Imagen de Portada

Audited Skill-Graph Self-Improvement for Agentic LLMs via Verifiable Rewards, Experience Synthesis, and Continual Memory

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Ken, Huang, Jerry
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Artificial Intelligence 68T05, 68T20, 68M25 (Learning and adaptive systems, Artificial intelligence, Computer security)
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A LoRA-Based Approach to Fine-Tuning LLMs for Educational Guidance in Resource-Constrained Settings
por: Hosen, Md Millat
Publicado: (2025)

Challenges and Future Directions in Agentic Reverse Engineering Systems
por: Radey, Salem, et al.
Publicado: (2026)

MITRE ATT&CK Applications in Cybersecurity and The Way Forward
por: Jiang, Yuning, et al.
Publicado: (2025)

CLNX: Bridging Code and Natural Language for C/C++ Vulnerability-Contributing Commits Identification
por: Qin, Zeqing, et al.
Publicado: (2024)

EmbGen: Teaching with Reassembled Corpora
por: Lenin, Arun K, et al.
Publicado: (2026)

Dark LLMs: The Growing Threat of Unaligned AI Models
por: Fire, Michael, et al.
Publicado: (2025)

Blind Gods and Broken Screens: Architecting a Secure, Intent-Centric Mobile Agent Operating System
por: Zou, Zhenhua, et al.
Publicado: (2026)

On Immutable Memory Systems for Artificial Agents: A Blockchain-Indexed Automata-Theoretic Framework Using ECDH-Keyed Merkle Chains
por: Wright, Craig Steven
Publicado: (2025)

VulRG: Multi-Level Explainable Vulnerability Patch Ranking for Complex Systems Using Graphs
por: Jiang, Yuning, et al.
Publicado: (2025)

Synthesizing Access Control Policies using Large Language Models
por: Vatsa, Adarsh, et al.
Publicado: (2025)

Action Agent: Agentic Video Generation Meets Flow-Constrained Diffusion
por: Sam, Jeffrin, et al.
Publicado: (2026)

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
por: Liu, Zhe, et al.
Publicado: (2026)

AVEC: Bootstrapping Privacy for Local LLMs
por: Gaikwad, Madhava
Publicado: (2025)

CveBinarySheet: A Comprehensive Pre-built Binaries Database for IoT Vulnerability Analysis
por: Chen, Lingfeng
Publicado: (2025)

Data Encryption Battlefield: A Deep Dive into the Dynamic Confrontations in Ransomware Attacks
por: Mahboubi, Arash, et al.
Publicado: (2025)

Supporting Socially Constrained Private Communications with SecureWhispers
por: Khandkar, Vinod, et al.
Publicado: (2025)

On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs
por: Bahar, Atmane Ayoub Mansour, et al.
Publicado: (2024)

A V2X-based Privacy Preserving Federated Measuring and Learning System
por: Alekszejenkó, Levente, et al.
Publicado: (2024)

A Hybrid Deep Learning and Anomaly Detection Framework for Real-Time Malicious URL Classification
por: Khaled, Berkani, et al.
Publicado: (2025)

Secrecy and Verifiability: An Introduction to Electronic Voting
por: Keeler, Paul, et al.
Publicado: (2026)

Multimodal Multi-Agent Ransomware Analysis Using AutoGen
por: Khan, Asifullah, et al.
Publicado: (2026)

AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement
por: Rosser, J, et al.
Publicado: (2025)

Hardening x402: PII-Safe Agentic Payments via Pre-Execution Metadata Filtering
por: Stantchev, Vladimir
Publicado: (2026)

Verifiable evaluations of machine learning models using zkSNARKs
por: South, Tobin, et al.
Publicado: (2024)

Auditable Homomorphic-based Decentralized Collaborative AI with Attribute-based Differential Privacy
por: Yeh, Lo-Yao, et al.
Publicado: (2024)

Watermarking Large Language Models in Europe: Interpreting the AI Act in Light of Technology
por: Souverain, Thomas
Publicado: (2025)

Resilient Federated Chain: Transforming Blockchain Consensus into an Active Defense Layer for Federated Learning
por: García-Márquez, Mario, et al.
Publicado: (2026)

Evaluation of Risk and Resilience of the MBTA Green Rapid Transit System
por: Gorthi, Anil Kumar
Publicado: (2025)

Generative AI Models: Opportunities and Risks for Industry and Authorities
por: Alt, Tobias, et al.
Publicado: (2024)

Deep Learning-Based Multi-Factor Authentication: A Survey of Biometric and Smart Card Integration Approaches
por: Ganmati, Abdelilah, et al.
Publicado: (2025)

Adaptive Reinforcement Learning for State Avoidance in Discrete Event Systems
por: Dony, Md Nur-A-Adam
Publicado: (2025)

Safety, Security, and Cognitive Risks in World Models
por: Parmar, Manoj
Publicado: (2026)

Cross-Domain Malware Detection via Probability-Level Fusion of Lightweight Gradient Boosting Models
por: Mohamed, Omar Khalid Ali
Publicado: (2025)

Evaluation of ChatGPT's Smart Contract Auditing Capabilities Based on Chain of Thought
por: Du, Yuying, et al.
Publicado: (2024)

A Method for Securely Transmitting Large Video Files Using Chaotic Compression and Encryption
por: Bhattacharjee, Shiladitya, et al.
Publicado: (2026)

X-NegoBox: An Explainable Privacy-Budget Negotiation Framework for Secure Peer-to-Peer Energy Data Exchange
por: Sengupta, Poushali, et al.
Publicado: (2026)

The Unicity Execution Layer
por: Buldas, Ahto, et al.
Publicado: (2026)

Unicity: Predicates and Atomic Swaps
por: Buldas, Ahto, et al.
Publicado: (2026)

Towards AI-enabled Cyber Threat Assessment in the Health Sector
por: Heinl, Patrizia, et al.
Publicado: (2024)

VOLTRON: Detecting Unknown Malware Using Graph-Based Zero-Shot Learning
por: Akdeniz, M. Tahir, et al.
Publicado: (2025)