English
Related papers

Related papers: Near-Miss: Latent Policy Failure Detection in Agen…

200 papers

Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage performance remains scarce. Existing skill benchmarking efforts…

Computation and Language · Computer Science 2026-04-07 Yujian Liu , Jiabao Ji , Li An , Tommi Jaakkola , Yang Zhang , Shiyu Chang

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

Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations, leading to significant operational expense,…

Artificial Intelligence · Computer Science 2026-02-03 Sami Abuzakuk , Anne-Marie Kermarrec , Rishi Sharma , Rasmus Moorits Veski , Martijn de Vos

Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals to agentic systems. We propose a framework for evaluating goal-directedness that integrates…

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

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…

Cryptography and Security · Computer Science 2026-05-12 Wei Zhao , Zhe Li , Peixin Zhang , Jun Sun

Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this…

Machine Learning · Computer Science 2026-03-26 Bjarni Haukur Bjarnason , André Silva , Martin Monperrus

While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing…

Artificial Intelligence · Computer Science 2025-05-28 Heng Tan , Hua Yan , Yu Yang

Large Language Models (LLMs) have shown remarkable capabilities in tool calling and tool usage, but suffer from hallucinations where they choose incorrect tools, provide malformed parameters and exhibit 'tool bypass' behavior by performing…

Artificial Intelligence · Computer Science 2026-01-09 Kait Healy , Bharathi Srinivasan , Visakh Madathil , Jing Wu

Evaluating large language model (LLM)-based multi-agent systems remains a critical challenge, as these systems must exhibit reliable coordination, transparent decision-making, and verifiable performance across evolving tasks. Existing…

Artificial Intelligence · Computer Science 2026-01-21 YenTing Lee , Keerthi Koneru , Zahra Moslemi , Sheethal Kumar , Ramesh Radhakrishnan

LLM agents achieve 85-96% success on tasks where instructions fully specify the action, but drop to 29-53% when action feasibility depends on environmental state that the instruction does not mention. We argue that this gap reflects a…

Computation and Language · Computer Science 2026-05-29 Zixuan Wang , Dingming Li , Hongxing Li , Yanrui Miao , Shuo Chen , Yuchen Yan , Wenqi Zhang , Yongliang Shen , Weiming Lu , Jun Xiao , Yueting Zhuang

Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the…

Multiagent Systems · Computer Science 2026-05-12 Tianxiao Li , Yixing Ma , Haiquan Wen , Zhenglin Huang , Qianyu Zhou , Zeyu Fu , Guangliang Cheng

Agentic AI systems are increasingly being integrated into scientific workflows, yet their behavior under realistic conditions remains insufficiently understood. We evaluate CMBAgent across two workflow paradigms and eighteen astrophysical…

Artificial Intelligence · Computer Science 2026-04-29 Shivam Rawat , Lucie Flek

As benchmarks grow in complexity, many apparent agent failures are not failures of the agent at all - they are failures of the benchmark itself: broken specifications, implicit assumptions, and rigid evaluation scripts that penalize valid…

Computation and Language · Computer Science 2026-04-29 Xinming Tu , Tianze Wang , Yingzhou , Lu , Kexin Huang , Yuanhao Qu , Sara Mostafavi

As Large Language Models (LLMs) continue to be increasingly applied across various domains, their widespread adoption necessitates rigorous monitoring to prevent unintended negative consequences and ensure robustness. Furthermore, LLMs must…

Computation and Language · Computer Science 2025-07-09 Seshu Tirupathi , Dhaval Salwala , Elizabeth Daly , Inge Vejsbjerg

Agentic systems are modern software systems: they consist of orchestrated modules, expose interfaces, and are deployed in software pipelines. Unlike conventional programs, their execution, i.e., trajectories, is inherently stochastic and…

Software Engineering · Computer Science 2026-04-14 Shuyang Liu , Yang Chen , Rahul Krishna , Saurabh Sinha , Jatin Ganhotra , Reyhan Jabbarvand

Agentic workflows -- where multiple large language model (LLM) instances interact to solve tasks -- are increasingly built on feedback mechanisms, where one model evaluates and critiques another. Despite the promise of feedback-driven…

Artificial Intelligence · Computer Science 2025-06-05 Yifei Ming , Zixuan Ke , Xuan-Phi Nguyen , Jiayu Wang , Shafiq Joty

Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in critical settings. However, the majority of existing methodologies for identifying biases in…

Computation and Language · Computer Science 2025-02-04 Erica Coppolillo , Giuseppe Manco , Luca Maria Aiello

Failure attribution in LLM multi-agent systems-identifying the agent and step responsible for task failures-provides crucial clues for systems debugging but remains underexplored and labor-intensive. In this paper, we propose and formulate…

Multiagent Systems · Computer Science 2025-06-03 Shaokun Zhang , Ming Yin , Jieyu Zhang , Jiale Liu , Zhiguang Han , Jingyang Zhang , Beibin Li , Chi Wang , Huazheng Wang , Yiran Chen , Qingyun Wu

Robot behavior policies trained via imitation learning are prone to failure under conditions that deviate from their training data. Thus, algorithms that monitor learned policies at test time and provide early warnings of failure are…

Robotics · Computer Science 2024-11-01 Christopher Agia , Rohan Sinha , Jingyun Yang , Zi-ang Cao , Rika Antonova , Marco Pavone , Jeannette Bohg
‹ Prev 1 3 4 5 6 7 10 Next ›