Cover Image

Mapping Smarter, Not Harder: A Test-Time Reinforcement Learning Agent That Improves Without Labels or Model Updates

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tsao, Wen-Kwang, Yu, Yao-Ching, Huang, Chien-Ming
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training
by: Yu, Yao-Ching, et al.
Published: (2025)

Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection
by: Cheng, Darren, et al.
Published: (2026)

Jamming Smarter, Not Harder: Exploiting O-RAN Y1 RAN Analytics for Efficient Interference
by: Ganiyu, Abiodun, et al.
Published: (2025)

Whisper Smarter, not Harder: Adversarial Attack on Partial Suppression
by: Wong, Zheng Jie, et al.
Published: (2025)

Reinforcement Learning for Automated Cybersecurity Penetration Testing
by: López-Montero, Daniel, et al.
Published: (2025)

Agent Safety Alignment via Reinforcement Learning
by: Sha, Zeyang, et al.
Published: (2025)

A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning
by: Yu, Yinbo, et al.
Published: (2024)

Targeted Bit-Flip Attacks on LLM-Based Agents
by: Wang, Jialai, et al.
Published: (2026)

Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
by: Khattar, Vanshaj, et al.
Published: (2026)

Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard
by: Abdelnabi, Sahar, et al.
Published: (2026)

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
by: Domico, Kyle, et al.
Published: (2025)

The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline
by: Wang, Haonan, et al.
Published: (2024)

APT-Agent: Automated Penetration Testing using Large Language Models
by: Li, William Guanting, et al.
Published: (2026)

Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents
by: Puppala, Sai, et al.
Published: (2026)

Evaluation of Reinforcement Learning for Autonomous Penetration Testing using A3C, Q-learning and DQN
by: Becker, Norman, et al.
Published: (2024)

Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label Information
by: Joung, Youngju, et al.
Published: (2025)

Silent Egress: When Implicit Prompt Injection Makes LLM Agents Leak Without a Trace
by: Lan, Qianlong, et al.
Published: (2026)

Multi-Agent Penetration Testing AI for the Web
by: David, Isaac, et al.
Published: (2025)

The Harder You Try, The Harder You Fail: The KeyTrap Denial-of-Service Algorithmic Complexity Attacks on DNSSEC
by: Heftrig, Elias, et al.
Published: (2024)

Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents
by: Wang, Xuan, et al.
Published: (2025)

Confidential Databases Without Cryptographic Mappings
by: Huang, Wenxuan, et al.
Published: (2026)

AWE: Adaptive Agents for Dynamic Web Penetration Testing
by: Jaswal, Akshat Singh, et al.
Published: (2026)

You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents
by: Kao, Ching-Yu, et al.
Published: (2026)

Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
by: Zolkowski, Artur, et al.
Published: (2025)

Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting
by: Carlini, Nicholas, et al.
Published: (2024)

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
by: Zhang, Hanrong, et al.
Published: (2024)

Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models
by: Zhong, Yisheng, et al.
Published: (2025)

xOffense: An Autonomous Multi-Agent Framework for Penetration Testing with Domain-Adapted Large Language Models
by: Luong, Phung Duc, et al.
Published: (2025)

LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning
by: Yan, Zeyu, et al.
Published: (2025)

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
by: Yang, Xianglin, et al.
Published: (2026)

Psyzkaller: Learning from Historical and On-the-Fly Execution Data for Smarter Seed Generation in OS kernel Fuzzing
by: Liu, Boyu, et al.
Published: (2025)

Lessons from Penetration Tests on Large-Scale Agent Systems
by: Eykholt, Kevin, et al.
Published: (2026)

AutoPenBench: Benchmarking Generative Agents for Penetration Testing
by: Gioacchini, Luca, et al.
Published: (2024)

Dullahan: Stealthy Backdoor Attack against Without-Label-Sharing Split Learning
by: Pu, Yuwen, et al.
Published: (2024)

OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services
by: Wang, Longxiang, et al.
Published: (2026)

A Novel Reinforcement Learning Model for Post-Incident Malware Investigations
by: Dunsin, Dipo, et al.
Published: (2024)

The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning
by: Rigaki, Maria, et al.
Published: (2023)

SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents
by: Du, Mengyao, et al.
Published: (2026)

Chronology of Multi-Agent Interactions for Provenance of Evolving Information
by: Chang, Ching-Chun, et al.
Published: (2025)

Parallel Test-Time Scaling with Multi-Sequence Verifiers
by: Kim, Yegon, et al.
Published: (2026)