Copertina

MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Changqing, Li, Tianlin, Zhang, Xiaohan, Liu, Aishan, Pan, Li
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents
di: Wang, Haochen, et al.
Pubblicazione: (2026)

SOMBRERO: Measuring and Steering Boundary Placement in End-to-End Hierarchical Sequence Models
di: Neitemeier, Pit, et al.
Pubblicazione: (2026)

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
di: Liang, Jiacheng, et al.
Pubblicazione: (2026)

End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning
di: Chen, Guanzhong, et al.
Pubblicazione: (2025)

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization
di: Sun, Qitong, et al.
Pubblicazione: (2026)

Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
di: Wang, Yifei, et al.
Pubblicazione: (2026)

Foam-Agent 2.0: An End-to-End Composable Multi-Agent Framework for Automating CFD Simulation in OpenFOAM
di: Yue, Ling, et al.
Pubblicazione: (2025)

Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning
di: Zhang, Kehao, et al.
Pubblicazione: (2026)

End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost
di: Tan, Qitao, et al.
Pubblicazione: (2025)

LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models
di: Mozaffari, Mohammad, et al.
Pubblicazione: (2026)

Constraint-Informed Active Learning for End-to-End ACOPF Optimization Proxies
di: Li, Miao, et al.
Pubblicazione: (2025)

HabitatAgent: An End-to-End Multi-Agent System for Housing Consultation
di: Yang, Hongyang, et al.
Pubblicazione: (2026)

Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion Method
di: Xu, Haofei, et al.
Pubblicazione: (2026)

OptiProxy-NAS: Optimization Proxy based End-to-End Neural Architecture Search
di: Lyu, Bo, et al.
Pubblicazione: (2025)

LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning
di: Wei, Yuan, et al.
Pubblicazione: (2025)

End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generation
di: Tripathi, Anurag, et al.
Pubblicazione: (2025)

Compromising Embodied Agents with Contextual Backdoor Attacks
di: Liu, Aishan, et al.
Pubblicazione: (2024)

An End-to-End Deep Reinforcement Learning Approach for Solving the Traveling Salesman Problem with Drones
di: Zeng, Taihelong, et al.
Pubblicazione: (2025)

An End-to-End Structure with Novel Position Mechanism and Improved EMD for Stock Forecasting
di: Li, Chufeng, et al.
Pubblicazione: (2024)

DISCO: An End-to-End Bandit Framework for Personalised Discount Allocation
di: Zhang, Jason Shuo, et al.
Pubblicazione: (2024)

Multimodal Large Language Models for End-to-End Affective Computing: Benchmarking and Boosting with Generative Knowledge Prompting
di: Luo, Miaosen, et al.
Pubblicazione: (2025)

TrustAgent: Towards Safe and Trustworthy LLM-based Agents
di: Hua, Wenyue, et al.
Pubblicazione: (2024)

Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving
di: Zheng, Yinan, et al.
Pubblicazione: (2026)

An End-to-End Learning Approach for Solving Capacitated Location-Routing Problems
di: Miao, Changhao, et al.
Pubblicazione: (2025)

Attack End-to-End Autonomous Driving through Module-Wise Noise
di: Wang, Lu, et al.
Pubblicazione: (2024)

End-to-end PDDL Planning with Hardcoded and Dynamic Agents
di: La Malfa, Emanuele, et al.
Pubblicazione: (2025)

BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning
di: Pan, Jianming, et al.
Pubblicazione: (2024)

Bridging the Divide: End-to-End Sequence-Graph Learning
di: Chen, Yuen, et al.
Pubblicazione: (2025)

Tackling Noisy Clients in Federated Learning with End-to-end Label Correction
di: Jiang, Xuefeng, et al.
Pubblicazione: (2024)

Stratos: An End-to-End Distillation Pipeline for Customized LLMs under Distributed Cloud Environments
di: Dai, Ziming, et al.
Pubblicazione: (2025)

$Agent^2$: An Agent-Generates-Agent Framework for Reinforcement Learning Automation
di: Wei, Yuan, et al.
Pubblicazione: (2025)

End-To-End Learning of Gaussian Mixture Priors for Diffusion Sampler
di: Blessing, Denis, et al.
Pubblicazione: (2025)

End-to-End Multi-Modal Diffusion Mamba
di: Lu, Chunhao, et al.
Pubblicazione: (2025)

Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing for Indoor Firefighting: An End-to-End Reinforcement Learning Approach
di: Huang, Baixiao, et al.
Pubblicazione: (2026)

PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks
di: Li, Xuran, et al.
Pubblicazione: (2025)

Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
di: Lu, Miao, et al.
Pubblicazione: (2025)

Guided Learning: Lubricating End-to-End Modeling for Multi-stage Decision-making
di: Guo, Jian, et al.
Pubblicazione: (2024)

RAP: Runtime Adaptive Pruning for LLM Inference
di: Liu, Huanrong, et al.
Pubblicazione: (2025)

Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
di: Braun, Dan, et al.
Pubblicazione: (2024)

End-to-End Learning for Partially-Observed Time Series with PyPOTS
di: Du, Wenjie, et al.
Pubblicazione: (2026)