Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yuxin, Zhu, Mingye, Liu, Siyuan, Hu, Bo, Zhang, Lei
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On-the-fly Preference Alignment via Principle-Guided Decoding
by: Zhu, Mingye, et al.
Published: (2025)

From Persona to Personalization: A Survey on Role-Playing Language Agents
by: Chen, Jiangjie, et al.
Published: (2024)

Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
by: Liu, Yi, et al.
Published: (2025)

CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents
by: Park, Jeiyoon, et al.
Published: (2024)

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

ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning
by: Tang, Yihong, et al.
Published: (2024)

A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles
by: Chen, Siyuan, et al.
Published: (2024)

Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs
by: Wang, Kai, et al.
Published: (2026)

DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents
by: Zhang, Rongsheng, et al.
Published: (2026)

Dynamic Role Assignment for Multi-Agent Debate
by: Zhang, Miao, et al.
Published: (2026)

DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check
by: Qiao, Ziheng, et al.
Published: (2024)

Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models
by: Costa, Davi Bastos, et al.
Published: (2025)

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
by: Wang, Yiming, et al.
Published: (2025)

HARBOR: Exploring Persona Dynamics in Multi-Agent Competition
by: Jiang, Kenan, et al.
Published: (2025)

AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning
by: Wang, Yutong, et al.
Published: (2026)

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
by: Wang, Zekun Moore, et al.
Published: (2023)

CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulation
by: Wang, Xintao, et al.
Published: (2025)

FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization
by: Zhu, Mingye, et al.
Published: (2024)

Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play
by: Shi, Yemin, et al.
Published: (2025)

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
by: Liu, Jingyu, et al.
Published: (2025)

Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
by: Liu, Quan, et al.
Published: (2024)

MTPChat: A Multimodal Time-Aware Persona Dataset for Conversational Agents
by: Yang, Wanqi, et al.
Published: (2025)

LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play
by: Lu, Li-Chun, et al.
Published: (2024)

Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation
by: Lin, Minhua, et al.
Published: (2024)

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

Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting
by: Ruangtanusak, Saksorn, et al.
Published: (2025)

Multi-Stage Patient Role-Playing Framework for Realistic Clinical Interactions
by: Jiang, Shijie, et al.
Published: (2026)

Knowledge Boundary and Persona Dynamic Shape A Better Social Media Agent
by: Zhou, Junkai, et al.
Published: (2024)

Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games
by: Lim, Seungwon, et al.
Published: (2025)

PersonaKit (PK): A Plug-and-Play Platform for User Testing Diverse Roles in Full-Duplex Dialogue
by: Jeon, Hyunbae, et al.
Published: (2026)

PAD: Personalized Alignment of LLMs at Decoding-Time
by: Chen, Ruizhe, et al.
Published: (2024)

VoxRole: A Comprehensive Benchmark for Evaluating Speech-Based Role-Playing Agents
by: Wu, Weihao, et al.
Published: (2025)

MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning
by: Huang, Kun, et al.
Published: (2025)

Scaling Laws for Speculative Decoding
by: Yan, Siyuan, et al.
Published: (2025)

AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing
by: Xu, Zhenhua, et al.
Published: (2026)

Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play
by: Li, Sha, et al.
Published: (2024)

Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding
by: Zhang, Kexun, et al.
Published: (2023)

PersonaGym: Evaluating Persona Agents and LLMs
by: Samuel, Vinay, et al.
Published: (2024)

Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment
by: Zhang, Xiaotian, et al.
Published: (2025)

Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models
by: Zhang, Yanyue, et al.
Published: (2025)