Cover Image

Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Safety Role-Playing Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liao, Mingyang, Wan, Yichen, wu, shuchen, Miao, Chenxi, Shen, Xin, Li, Weikang, Li, Yang, Xia, Deguo, Huang, Jizhou
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval
by: Chen, Wang, et al.
Published: (2026)

Cross-LoRA: A Data-Free LoRA Transfer Framework across Heterogeneous LLMs
by: Xia, Feifan, et al.
Published: (2025)

Probabilistic Modeling of Intentions in Socially Intelligent LLM Agents
by: Xia, Feifan, et al.
Published: (2025)

Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs
by: Zhu, Rui, et al.
Published: (2026)

PAIRS: Parametric-Verified Adaptive Information Retrieval and Selection for Efficient RAG
by: Chen, Wang, et al.
Published: (2025)

DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution
by: Shen, Xin, et al.
Published: (2026)

Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration
by: Wang, Dayu, et al.
Published: (2026)

The World Won't Stay Still: Programmable Evolution for Agent Benchmarks
by: Li, Guangrui, et al.
Published: (2026)

Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
by: Eisele, Artur, et al.
Published: (2026)

Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning
by: Goel, Jyotin, et al.
Published: (2026)

CMRAG: Co-modality-based visual document retrieval and question answering
by: Chen, Wang, et al.
Published: (2025)

To Be (Safe), or Not to Be (Safe)? A Daily Exploration of Why and When Gig Workers Stay Safe Under Customer Demands
by: Jinghao Zhang, et al.
Published: (2025)

SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning
by: Yu, Wenhan, et al.
Published: (2025)

Staying with the Planet
by: Çelik, Leman, et al.
Published: (2026)

Stay cool
Published: (1995)

Staying power
Published: (2003)

FingerCap: Fine-grained Finger-level Hand Motion Captioning
by: Shen, Xin, et al.
Published: (2025)

Beyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generation
by: Yan, Lingyong, et al.
Published: (2026)

To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning
by: Sadrtdinov, Ildus, et al.
Published: (2023)

Stay Hungry, Stay Foolish: On the Extended Reading Articles Generation with LLMs
by: Liou, Yow-Fu, et al.
Published: (2025)

Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
by: Tang, Yihong, et al.
Published: (2025)

The Art of Staying Neutral
by: Abbenhuis, Maartje
Published: (2010)

Stay Connected to Be Diverse!
by: Maria Stockenreiter
Published: (2025)

Business. Staying in touch
Published: (1998)

Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
by: Guo, Kuangpu, et al.
Published: (2025)

Stay Focused: Problem Drift in Multi-Agent Debate
by: Becker, Jonas, et al.
Published: (2025)

Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment
by: Li, Jiajia, et al.
Published: (2026)

StayLTC: A Cost-Effective Multimodal Framework for Hospital Length of Stay Forecasting
by: Jana, Sudeshna, et al.
Published: (2025)

StayRose: A photostable StayGold derivative redshifted by genetic code expansion.
by: Scott, Will, et al.
Published: (2025)

Women Who Stay Behind
by: Trinidad Galván, Ruth
Published: (2019)

Chapter 2 “Stay at Home”
by: Heinz, Sarah
Published: (2025)

'We Are All Here to Stay'
by: O'Sullivan, Dominic
Published: (2020)

Asia. Staying ahead in the Philippines
Published: (1996)

Staying One Century Ahead
by: Jacobs, Don
Published: (1970)

Populating and Staying with Methodological Surprise
by: Mira Kallio‐Tavin, et al.
Published: (2025)

Leave or Stay? Impact of City Attribute Perception and City Image on University Student Stay Intention
by: Haiyan Lu, et al.
Published: (2025)

Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
by: Li, Ziheng, et al.
Published: (2025)

Staying Fresh: Efficient Algorithms for Timely Social Information Distribution
by: Li, Songhua, et al.
Published: (2023)

Regularisations of Irregularly Staying Migrants in the EU
by: Hinterberger, Kevin Fredy
Published: (2023)

Barbed Stayed Bridge Pharyngoplasty (BSBP)
by: Giuseppe Magliulo, et al.
Published: (2024)