Cover Image

Benchmarking the Robustness of Agentic Systems to Adversarially-Induced Harms

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nöther, Jonathan, Singla, Adish, Radanovic, Goran
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints
by: Nöther, Jonathan, et al.
Published: (2025)

MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systems
by: Nöther, Jonathan, et al.
Published: (2026)

Policy Teaching via Data Poisoning in Learning from Human Preferences
by: Nika, Andi, et al.
Published: (2025)

Corruption-Robust Offline Two-Player Zero-Sum Markov Games
by: Nika, Andi, et al.
Published: (2024)

Corruption Robust Offline Reinforcement Learning with Human Feedback
by: Mandal, Debmalya, et al.
Published: (2024)

Learning Embeddings for Sequential Tasks Using Population of Agents
by: Mahajan, Mridul, et al.
Published: (2023)

Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback
by: Nika, Andi, et al.
Published: (2026)

AgenticRed: Evolving Agentic Systems for Red-Teaming
by: Yuan, Jiayi, et al.
Published: (2026)

Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences
by: Nika, Andi, et al.
Published: (2024)

On Corruption-Robustness in Performative Reinforcement Learning
by: Pollatos, Vasilis, et al.
Published: (2025)

Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation
by: Kotalwar, Nachiket, et al.
Published: (2024)

Distributionally Robust Reinforcement Learning with Human Feedback
by: Mandal, Debmalya, et al.
Published: (2025)

Reward Design for Justifiable Sequential Decision-Making
by: Sukovic, Aleksa, et al.
Published: (2024)

Performative Reinforcement Learning with Linear Markov Decision Process
by: Mandal, Debmalya, et al.
Published: (2024)

Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs
by: Tzannetos, Georgios, et al.
Published: (2025)

Informativeness of Reward Functions in Reinforcement Learning
by: Devidze, Rati, et al.
Published: (2024)

Proximal Curriculum with Task Correlations for Deep Reinforcement Learning
by: Tzannetos, Georgios, et al.
Published: (2024)

Can In-Context Reinforcement Learning Recover From Reward Poisoning Attacks?
by: Sasnauskas, Paulius, et al.
Published: (2025)

Towards Generalizable Agents in Text-Based Educational Environments: A Study of Integrating RL with LLMs
by: Radmehr, Bahar, et al.
Published: (2024)

Sparse Offline Reinforcement Learning with Corruption Robustness
by: Tran, Nam Phuong, et al.
Published: (2025)

Performative Reinforcement Learning in Gradually Shifting Environments
by: Rank, Ben, et al.
Published: (2024)

Independent Learning in Performative Markov Potential Games
by: Sahitaj, Rilind, et al.
Published: (2025)

The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness
by: Hao, Yifan, et al.
Published: (2024)

Neural Task Synthesis for Visual Programming
by: Pădurean, Victor-Alexandru, et al.
Published: (2023)

Formal Models of Active Learning from Contrastive Examples
by: Mansouri, Farnam, et al.
Published: (2025)

Inference-Time Personalized Alignment with a Few User Preference Queries
by: Pădurean, Victor-Alexandru, et al.
Published: (2025)

Stochastic Principal-Agent Problems: Efficient Computation and Learning
by: Gan, Jiarui, et al.
Published: (2023)

Adversarially Robust Detection of Harmful Online Content: A Computational Design Science Approach
by: Chai, Yidong, et al.
Published: (2025)

Learning Half-Spaces from Perturbed Contrastive Examples
by: Ravari, Aryan Alavi Razavi, et al.
Published: (2026)

Reinforcement Learning for Durable Algorithmic Recourse
by: Ceccon, Marina, et al.
Published: (2025)

Optimal Decision Making Under Strategic Behavior
by: Tsirtsis, Stratis, et al.
Published: (2019)

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
by: Sheshadri, Abhay, et al.
Published: (2024)

Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization
by: Mumcu, Furkan, et al.
Published: (2026)

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
by: Andriushchenko, Maksym, et al.
Published: (2024)

On the Benefits of Inducing Local Lipschitzness for Robust Generative Adversarial Imitation Learning
by: Memarian, Farzan, et al.
Published: (2021)

Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming
by: Pădurean, Victor-Alexandru, et al.
Published: (2024)

Whispers in the Machine: Confidentiality in Agentic Systems
by: Evertz, Jonathan, et al.
Published: (2024)

Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
by: Lange, Robert Tjarko, et al.
Published: (2025)

Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness
by: Piras, Giorgio, et al.
Published: (2024)

TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
by: Simonetto, Thibault, et al.
Published: (2024)