English
Related papers

Related papers: Beyond Task Completion: Revealing Corrupt Success …

200 papers

Hallucinations pose critical risks for large language model (LLM)-based agents, often manifesting as hallucinative actions resulting from fabricated or misinterpreted information within the cognitive context. While recent studies have…

Artificial Intelligence · Computer Science 2025-07-29 Weichen Zhang , Yiyou Sun , Pohao Huang , Jiayue Pu , Heyue Lin , Dawn Song

Despite rapid development, large language models (LLMs) still encounter challenges in multi-turn decision-making tasks (i.e., agent tasks) like web shopping and browser navigation, which require making a sequence of intelligent decisions…

Computation and Language · Computer Science 2025-11-12 Zhiheng Xi , Chenyang Liao , Guanyu Li , Yajie Yang , Wenxiang Chen , Zhihao Zhang , Binghai Wang , Senjie Jin , Yuhao Zhou , Jian Guan , Wei Wu , Tao Ji , Tao Gui , Qi Zhang , Xuanjing Huang

Large language model (LLM)-based agents exhibit strong step-by-step reasoning capabilities over short horizons, yet often fail to sustain coherent behavior over long planning horizons. We argue that this failure reflects a fundamental…

Artificial Intelligence · Computer Science 2026-02-02 Zehong Wang , Fang Wu , Hongru Wang , Xiangru Tang , Bolian Li , Zhenfei Yin , Yijun Ma , Yiyang Li , Weixiang Sun , Xiusi Chen , Yanfang Ye

Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…

Machine Learning · Computer Science 2025-07-11 Ram Potham

Public agencies are beginning to consider large language models (LLMs) as decision-support tools for grant evaluation. This creates a practical governance problem: the model and scoring rubric should not be exposed in a way that allows…

Cryptography and Security · Computer Science 2026-04-29 Kemal Bicakci

Language Model (LM) agents have demonstrated remarkable capabilities in solving tasks that require multiple interactions with the environment. However, they remain vulnerable in environments where a single error often leads to irrecoverable…

Artificial Intelligence · Computer Science 2026-02-24 Jongwon Jeong , Jungtaek Kim , Kangwook Lee

LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation…

Artificial Intelligence · Computer Science 2026-03-13 Yonas Atinafu , Robin Cohen

Multi-agent Large Language Model (LLM) systems create privacy risks that current benchmarks cannot measure. When agents coordinate on tasks, sensitive data passes through inter-agent messages, shared memory, and tool arguments, all pathways…

Artificial Intelligence · Computer Science 2026-03-31 Faouzi El Yagoubi , Godwin Badu-Marfo , Ranwa Al Mallah

The rise of Agentic applications and automation in the Voice AI industry has led to an increased reliance on Large Language Models (LLMs) to navigate graph-based logic workflows composed of nodes and edges. However, existing methods face…

Artificial Intelligence · Computer Science 2025-03-11 Alex Casella , Wayne Wang

As the focus in LLM-based coding shifts from static single-step code generation to multi-step agentic interaction with tools and environments, understanding which tasks will challenge agents and why becomes increasingly difficult. This is…

Artificial Intelligence · Computer Science 2026-04-02 Chris Ge , Daria Kryvosheieva , Daniel Fried , Uzay Girit , Kaivalya Hariharan

Peer review is fundamental to the integrity and advancement of scientific publication. Traditional methods of peer review analyses often rely on exploration and statistics of existing peer review data, which do not adequately address the…

Computation and Language · Computer Science 2026-05-12 Yiqiao Jin , Qinlin Zhao , Yiyang Wang , Hao Chen , Kaijie Zhu , Yijia Xiao , Jindong Wang

Repository-level issue resolution benchmarks have become a standard testbed for evaluating LLM-based agents, yet success is still predominantly measured by test pass rates. In practice, however, acceptable patches must also comply with…

Software Engineering · Computer Science 2026-04-08 Kai Yu , Zhenhao Zhou , Junhao Zeng , Ying Wang , Xueying Du , Zhiqiang Yuan , Junwei Liu , Ziyu Zhou , Yujia Wang , Chong Wang , Xin Peng

Web agents powered by large language models (LLMs) can autonomously perform complex, multistep tasks in dynamic web environments. However, current evaluations mostly focus on the overall success while overlooking intermediate errors. This…

Artificial Intelligence · Computer Science 2025-09-19 Daniel Röder , Akhil Juneja , Roland Roller , Sven Schmeier

Multi-Agent LLM Systems (MAS) have been adopted to automate complex human workflows by breaking down tasks into subtasks. However, due to the non-deterministic behavior of LLM agents and the intricate interactions between agents, MAS…

Software Engineering · Computer Science 2026-04-08 Mingxuan Hui , Xinyue Li , Lu Wang , Chengcheng Wan , Yifan Wang , Yimian Wang , Feiyue Song , Beining Shi , Yixi Li , Yaxiao Li

Large language models (LLMs) often achieve strong performance on reasoning benchmarks, but final-answer accuracy alone does not show whether they faithfully execute the procedure specified in a prompt. We introduce a controlled diagnostic…

Computation and Language · Computer Science 2026-05-26 Sailesh Panda , Pritam Kadasi , Abhishek Upperwal , Mayank Singh

The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluation of these systems is hampered by significant challenges,…

Software Engineering · Computer Science 2025-11-07 Zhengran Zeng , Yixin Li , Rui Xie , Wei Ye , Shikun Zhang

As large language models (LLMs) become high-privilege agents in risk-sensitive settings, they introduce systemic threats beyond hallucination, where minor compliance errors can cause critical data leaks. However, existing benchmarks focus…

Computational Engineering, Finance, and Science · Computer Science 2026-02-16 Jinru Ding , Chao Ding , Yidong Jiang , Wenrao Pang , Boyi Xiao , Zhiqiang Liu , Jiayuan Chen , Yun Zhong , Tiantian Yuan , Junming Guan , Dawei Cheng , Jie Xu

As agentic AI systems increasingly operate autonomously, establishing trust through verifiable evaluation becomes critical. Yet existing benchmarks lack the transparency and auditability needed to assess whether agents behave reliably. We…

Computation and Language · Computer Science 2025-12-02 Hyunjun Kim , Sooyoung Ryu

Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution…

Software Engineering · Computer Science 2026-05-11 Cheonsu Jeong , Younggun Shin

A growing body of work explores how Large Language Models (LLMs) can be embedded in trading systems as agents that perceive market information, retrieve context, reason about decisions, emit tradable actions, and adapt under market…

Artificial Intelligence · Computer Science 2026-05-20 Yihan Xia , Panpan You , Taotao Wang , Fang Liu , Han Qi , Xiaoxiao Wu , Shengli Zhang