English
Related papers

Related papers: Partial Evidence Bench: Benchmarking Authorization…

200 papers

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

Cryptography and Security · Computer Science 2026-05-27 Faruk Alpay , Taylan Alpay

LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, isolated, and short-horizon benchmarks that fail to capture…

Software Engineering · Computer Science 2026-05-28 Yipeng Ouyang , Xin Huang , Bingjie Liu , Zhongchun Zheng , Yuhao Gu , Xianwei Zhang

Autonomous web agents solve complex browsing tasks, yet existing benchmarks measure only whether an agent finishes a task, ignoring whether it does so safely or in a way enterprises can trust. To integrate these agents into critical…

Artificial Intelligence · Computer Science 2026-03-03 Ido Levy , Ben Wiesel , Sami Marreed , Alon Oved , Avi Yaeli , Segev Shlomov

Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or…

Artificial Intelligence · Computer Science 2026-05-29 Yibing Liu , Yangze Liu , Xiaolong Yin , Bin Wang , Chong Zhang , Hao Yin , Zhongyi Han

Interactive agent benchmarks face a tension between scalable construction and realistic workflow evaluation. Hand-authored tasks are expensive to extend and revise, while static prompt evaluation misses failures that only appear when agents…

Artificial Intelligence · Computer Science 2026-05-19 Yuxiang Lai , Peng Xia , Haonian Ji , Kaiwen Xiong , Kaide Zeng , Jiaqi Liu , Fang Wu , Jike Zhong , Zeyu Zheng , Cihang Xie , Huaxiu Yao

We present SIR-Bench, a benchmark of 794 test cases for evaluating autonomous security incident response agents that distinguishes genuine forensic investigation from alert parroting. Derived from 129 anonymized incident patterns with…

Cryptography and Security · Computer Science 2026-04-15 Daniel Begimher , Cristian Leo , Jack Huang , Pat Gaw , Bonan Zheng

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

Cryptography and Security · Computer Science 2025-06-02 Hanrong Zhang , Jingyuan Huang , Kai Mei , Yifei Yao , Zhenting Wang , Chenlu Zhan , Hongwei Wang , Yongfeng Zhang

While individual components of agentic architectures have been studied in isolation, there remains limited empirical understanding of how different design dimensions interact within complex multi-agent systems. This study aims to address…

Artificial Intelligence · Computer Science 2026-01-07 Tara Bogavelli , Roshnee Sharma , Hari Subramani

Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in \emph{over-refusal} of benign queries or \emph{unsafe compliance} with harmful ones. While existing…

Artificial Intelligence · Computer Science 2026-01-27 Zhihao Zhang , Liting Huang , Guanghao Wu , Preslav Nakov , Heng Ji , Usman Naseem

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…

Software Engineering · Computer Science 2026-02-12 Qixing Zhou , Jiacheng Zhang , Haiyang Wang , Rui Hao , Jiahe Wang , Minghao Han , Yuxue Yang , Shuzhe Wu , Feiyang Pan , Lue Fan , Dandan Tu , Zhaoxiang Zhang

Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…

Artificial Intelligence · Computer Science 2026-05-12 Royce Moon , Lav R. Varshney

Reasoning benchmarks such as the Abstraction and Reasoning Corpus (ARC) and ARC-AGI are widely used to assess progress in artificial intelligence and are often interpreted as probes of core, so-called ``fluid'' reasoning abilities. Despite…

Computation and Language · Computer Science 2026-01-12 Xinhe Wang , Jin Huang , Xingjian Zhang , Tianhao Wang , Jiaqi W. Ma

EVMbench, released by OpenAI, Paradigm, and OtterSec, is the first large-scale benchmark for AI agents on smart contract security. Its results -- agents detect up to 45.6% of vulnerabilities and exploit 72.2% of a curated subset -- have…

Cryptography and Security · Computer Science 2026-03-12 Chaoyuan Peng , Lei Wu , Yajin Zhou

While large language models have significantly accelerated scientific code generation, comprehensively evaluating the generated code remains a major challenge. Traditional benchmarks reduce evaluation to test-case matching, an approach…

Artificial Intelligence · Computer Science 2026-03-18 Hong Zhang , Barry Smith , Satish Balay , Le Chen , Murat Keceli , Lois Curfman McInnes , Junchao Zhang

Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluation remains dominated by task success metrics such as completion rate or manipulation…

Robotics · Computer Science 2026-04-14 Xue Qin , Simin Luan , John See , Cong Yang , Zhijun Li

This position paper provides a critical but constructive discussion of current practices in benchmarking and evaluative practices in the field of formal reasoning and automated theorem proving. We take the position that open code, open…

Artificial Intelligence · Computer Science 2025-07-08 Roozbeh Yousefzadeh , Xuenan Cao

Automatic Speech Recognition (ASR) in professional settings faces challenges that existing benchmarks underplay: dense domain terminology, formal register variation, and near-zero tolerance for critical entity errors. We present…

Computation and Language · Computer Science 2025-12-30 Deepak Babu Piskala

Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…

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