English
Related papers

Related papers: CP-Agent: A Calibrated Risk-Controlled Agent for F…

200 papers

Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to…

Cryptography and Security · Computer Science 2025-06-12 Li Changjiang , Liang Jiacheng , Cao Bochuan , Chen Jinghui , Wang Ting

Large Language Models (LLMs) have significantly advanced the fact-checking studies. However, existing automated fact-checking evaluation methods rely on static datasets and classification metrics, which fail to automatically evaluate the…

Computation and Language · Computer Science 2025-03-04 Hongzhan Lin , Yang Deng , Yuxuan Gu , Wenxuan Zhang , Jing Ma , See-Kiong Ng , Tat-Seng Chua

Recent advances in large language models (LLMs) have significantly improved multi-hop question answering (QA) through direct Chain-of-Thought (CoT) reasoning. However, the irreversible nature of CoT leads to error accumulation, making it…

Artificial Intelligence · Computer Science 2025-05-30 Xinjie Zhao , Fan Gao , Xingyu Song , Yingjian Chen , Rui Yang , Yanran Fu , Yuyang Wang , Yusuke Iwasawa , Yutaka Matsuo , Irene Li

When multi-agent systems (MAS) fail, identifying where the decisive error occurred is the first step for automated recovery to an earlier state. Error attribution remains a fundamental challenge due to the long interaction traces that large…

Machine Learning · Computer Science 2026-05-11 Naihe Feng , Yi Sui , Shiyi Hou , Ga Wu , Jesse C. Cresswell

The integration of experimental technologies with large language models (LLMs) is transforming scientific research. It positions AI as a versatile research assistant rather than a mere problem-solving tool. In the field of power systems,…

Computation and Language · Computer Science 2025-05-20 Mengshuo Jia , Zeyu Cui , Gabriela Hug

Conformal prediction (CP) is a wrapper around traditional machine learning models, giving coverage guarantees under the sole assumption of exchangeability; in classification problems, for a chosen significance level $\varepsilon$, CP…

Machine Learning · Computer Science 2023-02-23 Javier Abad , Umang Bhatt , Adrian Weller , Giovanni Cherubin

Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture…

Artificial Intelligence · Computer Science 2026-04-24 Keyu Li , Junhao Shi , Yang Xiao , Mohan Jiang , Jie Sun , Yunze Wu , Dayuan Fu , Shijie Xia , Xiaojie Cai , Tianze Xu , Weiye Si , Wenjie Li , Dequan Wang , Pengfei Liu

Large language models (LLMs) show the promise in supporting scientific research implementation, yet their ability to generate correct and executable code remains limited. Existing works largely adopt one-shot settings, ignoring the…

Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production-grade software requires strict adherence to structural constraints, such as architectural…

Software Engineering · Computer Science 2026-05-08 Francesco Dente , Dario Satriani , Paolo Papotti

The remarkable capabilities of Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks, but their escalating costs threaten scalability and accessibility. This work presents the first…

Long-horizon language agents can make many plausible local tool calls yet fail to persist until a requested count is actually complete. We study this gap as Quantitative Goal Persistence (QGP): whether an agent keeps working until an…

Machine Learning · Computer Science 2026-05-25 Yuandao Cai , Yuzhang Zhu , Liyou Gao , Wensheng Tang , Shengchao Qin

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

Large Language Model agents are increasingly augmented with agent skills. Current evaluation methods for skills remain limited. Most deployed benchmarks report only pass rate before and after a skill is attached, treating the skill as a…

Artificial Intelligence · Computer Science 2026-05-13 Xiaolin Zhou , Jinbo Liu , Li Li , Ryan A. Rossi , Xiyang Hu

Large Language Models (LLMs) have substantially influenced various software engineering tasks. Indeed, in the case of software refactoring, traditional LLMs have shown the ability to reduce development time and enhance code quality.…

Software Engineering · Computer Science 2026-03-06 Khouloud Oueslati , Maxime Lamothe , Foutse Khomh

Large language model (LLM) self-correction -- the ability to detect and fix errors in generated outputs -- remains largely ad hoc, relying on generic prompts such as "please reconsider your answer" without systematic error analysis or…

Artificial Intelligence · Computer Science 2026-05-19 Yuning Wu , Yingmin Liu , Yang Shu

Agents based on large language models leverage tools to modify environments, revolutionizing how AI interacts with the physical world. Unlike traditional NLP tasks that rely solely on historical dialogue for responses, these agents must…

Artificial Intelligence · Computer Science 2025-06-30 Peijie Yu , Yifan Yang , Jinjian Li , Zelong Zhang , Haorui Wang , Xiao Feng , Feng Zhang

Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks…

Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycle. However, existing benchmarks largely rely on synthetic…

Machine Learning · Computer Science 2025-10-23 Hwiwon Lee , Ziqi Zhang , Hanxiao Lu , Lingming Zhang

Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to…

Artificial Intelligence · Computer Science 2026-04-29 Kaixuan Fan , Kaituo Feng , Manyuan Zhang , Tianshuo Peng , Zhixun Li , Yilei Jiang , Shuang Chen , Peng Pei , Xunliang Cai , Xiangyu Yue

Large language models are increasingly deployed as autonomous coding agents and have achieved remarkably strong performance on software engineering benchmarks. However, it is unclear whether such success transfers to computational…

‹ Prev 1 3 4 5 6 7 10 Next ›