English
Related papers

Related papers: STARS: Skill-Triggered Audit for Request-Condition…

200 papers

In a previous study [Jo, 2026], STAR reasoning (Situation, Task, Action, Result) raised car wash problem accuracy from 0% to 85% on Claude Sonnet 4.5, and to 100% with additional prompt layers. This follow-up asks: does STAR maintain its…

Artificial Intelligence · Computer Science 2026-03-17 Heejin Jo

Creating agents that can interact naturally with humans is a common goal in artificial intelligence (AI) research. However, evaluating these interactions is challenging: collecting online human-agent interactions is slow and expensive, yet…

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

Early identification of security issues in software development is vital to minimize their unanticipated impacts. Code review is a widely used manual analysis method that aims to uncover security issues along with other coding issues in…

Software Engineering · Computer Science 2024-07-18 Wachiraphan Charoenwet , Patanamon Thongtanunam , Van-Thuan Pham , Christoph Treude

Reasoning methods that adaptively allocate test-time compute have advanced LLM performance on easy to verify domains such as math and code. In this work, we study how to utilize this approach to train models that exhibit a degree of…

Machine Learning · Computer Science 2025-10-28 Taeyoun Kim , Fahim Tajwar , Aditi Raghunathan , Aviral Kumar

Safe reinforcement learning has traditionally relied on predefined constraint functions to ensure safety in complex real-world tasks, such as autonomous driving. However, defining these functions accurately for varied tasks is a persistent…

Machine Learning · Computer Science 2025-01-31 Se-Wook Yoo , Seung-Woo Seo

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious…

Cryptography and Security · Computer Science 2026-04-08 Zenghao Duan , Yuxin Tian , Zhiyi Yin , Liang Pang , Jingcheng Deng , Zihao Wei , Shicheng Xu , Yuyao Ge , Xueqi Cheng

We present STAR: a novel system aimed at solving the complex issue of "p-hacking" and false discoveries in scientific studies. STAR provides a concrete way for ensuring the application of false discovery control procedures in hypothesis…

Cryptography and Security · Computer Science 2019-10-24 Sacha Servan-Schreiber , Olga Ohrimenko , Tim Kraska , Emanuel Zgraggen

Credit risk default prediction remains a cornerstone of risk management in the financial industry. The task involves estimating the likelihood that a borrower will fail to meet debt obligations, an objective critical for lending decisions,…

Machine Learning · Computer Science 2026-04-21 Swattik Maiti , Ritik Pratap Singh , Fardina Fathmiul Alam

Self-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition. However, we show that, unlike contrastive learning approaches, they do not produce…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Soroush Mehraban , Mohammad Javad Rajabi , Andrea Iaboni , Babak Taati

Despite universal GenAI adoption, students cannot distinguish task performance from actual learning and lack skills to leverage AI for learning, leading to worse exam performance when AI use remains unreflective. Yet few interventions…

Human-Computer Interaction · Computer Science 2026-02-19 Ruiwei Xiao , Runlong Ye , Xinying Hou , Jessica Wen , Harsh Kumar , Michael Liut , John Stamper

While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation behaviors in real time and proactively intervening before…

Computation and Language · Computer Science 2026-01-16 Yutao Mou , Zhangchi Xue , Lijun Li , Peiyang Liu , Shikun Zhang , Wei Ye , Jing Shao

Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved through prompt engineering or by aligning the task LLM itself,…

Deep Reinforcement Learning (DRL) algorithms have been increasingly employed during the last decade to solve various decision-making problems such as autonomous driving and robotics. However, these algorithms have faced great challenges…

Software Engineering · Computer Science 2023-08-08 Amirhossein Zolfagharian , Manel Abdellatif , Lionel Briand , Mojtaba Bagherzadeh , Ramesh S

The temporal assumptions underpinning conventional Identity and Access Management collapse under agentic execution regimes. A sixty-second revocation window permits on the order of $6 \times 10^3$ unauthorized API calls at 100 ops/tick; at…

Multiagent Systems · Computer Science 2026-03-11 Vladyslav Parakhin

The rapid integration of AI into education has prioritized capability over trustworthiness, creating significant risks. Real-world deployments reveal that even advanced models are insufficient without extensive architectural scaffolding to…

Computers and Society · Computer Science 2026-01-13 Abu Syed

Context: Static Application Security Testing Tools (SASTTs) identify software vulnerabilities to support the security and reliability of software applications. Interestingly, several studies have suggested that alternative solutions may be…

Software Engineering · Computer Science 2024-03-15 Matteo Esposito , Valentina Falaschi , Davide Falessi

Skill ecosystems have emerged as an increasingly important layer in Large Language Model (LLM) agent systems, enabling reusable task packaging, public distribution, and community-driven capability sharing. However, despite their rapid…

Computation and Language · Computer Science 2026-04-16 Haichuan Hu , Ye Shang , Quanjun Zhang

Much work aims to explain a model's prediction on a static input. We consider explanations in a temporal setting where a stateful dynamical model produces a sequence of risk estimates given an input at each time step. When the estimated…

Machine Learning · Computer Science 2019-07-12 Michaela Hardt , Alvin Rajkomar , Gerardo Flores , Andrew Dai , Michael Howell , Greg Corrado , Claire Cui , Moritz Hardt

Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety risk through breadth-oriented evaluation across diverse tasks. However, real-world deployment often exposes a different class of…

Artificial Intelligence · Computer Science 2026-04-14 Keita Broadwater