27 papers
UniW(A)M: A Unified Mixture-of-Experts Framework for World and World-Action Models
Jingbo Xu, Jianjie Fang, Zhuohang Li +9
World models (WMs) and world-action models (WAMs) focus on future world prediction and executable action generation, respectively. Although these models learn shared physical dynam…
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
Yongqi Tong, Pan Wang, Hang Wang +4
Reusable skills give agents transferable procedural knowledge, making scalable acquisition essential for extending agents beyond prior experience. Existing methods face two limitat…
IMPACT: Attention Is the Interaction Map for Scalable Interaction-Aware World Model Training
Rongze Tang, Jianjie Fang, Zhaolu Wang +8
World models have made remarkable progress in action-conditioned future prediction for embodied agents, yet still struggle to model physically plausible interactions. Existing appr…
CAER: Causal Action Effect Reweighting for World Model Training
Jianjie Fang, Xvyuan Liu, Ziyou Wang +9
World models are becoming core infrastructure for embodied intelligence, with action-conditioned video generation providing controllable predictions of how scenes evolve after agen…
DriftingVLA: Native One-Step Vision-Language-Action Generation via Per-Dimension Temporal Drifting
Yuxuan Gao, Shiqi Zhang, Yedong Shen +6
Conventional flow-based vision-language-action (VLA) models support expressive continuous action generation but rely on multi-step refinement to produce each action chunk, increasi…
DensityKV: Density-Guided KV Cache Compression for Long Video Generation
Wenqu Zhao, Xuemin Chi, Xin Zhang +6
Autoregressive video diffusion models enable streaming generation through sliding-window attention, but each generated block is conditioned on previously generated content, causing…
TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction
Lei Jin, Yiding Ma, Xin Zhang +3
World Action Models (WAMs) combine future-state prediction with robot action generation, but existing approaches largely rely on visual futures. Visual prediction captures scene st…
Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Context
Yiwen Zhao, Zhihao Wen, Yuchen Mao +5
User-facing tool agents must coordinate dialogue and tool use as user goals unfold over multiple turns. Yet interactive reinforcement learning typically reduces each rollout to a t…
ReTouch: Empowering Contact-Rich Dexterous Manipulation with Online-Refined Tactile Prediction
Shiqi Zhang, Xin Zhang, Yedong Shen +9
Fusing tactile signals has proven effective for contact-rich manipulation, enabling robots to perceive contact states and adapt to rapidly changing physical interactions. Yet effec…
Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction
Pan Wang, Yihao Hu, Hang Wang +6
Self-correction is particularly useful when a failure constrains the next repair. Coding agents benefit from this property because compilers, tests, and execution traces turn many…
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
Wanying Qu, Qinghua Mao, Yu Li +12
The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime contro…
WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory and In-Context Learning
Haisheng Su, Zongdai Liu, Xin Jin +13
World Action Models (WAMs) offer a promising paradigm for robotic manipulation by jointly modeling visual state transitions and robot actions. However, existing WAMs are constraine…
Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control
Jianjie Fang, Yongyan Xu, Ziyou Wang +13
World models are rapidly becoming a core infrastructure for embodied intelligence and interactive agents: they provide controllable simulators in which agents can perceive, act, fo…
GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation
Yuan Zhang, Shiqi Zhang, Yedong Shen +11
Vision-Language-Action (VLA) models achieve strong benchmark performance but still struggle in real-world deployment with unseen objects, background shifts, and different robot emb…
SEAL: Synergistic Co-Evolution of Agents and Learning Environments
Yihao Hu, Zhihao Wen, Xiujin Liu +3
Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. W…
Draw2Think: Harnessing Geometry Reasoning through Constraint Engine Interaction
Juncheng Hu, Jiawei Du, Xin Zhang +1
Vision-language models solve geometry problems with rising accuracy, yet their intermediate states remain latent and unverifiable: a relation expressed in textual reasoning or draw…
WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform
Yu Shang, Yinzhou Tang, Yiding Ma +26
World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, ex…
WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation
Baining Zhao, Jiacheng Xu, Weicheng Feng +13
Aerial vision-language navigation (VLN) requires agents to follow natural-language instructions through closed-loop perception and action in 3D environments. We argue that aerial V…
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
Haonan Dong, Qiguan Feng, Kehan Jiang +3
Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly drawn growing research attentio…
PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interaction
Xin Zhang, Yabo Chen, Yijie Fang +5
Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing video generation methods provi…
WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
Yu Shang, Zhuohang Li, Yiding Ma +18
While world models have emerged as a cornerstone of embodied intelligence by enabling agents to reason about environmental dynamics through action-conditioned prediction, their eva…
RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL
Yinzhou Tang, Yu Shang, Yinuo Chen +8
Achieving generalizable embodied policies remains a key challenge. Traditional policy learning paradigms, including both Imitation Learning (IL) and Reinforcement Learning (RL), st…
LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE
Yu Shang, Lei Jin, Yiding Ma +4
Video-based world models hold significant potential for generating high-quality embodied manipulation data. However, current video generation methods struggle to achieve stable lon…
MoWM: Mixture-of-World-Models for Embodied Planning via Latent-to-Pixel Feature Modulation
Yangcheng Yu, Xin Jin, Yu Shang +4
Embodied action planning is a core challenge in robotics, requiring models to generate precise actions from visual observations and language instructions. While video generation wo…