Cover Image

DRAFT: Task Decoupled Latent Reasoning for Agent Safety

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Lin, Fang, Junfeng, Zhang, Dan, Shen, Fei, Wang, Xiang, Chua, Tat-Seng
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems
by: Fang, Junfeng, et al.
Published: (2025)

SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models
by: Fang, Junfeng, et al.
Published: (2025)

NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels
by: Fang, Junfeng, et al.
Published: (2026)

SafeNeuron: Neuron-Level Safety Alignment for Large Language Models
by: Wang, Zhaoxin, et al.
Published: (2026)

Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics
by: Sheng, Leheng, et al.
Published: (2026)

NextMem: Towards Latent Factual Memory for LLM-based Agents
by: Zhang, Zeyu, et al.
Published: (2026)

Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration
by: He, Jinghan, et al.
Published: (2026)

Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling
by: Luo, Yanchen, et al.
Published: (2025)

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
by: Sheng, Leheng, et al.
Published: (2025)

Are Reasoning Models More Prone to Hallucination?
by: Yao, Zijun, et al.
Published: (2025)

Rubric-based On-policy Distillation
by: Fang, Junfeng, et al.
Published: (2026)

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
by: Li, Gengsheng, et al.
Published: (2026)

The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment
by: Zhang, Zhexin, et al.
Published: (2026)

Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules
by: Liu, Zhiyuan, et al.
Published: (2023)

NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation
by: Liu, Zhiyuan, et al.
Published: (2025)

Enhancing Spectral Graph Neural Networks with LLM-Predicted Homophily
by: Lu, Kangkang, et al.
Published: (2025)

Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control
by: Yang, Yonghui, et al.
Published: (2026)

On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR
by: Ye, Hao, et al.
Published: (2026)

NExT-GPT: Any-to-Any Multimodal LLM
by: Wu, Shengqiong, et al.
Published: (2023)

Continual Multimodal Contrastive Learning
by: Liu, Xiaohao, et al.
Published: (2025)

Less Approximates More: Harmonizing Performance and Confidence Faithfulness via Hybrid Post-Training for High-Stakes Tasks
by: Ma, Haokai, et al.
Published: (2026)

CARL: Criticality-Aware Agentic Reinforcement Learning
by: Shen, Leyang, et al.
Published: (2025)

Reasoning on Time-Series for Financial Technical Analysis
by: Koa, Kelvin J. L., et al.
Published: (2025)

Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
by: Xu, Chen, et al.
Published: (2025)

Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment
by: Li, Moxin, et al.
Published: (2025)

Principled Multimodal Representation Learning
by: Liu, Xiaohao, et al.
Published: (2025)

GOODAT: Towards Test-time Graph Out-of-Distribution Detection
by: Wang, Luzhi, et al.
Published: (2024)

Towards 3D Molecule-Text Interpretation in Language Models
by: Li, Sihang, et al.
Published: (2024)

Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations
by: Deng, Yang, et al.
Published: (2024)

ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning
by: Zhang, Jinyang, et al.
Published: (2025)

Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models
by: Koa, Kelvin J. L., et al.
Published: (2024)

Addressing Graph Heterogeneity and Heterophily from A Spectral Perspective
by: Lu, Kangkang, et al.
Published: (2024)

DRAFT-ing Architectural Design Decisions using LLMs
by: Dhar, Rudra, et al.
Published: (2025)

Temporal Relational Reasoning of Large Language Models for Detecting Stock Portfolio Crashes
by: Koa, Kelvin J. L., et al.
Published: (2024)

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation
by: Qu, Leigang, et al.
Published: (2024)

Towards Modality Generalization: A Benchmark and Prospective Analysis
by: Liu, Xiaohao, et al.
Published: (2024)

TTOM: Test-Time Optimization and Memorization for Compositional Video Generation
by: Qu, Leigang, et al.
Published: (2025)

STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training
by: Qiu, Haiyi, et al.
Published: (2024)

DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization
by: Zhou, Zhenglin, et al.
Published: (2025)

Optimize Incompatible Parameters through Compatibility-aware Knowledge Integration
by: Lv, Zheqi, et al.
Published: (2025)