中文
相关论文

相关论文: LiveFMBench: Unveiling the Power and Limits of Age…

200 篇论文

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…

Evaluating Large Language Models (LLMs) on repository-level feature implementation is a critical frontier in software engineering. However, establishing a benchmark that faithfully mirrors realistic development scenarios remains a…

计算与语言 · 计算机科学 2026-02-19 Haorui Chen , Chengze Li , Jia Li

Large Language Models (LLMs) are increasingly being used to automate programming tasks. Yet, LLMs' capabilities in reasoning about program semantics are still inadequately studied, leaving significant potential for further exploration. This…

编程语言 · 计算机科学 2025-05-30 Thanh Le-Cong , Bach Le , Toby Murray

Early-stage specifications of safety-critical systems are typically expressed in natural language, making it difficult to derive formal properties suitable for verification and needed to guarantee safety. While recent Large Language Model…

软件工程 · 计算机科学 2026-04-21 Alberto Tagliaferro , Bruno Guindani , Livia Lestingi , Matteo Rossi

Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current…

Post-training compression reduces the computational and memory costs of large language models (LLMs), enabling resource-efficient deployment. However, existing compression benchmarks only focus on language modeling (e.g., perplexity) and…

机器学习 · 计算机科学 2025-06-03 Peijie Dong , Zhenheng Tang , Xiang Liu , Lujun Li , Xiaowen Chu , Bo Li

Formal specification generation has recently drawn attention in software engineering as a way to improve program correctness without requiring manual annotations. Large Language Models (LLMs) have shown promise in this area, but early…

软件工程 · 计算机科学 2026-04-07 Ragib Shahariar Ayon , Shibbir Ahmed

The emergence of agentic recommender systems powered by Large Language Models (LLMs) represents a paradigm shift in personalized recommendations, leveraging LLMs' advanced reasoning and role-playing capabilities to enable autonomous,…

信息检索 · 计算机科学 2025-05-29 Yu Shang , Peijie Liu , Yuwei Yan , Zijing Wu , Leheng Sheng , Yuanqing Yu , Chumeng Jiang , An Zhang , Fengli Xu , Yu Wang , Min Zhang , Yong Li

Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…

人工智能 · 计算机科学 2025-03-12 Dhruv Gautam , Spandan Garg , Jinu Jang , Neel Sundaresan , Roshanak Zilouchian Moghaddam

Large Language Models (LLMs) with agentic web search capabilities show strong potential for tasks requiring real-time information access and complex fact retrieval, yet evaluating such systems remains challenging. We introduce \bench, a…

信息检索 · 计算机科学 2026-02-17 Yunfan Zhang , Kathleen McKeown , Smaranda Muresan

Large Language Models (LLMs) are driving a shift towards intent-driven development, where agents build complete software from scratch. However, existing benchmarks fail to assess this 0-to-1 generation capability due to two limitations:…

软件工程 · 计算机科学 2026-04-09 Ruida Hu , Xinchen Wang , Chao Peng , Cuiyun Gao , David Lo

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…

Formal verification of memory-manipulating programs critically depends on precise function specifications that capture memory states written by experts. This requirement has become a major bottleneck as large language models (LLMs)…

软件工程 · 计算机科学 2026-03-17 Liao Zhang , Tong Chen , Xiwei Wu , Qi Liu , Xiyu Zhai , Xinqi Wang , Qinxiang Cao

Large Language Models (LLMs) have demonstrated advanced capabilities in real-world agentic applications. Growing research efforts aim to develop LLM-based agents to address practical demands, introducing a new challenge: agentic scenarios…

人工智能 · 计算机科学 2025-05-23 Yunjia Qi , Hao Peng , Xiaozhi Wang , Amy Xin , Youfeng Liu , Bin Xu , Lei Hou , Juanzi Li

This work is concerned with the generation of formal specifications from code, using Large Language Models (LLMs) in combination with symbolic methods. Concretely, in our study, the programming language is C, the specification language is…

软件工程 · 计算机科学 2025-05-01 George Granberry , Wolfgang Ahrendt , Moa Johansson

Recent advances in large language models have enabled LLM-based agents to achieve strong performance on a variety of benchmarks. However, their performance in real-world deployments often that observed on benchmark settings, especially in…

Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing…

人工智能 · 计算机科学 2025-10-14 Jiateng Liu , Zhenhailong Wang , Xiaojiang Huang , Yingjie Li , Xing Fan , Xiang Li , Chenlei Guo , Ruhi Sarikaya , Heng Ji

Large language models (LLMs) are increasingly deployed as agents, expected to decompose goals, invoke tools, and verify results in dynamic environments. Realizing these capabilities requires access to agentic data-structured interaction…

人工智能 · 计算机科学 2025-10-22 Abhigya Verma , Seganrasan Subramanian , Nandhakumar Kandasamy , Naman Gupta

The integration of Large Language Models (LLMs) into software engineering has driven a transition from traditional rule-based systems to autonomous agentic systems capable of solving complex problems. However, systematic progress is…

Formal specifications are crucial for building verifiable and dependable software systems, yet generating accurate and verifiable specifications for real-world C programs remains challenging. This paper presents an empirical evaluation of…

软件工程 · 计算机科学 2026-04-15 Arshad Beg , Diarmuid O'Donoghue , Rosemary Monahan
‹ 上一页 1 2 3 10 下一页 ›