English
Related papers

Related papers: ChainCaps: Composition-Safe Tool-Using Agents via …

200 papers

Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, not for interpretation by language models. For small models (4B-14B), this protocol…

Software Engineering · Computer Science 2026-05-07 Furkan Sakizli

As large language models (LLMs) become high-privilege agents in risk-sensitive settings, they introduce systemic threats beyond hallucination, where minor compliance errors can cause critical data leaks. However, existing benchmarks focus…

Computational Engineering, Finance, and Science · Computer Science 2026-02-16 Jinru Ding , Chao Ding , Yidong Jiang , Wenrao Pang , Boyi Xiao , Zhiqiang Liu , Jiayuan Chen , Yun Zhong , Tiantian Yuan , Junming Guan , Dawei Cheng , Jie Xu

Industrial asset operations workflows are latency-sensitive because a single user query may require coordination over sensor data, work orders, failure modes, forecasting tools, and domain-specific agents. We evaluate this problem on…

Artificial Intelligence · Computer Science 2026-05-21 Alimurtaza Mustafa Merchant , Krish Veera , Sajal Kumar Goyla , Shambhawi Bhure , Dhaval Patel , Kaoutar El Maghraoui

Recent Pwn2Own competitions have demonstrated the continued effectiveness of control hijacking attacks despite deployed countermeasures including stack canaries and ASLR. A powerful defense called Control flow Integrity (CFI) offers a…

Cryptography and Security · Computer Science 2014-08-08 Ali Jose Mashtizadeh , Andrea Bittau , David Mazieres , Dan Boneh

General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…

While pre-trained multimodal representations (e.g., CLIP) have shown impressive capabilities, they exhibit significant compositional vulnerabilities leading to counterintuitive judgments. We introduce Multimodal Adversarial Compositionality…

Computation and Language · Computer Science 2025-05-30 Jaewoo Ahn , Heeseung Yun , Dayoon Ko , Gunhee Kim

Unsafe memory accesses in programs written using popular programming languages like C/C++ have been among the leading causes for software vulnerability. Prior memory safety checkers such as SoftBound enforce memory spatial safety by…

Programming Languages · Computer Science 2019-07-10 Yurong Chen , Hongfa Xue , Tian Lan , Guru Venkataramani

Concurrency testing is essential to improve the reliability and security of multi-threaded programs. Dynamic analysis tools, such as TSan, depend on high-quality test drivers that reach critical shared-memory interactions at runtime.…

Software Engineering · Computer Science 2026-05-12 Yuandao Cai , Shuhao Fu , Wensheng Tang , Cheng Wen , Shengchao Qin , Charles Zhang

Coding agents powered by large language models are becoming central modules of modern IDEs, helping users perform complex tasks by invoking tools. While powerful, tool invocation opens a substantial attack surface. Prior work has…

Cryptography and Security · Computer Science 2026-01-06 Yuchong Xie , Mingyu Luo , Zesen Liu , Zhixiang Zhang , Kaikai Zhang , Yu Liu , Zongjie Li , Ping Chen , Shuai Wang , Dongdong She

Agentic RAG systems that equip language models with dozens to hundreds of tool definitions face a critical resource conflict: tool schemas consume the same context window needed for retrieval-augmented generation. We present the first…

Software Engineering · Computer Science 2026-05-27 Furkan Sakizli

Real-world tool-using agents operate over long-horizon workflows with recurring structure and diverse demands, where effective behavior requires not only invoking atomic tools but also abstracting, and reusing higher-level tool…

As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability (knowing what they do not know, detecting errors, seeking clarification) under adversarial pressure is a critical safety…

Artificial Intelligence · Computer Science 2026-05-15 Rahul Kumar

We propose a Capabilities-based approach for building long-lived, complex systems that have lengthy development cycles. User needs and technology evolve during these extended development periods, and thereby, inhibit a fixed…

Software Engineering · Computer Science 2007-05-23 Ramya Ravichandar , James D. Arthur , Shawn A. Bohner

Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. Existing methods employ one single LLM-based agent to iteratively select and execute tools, thereafter incorporating execution…

Computation and Language · Computer Science 2024-06-25 Zhengliang Shi , Shen Gao , Xiuyi Chen , Yue Feng , Lingyong Yan , Haibo Shi , Dawei Yin , Pengjie Ren , Suzan Verberne , Zhaochun Ren

LLM agents increasingly act by writing code, yet a split persists between the runtime that drives the agent and the code the model writes. The runtime owns the loop, context, and control flow, and the model has little say over any of them.…

Artificial Intelligence · Computer Science 2026-05-28 Yaoyu Zhao , Yichen Xu , Oliver Bračevac , Cao Nguyen Pham , Frank Zhengqing Wu , Martin Odersky

Information flow analysis is a powerful technique for reasoning about the sensitive information exposed by a program during its execution. While past work has proposed information theoretic metrics (e.g., Shannon entropy, min-entropy,…

Cryptography and Security · Computer Science 2010-09-22 Ji Zhu , Mudhakar Srivatsa

Traditional threat modeling occurs during design, but cloud deployments introduce unanticipated threats, especially multi-stage attacks chaining vulnerabilities across trust boundaries. Existing security tools analyze components in…

Cryptography and Security · Computer Science 2026-03-25 Nicholas Pecka , Lotfi Ben Othmane , Bharat Bhargava , Renee Bryce

Integrated Circuits (ICs) are the target of diverse attacks during their lifetime. Fabrication-time attacks, such as the insertion of Hardware Trojans, can give an adversary access to privileged data and/or the means to corrupt the IC's…

Cryptography and Security · Computer Science 2023-08-22 Mohammad Eslami , Tiago Perez , Samuel Pagliarini

The standard operational semantics of the sequential composition operator gives rise to unbounded branching and forgetfulness when transparent process expressions are put in sequence. Due to transparency, the correspondence between…

Logic in Computer Science · Computer Science 2017-09-11 Jos Baeten , Bas Luttik , Fei Yang

While decoupled control schemes for legged mobile manipulators have shown robustness, learning holistic whole-body control policies for tracking global end-effector poses remains fragile against Out-of-Distribution (OOD) inputs induced by…

Robotics · Computer Science 2026-04-10 Ziyang Cheng , Haoyu Wei , Hang Yin , Xiuwei Xu , Bingyao Yu , Jie Zhou , Jiwen Lu