5 citations · 19 across the 12 of their papers we have counts for
13 papers
RAGEN-2: Reasoning Collapse in Agentic RL
Zihan Wang, Chi Gui, Xing Jin +13
RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. Howeve…
ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
Hongjue Zhao, Haosen Sun, Jiangtao Kong +8
Activation steering, or representation engineering, offers a lightweight approach to align large language models (LLMs) by manipulating their internal activations at inference time…
Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
Pingyue Zhang, Zihan Huang, Yue Wang +11
Spatial embodied intelligence requires agents to act to acquire information under partial observability. While multimodal foundation models excel at passive perception, their capac…
ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
Qineng Wang, Wenlong Huang, Yu Zhou +8
Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation. It raises an intriguing question: do modern vision-language models…
VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
Kangrui Wang, Pingyue Zhang, Zihan Wang +13
A key challenge in training Vision-Language Model (VLM) agents, compared to Language Model (LLM) agents, lies in the shift from textual states to complex visual observations. This…
SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents
Simon Sinong Zhan, Philip Wang, Yao Liu +13
We present SENTINEL, a framework for formally evaluating the physical safety of foundation model (FM)-based embodied agents. SENTINEL is the first to provide multi-level safety eva…
MindCube: Spatial Mental Modeling from Limited Views
Qineng Wang, Baiqiao Yin, Pingyue Zhang +11
Can Vision-Language Models (VLMs) imagine the full scene from just a few views, like humans do? Humans form spatial mental models naturally, internal representations of unseen spac…
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
Zihan Wang, Kangrui Wang, Qineng Wang +15
Training large language models (LLMs) as interactive agents presents unique challenges including long-horizon decision making and interacting with stochastic environment feedback.…
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Rui Yang, Hanyang Chen, Junyu Zhang +10
Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have…
Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
Manling Li, Shiyu Zhao, Qineng Wang +12
We aim to evaluate Large Language Models (LLMs) for embodied decision making. While a significant body of work has been leveraging LLMs for decision making in embodied environments…
Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?
Qineng Wang, Zihao Wang, Ying Su +2
Recent progress in LLMs discussion suggests that multi-agent discussion improves the reasoning abilities of LLMs. In this work, we reevaluate this claim through systematic experime…
Lens: A Knowledge-Guided Foundation Model for Network Traffic
Xiaochang Li, Chen Qian, Qineng Wang +7
Network traffic refers to the amount of data being sent and received over the Internet or any system that connects computers. Analyzing network traffic is vital for security and ma…
On the Discussion of Large Language Models: Symmetry of Agents and Interplay with Prompts
Qineng Wang, Zihao Wang, Ying Su +1
Two ways has been discussed to unlock the reasoning capability of a large language model. The first one is prompt engineering and the second one is to combine the multiple inferenc…