17 papers
4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented Agents
Yanhao Jia, Yi Zhu, Yiran Zhong +7
Humans efficiently process multimodal streams spanning hours to years, building persistent, fine-grained spatiotemporal memories that support reasoning about and predicting long-ho…
Trace2World: Reconstructing App Worlds from Real Interaction Traces for Scalable GUI Agent Training
Zezhou Wang, Hanzhang Zhou, Panrong Tong +5
Scaling GUI reinforcement learning requires environments that preserve real-app behavior. Yet coupling behavior inference with coding can turn partial traces into runnable mocks wi…
OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use
Hanzhang Zhou, Long Li, Quyu Kong +12
Computer use has reached a turning point: the focus is expanding from GUI-only interaction to systems that complete tasks on users' computers through visual and programmatic interf…
MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments
Panrong Tong, Quyu Kong, Pengxiang Li +12
Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool use, but scaling this success to GUI agents remains challengin…
From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks
Yuchen Sun, Chenglin Cai, Gongjie Zhang +8
Mobile GUI agents complete tasks using GUI actions like taps and swipes. These actions are broadly applicable across applications, but reaching a navigation interface. A single dee…
Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents
Tingyu Qu, Weigao Sun, Yuecheng Liu +23
The rapid progression of large language models is extending AI from passive content generation into the active workflows of engineering and scientific discovery. This shift raises…
ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning
Ming Ma, Yi Zhu, Yiran Zhong +7
Long-horizon agentic tasks require an agent to modify an environment through a sequence of tool calls, with success determined by the final state. The standard recipe assigns a sin…
Block-Sparse Attention with Semantic-Geometric Decoupled Routing
Xinwei Long, Weigao Sun, Weibo Gao +6
Long-context inference has become a defining capability of large language models, but exact dense attention remains costly due to its quadratic scaling with sequence length. Block-…
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…
MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks
Yi Zhu, Xiongwei Wu, Qiyi Wang +8
Mobile planning requires a central agent to coordinate tools, persistent user context, reusable procedures, and specialized sub-agents while adapting to execution feedback. Evaluat…
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
Hanzhang Zhou, Panrong Tong, Xu Zhang +13
GUI agents have the potential to become a general purpose executor over existing digital devices. To advance them toward real-world use, we envision agents that operate reliably on…
Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents
Ming Ma, Yi Zhu, Yiran Zhong +7
Omni-modal agents must seek evidence across video, audio, web pages, and computation to answer questions. Their main bottleneck is planning: noisy multimodal observations accumulat…
What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States
Chen Liu, Ling Chen, Hanzhang Zhou +7
Mobile GUI agents increasingly face long-horizon tasks that require reading, updating, and reusing task-relevant data across pages and applications. Existing methods treat memory l…
One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding
Chen Liu, Ling Chen, Hanzhang Zhou +5
MLLM-based GUI grounding methods commonly formulate target localization as autoregressive coordinate generation, enabling models to leverage the strong instruction-following and se…
MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments
Quyu Kong, Xu Zhang, Zhenyu Yang +10
Among existing online mobile-use benchmarks, AndroidWorld has emerged as the dominant benchmark due to its reproducible environment and deterministic evaluation; however, recent ag…
MAI-UI Technical Report: Real-World Centric Foundation GUI Agents
Hanzhang Zhou, Xu Zhang, Panrong Tong +8
The development of GUI agents could revolutionize the next generation of human-computer interaction. Motivated by this vision, we present MAI-UI, a family of foundation GUI agents…
UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning
Liangyu Chen, Hanzhang Zhou, Chenglin Cai +10
GUI grounding, which maps natural-language instructions to actionable UI elements, is a core capability of GUI agents. Prior works largely treats instructions as a static proxy for…