Image de couverture de livre

Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Yuxin, Zhu, Mingye, Liu, Siyuan, Hu, Bo, Zhang, Lei
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

On-the-fly Preference Alignment via Principle-Guided Decoding
par: Zhu, Mingye, et autres
Publié: (2025)

From Persona to Personalization: A Survey on Role-Playing Language Agents
par: Chen, Jiangjie, et autres
Publié: (2024)

Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
par: Liu, Yi, et autres
Publié: (2025)

CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents
par: Park, Jeiyoon, et autres
Publié: (2024)

DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans
par: Yao, Bingsheng, et autres
Publié: (2025)

ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning
par: Tang, Yihong, et autres
Publié: (2024)

A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles
par: Chen, Siyuan, et autres
Publié: (2024)

Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs
par: Wang, Kai, et autres
Publié: (2026)

DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents
par: Zhang, Rongsheng, et autres
Publié: (2026)

Dynamic Role Assignment for Multi-Agent Debate
par: Zhang, Miao, et autres
Publié: (2026)

DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check
par: Qiao, Ziheng, et autres
Publié: (2024)

Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models
par: Costa, Davi Bastos, et autres
Publié: (2025)

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
par: Wang, Yiming, et autres
Publié: (2025)

HARBOR: Exploring Persona Dynamics in Multi-Agent Competition
par: Jiang, Kenan, et autres
Publié: (2025)

AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning
par: Wang, Yutong, et autres
Publié: (2026)

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
par: Wang, Zekun Moore, et autres
Publié: (2023)

CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulation
par: Wang, Xintao, et autres
Publié: (2025)

FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization
par: Zhu, Mingye, et autres
Publié: (2024)

Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play
par: Shi, Yemin, et autres
Publié: (2025)

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
par: Liu, Jingyu, et autres
Publié: (2025)

Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
par: Liu, Quan, et autres
Publié: (2024)

MTPChat: A Multimodal Time-Aware Persona Dataset for Conversational Agents
par: Yang, Wanqi, et autres
Publié: (2025)

LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play
par: Lu, Li-Chun, et autres
Publié: (2024)

Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation
par: Lin, Minhua, et autres
Publié: (2024)

AgentSHAP: Interpreting LLM Agent Tool Importance with Monte Carlo Shapley Value Estimation
par: Horovicz, Miriam
Publié: (2025)

Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting
par: Ruangtanusak, Saksorn, et autres
Publié: (2025)

Multi-Stage Patient Role-Playing Framework for Realistic Clinical Interactions
par: Jiang, Shijie, et autres
Publié: (2026)

Knowledge Boundary and Persona Dynamic Shape A Better Social Media Agent
par: Zhou, Junkai, et autres
Publié: (2024)

Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games
par: Lim, Seungwon, et autres
Publié: (2025)

PersonaKit (PK): A Plug-and-Play Platform for User Testing Diverse Roles in Full-Duplex Dialogue
par: Jeon, Hyunbae, et autres
Publié: (2026)

PAD: Personalized Alignment of LLMs at Decoding-Time
par: Chen, Ruizhe, et autres
Publié: (2024)

VoxRole: A Comprehensive Benchmark for Evaluating Speech-Based Role-Playing Agents
par: Wu, Weihao, et autres
Publié: (2025)

MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning
par: Huang, Kun, et autres
Publié: (2025)

Scaling Laws for Speculative Decoding
par: Yan, Siyuan, et autres
Publié: (2025)

AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing
par: Xu, Zhenhua, et autres
Publié: (2026)

Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play
par: Li, Sha, et autres
Publié: (2024)

Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding
par: Zhang, Kexun, et autres
Publié: (2023)

PersonaGym: Evaluating Persona Agents and LLMs
par: Samuel, Vinay, et autres
Publié: (2024)

Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment
par: Zhang, Xiaotian, et autres
Publié: (2025)

Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models
par: Zhang, Yanyue, et autres
Publié: (2025)