English
Related papers

Related papers: SPECA: Specification-to-Checklist Agentic Auditing…

200 papers

Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-hoc. Disconnected from the active execution loop, such assessments identify errors that…

Artificial Intelligence · Computer Science 2026-05-01 Anh Ta , Junjie Zhu , Shahin Shayandeh

We address the challenge of multi-agent cooperation, where agents achieve a common goal by cooperating with decentralized agents under complex partial observations. Existing cooperative agent systems often struggle with efficiently…

Artificial Intelligence · Computer Science 2024-12-19 SeungWon Seo , SeongRae Noh , Junhyeok Lee , SooBin Lim , Won Hee Lee , HyeongYeop Kang

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 systems increasingly expose explicit workflow structure: agents, tools, tool-access rules, restrictions, and delegation paths. Existing evaluations rely largely on end-to-end task success, benchmark scores, final-response…

Software Engineering · Computer Science 2026-05-27 Nafiseh Kahani , Mojtaba Bagherzadeh

We ask whether agentic AI systems built for software engineering transfer to realistic hardware engineering. Existing hardware LLM benchmarks isolate sub-tasks but none jointly requires repository navigation, hierarchy-aware localization,…

Hardware Architecture · Computer Science 2026-05-18 Qingyun Zou , Feng Yu , Hongshi Tan , Bingsheng He , WengFai Wong

Agent applications are increasingly adopted to automate workflows across diverse tasks. However, due to the heterogeneous domains they operate in, it is challenging to create a scalable evaluation framework. Prior works each employ their…

Artificial Intelligence · Computer Science 2026-03-17 Penny Chong , Harshavardhan Abichandani , Jiyuan Shen , Atin Ghosh , Min Pyae Moe , Yifan Mai , Daniel Dahlmeier

AI-based systems, currently driven largely by LLMs and tool-using agentic harnesses, are increasingly discussed as a possible threat to software engineering. Foundation models get stronger, agents can plan and act across multiple steps, and…

Software Engineering · Computer Science 2026-04-24 Robert Feldt , Per Lenberg , Julian Frattini , Dhasarathy Parthasarathy

Failure Mode, Effects and Criticality Analysis (FMECA) is one of the safety analysis methods recommended by most of the international standards. The classical FMECA is made in a form of a table filled in either manually or by using safety…

Artificial Intelligence · Computer Science 2024-03-26 Önder Gürcan , Nataliya Yakymets , Sara Tucci-Piergiovanni , Ansgar Radermacher

System-Theoretic Process Analysis (STPA) is a recommended method for analysing complex systems, capable of identifying thousands of safety requirements often missed by traditional techniques such as Failure Mode and Effects Analysis (FMEA)…

Software Engineering · Computer Science 2025-08-26 Shufeng Chen , Halima El Badaoui , Mariat James Elizebeth , Takuya Nakashima , Siddartha Khastgir , Paul Jennings

Large language model (LLM)-powered agents have demonstrated strong capabilities in automating software engineering tasks such as static bug fixing. However, in the real world, the development of mature software is typically predicated on…

Software Engineering · Computer Science 2026-04-02 Jialong Chen , Xander Xu , Hu Wei , Chuan Chen , Bing Zhao

Large language models have advanced software engineering automation, yet resolving real-world software issues remains difficult because it requires repository-level reasoning, accurate diagnostics, and strong verification signals. Existing…

Software Engineering · Computer Science 2025-11-21 KeFan Li , Mengfei Wang , Hengzhi Zhang , Zhichao Li , Yuan Yuan , Mu Li , Xiang Gao , Hailong Sun , Chunming Hu , Weifeng Lv

Automated issue solving seeks to autonomously identify and repair defective code snippets across an entire codebase. SWE-Bench has emerged as the most widely adopted benchmark for evaluating progress in this area. While LLM-based agentic…

Software Engineering · Computer Science 2025-09-18 Simiao Liu , Fang Liu , Liehao Li , Xin Tan , Yinghao Zhu , Xiaoli Lian , Li Zhang

The rapid advancement of Large Language Models (LLMs) in software engineering has revealed critical limitations in existing benchmarks, particularly the widely used SWE-bench dataset. Recent studies have uncovered severe data contamination…

One of the most challenging tasks in software specifications engineering for a multi-agent system is to ensure correctness. As these systems have high concurrency, often have dynamic environments, the formal specification and verification…

Software Engineering · Computer Science 2015-01-22 Nadeem Akhtar

As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests…

Software Engineering · Computer Science 2026-05-21 Bingchen Zhao , Dhruv Srikanth , Yuxiang Wu , Zhengyao Jiang

Reliable evaluation is essential for developing and deploying large language models, yet in practice it often requires substantial manual effort: practitioners must identify appropriate benchmarks, reproduce heterogeneous evaluation…

Computation and Language · Computer Science 2026-03-11 Chengyu Shen , Yanheng Hou , Minghui Pan , Runming He , Zhen Hao Wong , Meiyi Qiang , Zhou Liu , Hao Liang , Peichao Lai , Zeang Sheng , Wentao Zhang

Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, and the risks grow dramatically as agents engage in multi-turn conversations and scale…

Artificial Intelligence · Computer Science 2026-05-05 Majed El Helou , Benjamin Ryder , Chiara Troiani , Jean Diaconu , Hervé Muyal , Marcelo Yannuzzi

Ethereum smart contracts are an innovation built on top of the blockchain technology, which provides a platform for automatically executing contracts in an anonymous, distributed, and trusted way. The problem is magnified by the fact that…

Cryptography and Security · Computer Science 2019-11-07 Jialiang Chang , Bo Gao , Hao Xiao , Jun Sun , Yan Cai , Zijiang Yang

Getting a real cybersecurity risk assessment for a small organization is expensive -- a NIST CSF-aligned engagement runs $15,000 on the low end, takes weeks, and depends on practitioners who are genuinely scarce. Most small companies skip…

Systems and Control · Electrical Eng. & Systems 2026-03-26 Ravish Gupta , Saket Kumar , Shreeya Sharma , Maulik Dang , Abhishek Aggarwal

As large language models become components of larger agentic systems, evaluation reliability becomes critical: unreliable sub-agents introduce brittleness into downstream system behavior. Yet current evaluation practice, reporting a single…

Artificial Intelligence · Computer Science 2025-12-09 Zairah Mustahsan , Abel Lim , Megna Anand , Saahil Jain , Bryan McCann