Cover Image

Sound Agentic Science Requires Adversarial Experiments

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fa, Dionizije, Culjak, Marko
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics
by: Fa, Dionizije, et al.
Published: (2026)

Experiments in Agentic AI for Science
by: Fox, Judy, et al.
Published: (2026)

Accelerating Social Science Research via Agentic Hypothesization and Experimentation
by: Gupta, Jishu Sen, et al.
Published: (2026)

How Adversarial Environments Mislead Agentic AI?
by: Zhan, Zhonghao, et al.
Published: (2026)

Interactive Evaluation Requires a Design Science
by: Xuan, Keyang, et al.
Published: (2026)

Responsible Agentic AI Requires Explicit Provenance
by: Hu, Jinwei, et al.
Published: (2026)

Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI
by: Zhang, Sha, et al.
Published: (2025)

Sanity Checks for Agentic Data Science
by: Rewolinski, Zachary T., et al.
Published: (2026)

Towards Agentic Intelligence for Materials Science
by: Zhang, Huan, et al.
Published: (2026)

Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines
by: Bethany, Mazal, et al.
Published: (2026)

Fast Adversarial Training against Sparse Attacks Requires Loss Smoothing
by: Zhong, Xuyang, et al.
Published: (2025)

Embodied Science: Closing the Discovery Loop with Agentic Embodied AI
by: Zhuang, Xiang, et al.
Published: (2026)

Read the Paper, Write the Code: Agentic Reproduction of Social-Science Results
by: Kohler, Benjamin, et al.
Published: (2026)

Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale
by: Zhang, Linfeng, et al.
Published: (2025)

UniAPL: A Unified Adversarial Preference Learning Framework for Instruct-Following
by: Qian, FaQiang, et al.
Published: (2025)

Automated Adversarial Collaboration for Advancing Theory Building in the Cognitive Sciences
by: Chandramouli, Suyog, et al.
Published: (2026)

From Research Question to Scientific Workflow: Leveraging Agentic AI for Science Automation
by: Balis, Bartosz, et al.
Published: (2026)

EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale
by: Zhu, Xinyu, et al.
Published: (2026)

KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth Science
by: Li, Ziwei, et al.
Published: (2026)

A Cloud-based Multi-Agentic Workflow for Science
by: Acharya, Anurag, et al.
Published: (2026)

Agentic Adversarial QA for Improving Domain-Specific LLMs
by: Grari, Vincent, et al.
Published: (2026)

Creative Adversarial Testing (CAT): A Novel Framework for Evaluating Goal-Oriented Agentic AI Systems
by: Dhrif, Hassen
Published: (2025)

FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean
by: Meadows, Jordan, et al.
Published: (2026)

CATSE: A Context-Aware Framework for Causal Target Sound Extraction
by: Baligar, Shrishail, et al.
Published: (2024)

Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
by: Zhu, Xinyu, et al.
Published: (2026)

Zephyrus: An Agentic Framework for Weather Science
by: Varambally, Sumanth, et al.
Published: (2025)

AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework
by: Zeng, Zihang, et al.
Published: (2026)

Agentic Design of Compositional Descriptors via Autoresearch for Materials Science Applications
by: Cobelli, Matteo, et al.
Published: (2026)

Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT
by: El-Hajjami, Abdelkarim, et al.
Published: (2023)

Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique
by: Roy, Joyjit, et al.
Published: (2026)

Sci-VLA: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments
by: Pang, Yiwen, et al.
Published: (2026)

CEDAR: Context Engineering for Agentic Data Science
by: Roy, Rishiraj Saha, et al.
Published: (2026)

DUET: Agentic Design Understanding via Experimentation and Testing
by: Smith, Gus Henry, et al.
Published: (2025)

Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption
by: Poinsot, Audrey, et al.
Published: (2025)

Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse
by: Bertran, Martin, et al.
Published: (2026)

DeepAnalyze: Agentic Large Language Models for Autonomous Data Science
by: Zhang, Shaolei, et al.
Published: (2025)

From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science
by: Weidener, Lukas, et al.
Published: (2026)

Roots and Requirements for Collaborative AIs
by: Stefik, Mark
Published: (2023)

GRACE: an Agentic AI for Particle Physics Experiment Design and Simulation
by: Hill, Justin, et al.
Published: (2026)

Homoglyph-based Adversarial Perturbation of Introductory Computer Science Theory Problems
by: Alexander, Aidan, et al.
Published: (2026)