to evaluate Large Language Models (LLMs) for embodied decision making. While a significant body of work has been leveraging LLMs for decision making in embodied environments, we still lack a systematic understanding of their…

Recent work has embodied LLMs as agents, allowing them to access tools, perform actions, and interact with external content (e.g., emails or websites). However, external content introduces the risk of indirect prompt injection (IPI)…

Computation and Language · Computer Science 2024-08-06 Qiusi Zhan , Zhixiang Liang , Zifan Ying , Daniel Kang

Existing benchmarks for Large Language Model (LLM) agents focus on task completion under idealistic settings but overlook reliability in real-world, user-facing applications. In domains, such as in-car voice assistants, users often issue…

Artificial Intelligence · Computer Science 2026-01-30 Johannes Kirmayr , Lukas Stappen , Elisabeth André

Large Language Models (LLMs) and Multi-Agent LLMs (MALLMs) introduce non-determinism unlike traditional or machine learning software, requiring new approaches to verifying correctness beyond simple output comparisons or statistical accuracy…

Software Engineering · Computer Science 2025-10-22 Felix Dobslaw , Robert Feldt , Juyeon Yoon , Shin Yoo

Current test-time scaling (TTS) techniques enhance large language model (LLM) performance by allocating additional computation at inference time, yet they remain insufficient for agentic settings, where actions directly interact with…

Computation and Language · Computer Science 2026-02-04 Xingshan Zeng , Lingzhi Wang , Weiwen Liu , Liangyou Li , Yasheng Wang , Lifeng Shang , Xin Jiang , Qun Liu

Recent advances in Language Model (LM) agents and tool use, exemplified by applications like ChatGPT Plugins, enable a rich set of capabilities but also amplify potential risks - such as leaking private data or causing financial losses.…

Artificial Intelligence · Computer Science 2024-05-20 Yangjun Ruan , Honghua Dong , Andrew Wang , Silviu Pitis , Yongchao Zhou , Jimmy Ba , Yann Dubois , Chris J. Maddison , Tatsunori Hashimoto

The potential of Large Language Model (LLM) as agents has been widely acknowledged recently. Thus, there is an urgent need to quantitatively \textit{evaluate LLMs as agents} on challenging tasks in interactive environments. We present…

We present, to our knowledge, the most comprehensive cross-model evaluation of LLM agents on offensive cybersecurity tasks, benchmarking 10 frontier models from 7 providers on all 200 challenges of the NYU CTF Bench. Building on the…

Cryptography and Security · Computer Science 2026-04-21 Tyler H. Merves , Michael H. Conaway , Joseph M. Escobar , Hakan T. Otal , Unal Tatar

LLM-based tools are automating more software development tasks at a rapid pace, but there is no rigorous way to evaluate how different architectural choices -- prompts, skills, tools, multi-agent setups -- materially affect both capability…

Software Engineering · Computer Science 2026-02-10 Micah Villmow

Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from executing a single buggy line of code to taking full control of the target. However, existing LLM security benchmarks treat a crash as…

Cryptography and Security · Computer Science 2026-05-15 Seunghyun Lee , David Brumley

With the rise of large language models (LLMs), researchers are increasingly exploring their applications in var ious vertical domains, such as software engineering. LLMs have achieved remarkable success in areas including code generation…

Software Engineering · Computer Science 2025-04-15 Haolin Jin , Linghan Huang , Haipeng Cai , Jun Yan , Bo Li , Huaming Chen

Large language model (LLM) agents perform strongly on short- and mid-horizon tasks, but often break down on long-horizon tasks that require extended, interdependent action sequences. Despite rapid progress in agentic systems, these…

Artificial Intelligence · Computer Science 2026-04-15 Xinyu Jessica Wang , Haoyue Bai , Yiyou Sun , Haorui Wang , Shuibai Zhang , Wenjie Hu , Mya Schroder , Bilge Mutlu , Dawn Song , Robert D Nowak

Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tackle compounding real-world problems that require a diverse…

Artificial Intelligence · Computer Science 2025-11-04 Hanwen Xu , Xuyao Huang , Yuzhe Liu , Kai Yu , Zhijie Deng

The growing dependence on mobile phones and their apps has made multi-user interactive features, like chat calls, live streaming, and video conferencing, indispensable for bridging the gaps in social connectivity caused by physical and…

Software Engineering · Computer Science 2025-09-17 Sidong Feng , Changhao Du , Huaxiao Liu , Qingnan Wang , Zhengwei Lv , Mengfei Wang , Chunyang Chen

Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning…

Artificial Intelligence · Computer Science 2025-10-01 Ruolin Chen , Yinqian Sun , Jihang Wang , Mingyang Lv , Qian Zhang , Yi Zeng