1 citations · 1 across the 5 of their papers we have counts for
7 papers
World Models for Embodied Intelligence: From Plausible to Controllable to Actionable
Nanjie Yao, Hao Wang, Chong Cheng +10
World models connect perception and decision-making in embodied intelligence by maintaining hidden state, anticipating consequences, comparing interventions, and adapting when exec…
CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games
Zheng Zhang, Nanjie Yao, Jiarui He +3
Social deduction games (SDGs) such as Werewolf have become challenging testbeds for AI agents. These games require complex social skills such as reasoning, deception, and collabora…
PACT: Preserving Anchored Cores in Task-vectors for Model Merging
Ningyuan Shi, Zhipeng Zhou, Hao Wang +2
Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model. Most exi…
Genesis: Evolving Attack Strategies for LLM Web Agent Red-Teaming
Zheng Zhang, Jiarui He, Yuchen Cai +4
As large language model (LLM) agents increasingly automate complex web tasks, they boost productivity while simultaneously introducing new security risks. However, relevant studies…
The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Games
Zhang Zheng, Deheng Ye, Peilin Zhao +1
Large language model (LLM) agents have shown remarkable progress in social deduction games (SDGs). However, existing approaches primarily focus on information processing and strate…
Enhancing Jailbreak Attacks on LLMs via Persona Prompts
Zheng Zhang, Peilin Zhao, Deheng Ye +1
Jailbreak attacks aim to exploit large language models (LLMs) by inducing them to generate harmful content, thereby revealing their vulnerabilities. Understanding and addressing th…
LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay
Yihuai Lan, Zhiqiang Hu, Lei Wang +6
This paper explores the open research problem of understanding the social behaviors of LLM-based agents. Using Avalon as a testbed, we employ system prompts to guide LLM agents in…