English
Related papers

Related papers: Sanity Checks for Agentic Data Science

200 papers

Agentic AI systems are increasingly being integrated into scientific workflows, yet their behavior under realistic conditions remains insufficiently understood. We evaluate CMBAgent across two workflow paradigms and eighteen astrophysical…

Artificial Intelligence · Computer Science 2026-04-29 Shivam Rawat , Lucie Flek

Autonomous driving systems (ADS) have been an active area of research, with the potential to deliver significant benefits to society. However, before large-scale deployment on public roads, extensive testing is necessary to validate their…

Software Engineering · Computer Science 2025-08-28 Qunying Song , He Ye , Mark Harman , Federica Sarro

Autonomous driving systems (ADSs) rely on real-time sensor data, such as cameras and LiDARs, for time-critical decisions using deep neural networks. The accuracy of these decisions is crucial for the widespread adoption of ADSs, as errors…

Software Engineering · Computer Science 2025-10-15 Tri Minh Triet Pham , Bo Yang , Jinqiu Yang

Autonomous coding agents are increasingly deployed as AI teammates in modern software engineering, independently authoring pull requests (PRs) that modify production code at scale. This study aims to systematically characterize how…

Cryptography and Security · Computer Science 2026-01-05 Mohammed Latif Siddiq , Xinye Zhao , Vinicius Carvalho Lopes , Beatrice Casey , Joanna C. S. Santos

Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…

How many scenarios are sufficient to validate the safe Operational Design Domain (ODD) of an Automated Driving System (ADS) equipped vehicle? Is a more significant number of sampled scenarios guaranteeing a more accurate safety assessment…

Robotics · Computer Science 2021-11-16 Bowen Weng , Linda Capito , Umit Ozguner , Keith Redmill

Artificial intelligence (AI) is reshaping scientific discovery, evolving from specialized computational tools into autonomous research partners. We position Agentic Science as a pivotal stage within the broader AI for Science paradigm,…

Agentic search such as Deep Research systems-where agents autonomously browse the web, synthesize information, and return comprehensive citation-backed answers-represents a major shift in how users interact with web-scale information. While…

Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems often suffer from a critical limitation in practice: agents fail to recognize their…

Artificial Intelligence · Computer Science 2026-05-29 Yunbo Tang , Chengyi Yang , Shiyu Liu , Zhishang Xiang , Zerui Chen , Qinggang Zhang , Jinsong Su

Current code generation benchmarks focus primarily on functional correctness while overlooking two critical aspects of real-world programming: algorithmic efficiency and code quality. We introduce COMPASS (COdility's Multi-dimensional…

Software Engineering · Computer Science 2025-08-20 James Meaden , Michał Jarosz , Piotr Jodłowski , Grigori Melnik

The past decade has seen a substantial rise in the amount of mis- and disinformation online, from targeted disinformation campaigns to influence politics, to the unintentional spreading of misinformation about public health. This…

Computation and Language · Computer Science 2021-12-09 Isabelle Augenstein

In the age of social media and generative AI, the ability to automatically assess the credibility of online content has become increasingly critical, complementing traditional approaches to false information detection. Credibility…

Explanations for AI models in high-stakes domains like medicine often lack verifiability, which can hinder trust. To address this, we propose an interactive agent that produces explanations through an auditable sequence of actions. The…

Artificial Intelligence · Computer Science 2025-11-04 Yuhang Huang , Zekai Lin , Fan Zhong , Lei Liu

Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel…

Computation and Language · Computer Science 2025-09-08 Pranav Narayanan Venkit , Philippe Laban , Yilun Zhou , Kung-Hsiang Huang , Yixin Mao , Chien-Sheng Wu

Speech activity detection (SAD), which often rests on the fact that the noise is "more" stationary than speech, is particularly challenging in non-stationary environments, because the time variance of the acoustic scene makes it difficult…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-29 Jens Heitkaemper , Joerg Schmalenstroeer , Reinhold Haeb-Umbach

AI agents are now running real transactions, workflows, and sub-agent chains across organizational boundaries without continuous human supervision. This creates a problem no current infrastructure is equipped to solve: how do you identify,…

Artificial Intelligence · Computer Science 2026-04-28 Takumi Otsuka , Kentaroh Toyoda , Alex Leung

AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot provide. Distributed systems are a prime example: properties…

Agentic retrieval-augmented reasoning pipelines are increasingly used to structure how large language models (LLMs) incorporate external evidence in clinical decision support. These systems iteratively retrieve curated domain knowledge and…

TADS are a novel, concise white-box representation of neural networks. In this paper, we apply TADS to the problem of neural network verification, using them to generate either proofs or concise error characterizations for desirable neural…

Machine Learning · Computer Science 2023-05-01 Gerrit Nolte , Maximilian Schlüter , Alnis Murtovi , Bernhard Steffen

AI agents are increasingly expected to operate as digital employees: accessing enterprise data, making decisions, and taking actions autonomously. But agents are simultaneously less predictable than humans -- prone to hallucination,…

Artificial Intelligence · Computer Science 2026-05-29 Tyler Akidau , Tyler Rockwood , Johannes Brüderl , Marc Millstone