Imagen de Portada

SafeCtrl-RL: Inference-Time Adaptive Behaviour Control for LLM Dialogue via RL-Driven Prompt Optimisation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Orme, Michael, Yu, Yanchao, Tan, Zhiyuan
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

OnRL-RAG: Real-Time Personalized Mental Health Dialogue System
por: Bilal, Ahsan, et al.
Publicado: (2025)

AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting
por: Huang, Shijue, et al.
Publicado: (2025)

Tailored Conversations beyond LLMs: A RL-Based Dialogue Manager
por: Galland, Lucie, et al.
Publicado: (2025)

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
por: Zhang, Shenao, et al.
Publicado: (2025)

CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
por: Liu, Huanshuo, et al.
Publicado: (2024)

ReviewRL: Towards Automated Scientific Review with RL
por: Zeng, Sihang, et al.
Publicado: (2025)

On Designing Effective RL Reward at Training Time for LLM Reasoning
por: Gao, Jiaxuan, et al.
Publicado: (2024)

Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
por: Cen, Zhepeng, et al.
Publicado: (2025)

Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL
por: Abdulhai, Marwa, et al.
Publicado: (2025)

Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
por: Choi, Yunseon, et al.
Publicado: (2024)

Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning
por: Lacombe, Valentin, et al.
Publicado: (2025)

Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
por: Xie, Tian, et al.
Publicado: (2025)

Efficient RL for optimizing conversation level outcomes with an LLM-based tutor
por: Nam, Hyunji, et al.
Publicado: (2025)

LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialogues
por: Li, Haoyang, et al.
Publicado: (2025)

Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL
por: Sun, Hao, et al.
Publicado: (2023)

Propensity Inference: Environmental Contributors to LLM Behaviour
por: Järviniemi, Olli, et al.
Publicado: (2026)

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
por: Wang, Sudong, et al.
Publicado: (2026)

DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
por: Wu, Junchao, et al.
Publicado: (2024)

Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL
por: Song, Xiaoying, et al.
Publicado: (2025)

FlowRL: Matching Reward Distributions for LLM Reasoning
por: Zhu, Xuekai, et al.
Publicado: (2025)

LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning
por: Zhu, Yu, et al.
Publicado: (2026)

Words as Beacons: Guiding RL Agents with High-Level Language Prompts
por: Ruiz-Gonzalez, Unai, et al.
Publicado: (2024)

GLIDE-RL: Grounded Language Instruction through DEmonstration in RL
por: Kharyal, Chaitanya, et al.
Publicado: (2024)

CtrlCoT: Dual-Granularity Chain-of-Thought Compression for Controllable Reasoning
por: Fan, Zhenxuan, et al.
Publicado: (2026)

SafeCtrl: Region-Aware Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress
por: Zhang, Lingyun, et al.
Publicado: (2026)

Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL
por: Liu, Che, et al.
Publicado: (2025)

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
por: Wei, Yuxiang, et al.
Publicado: (2025)

THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
por: Chang, Qikai, et al.
Publicado: (2025)

Speak & Spell: LLM-Driven Controllable Phonetic Error Augmentation for Robust Dialogue State Tracking
por: Lee, Jihyun, et al.
Publicado: (2024)

SafeCtrl: Region-Based Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress
por: Zhang, Lingyun, et al.
Publicado: (2025)

Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL
por: Zhou, Yixiao, et al.
Publicado: (2026)

SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
por: Limozin, Alexis, et al.
Publicado: (2026)

ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL
por: Lu, Xingyu, et al.
Publicado: (2026)

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
por: Yang, Zhihe, et al.
Publicado: (2025)

Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts
por: Luo, Sijia, et al.
Publicado: (2026)

ReadCtrl: Personalizing text generation with readability-controlled instruction learning
por: Tran, Hieu, et al.
Publicado: (2024)

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
por: Wei, Zhepei, et al.
Publicado: (2025)

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
por: Zhou, Jin Peng, et al.
Publicado: (2025)

TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents
por: Djuhera, Aladin, et al.
Publicado: (2026)

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
por: Shen, Guobin, et al.
Publicado: (2026)