14 papers
OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools
Chenyang Yan, Yingying Zhang, Kanzhi Cheng +21
We introduce OpenMobile-2, a near-frontier mobile agent with fully open training environments and recipes. We make three key advances: (1) Diverse environments with simulated comme…
Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training
Xinyu Che, Hang Yan, Yanchen Liu +5
Predicting how an environment will change before acting is a natural route to better decision making for agents. Recent post-training methods therefore require agents to predict th…
GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions
Xinyu Che, Yunfei Ge, Shihao Li +9
Coding agents can modify and test code across large software projects. Game development is a domain where agents must implement gameplay rules. A game can end in a valid state even…
Self-Specialized Teachers for Domain Post-Training
Yifei Li, Rongman Xu, Lingling Zhang +5
Target-only post-training can improve performance in a specialized domain while degrading behaviors that a general-purpose base model acquired before adaptation. We study this prob…
Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories
Yifei Li, Heng Wang, Lingling Zhang +5
Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or environment…
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
Qiushi Sun, Kanzhi Cheng, Yian Wang +20
Computer-using agents (CUAs) are advancing rapidly across the digital world. A CUA trajectory records the agent's actions, states, and reasoning. Verifying whether it fulfilled the…
MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?
Xinyu Che, Junqi Xiong, Yunfei Ge +9
Abundant procedural knowledge on the Web holds great potential for helping agents solve long-horizon tasks. However, such knowledge is often multimodal, heterogeneous, noisy, and i…
ChartAct: A Benchmark for Dynamic Chart Understanding
Muye Huang, Lin Wu, Lingling Zhang +5
Charts are widely used to present complex data for analysis and decision making. Existing chart understanding benchmarks mainly focus on static charts, but real-world charts are of…
OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
Kanzhi Cheng, Zehao Li, Zheng Ma +11
Mobile agents powered by vision-language models have demonstrated impressive capabilities in automating mobile tasks, with recent leading models achieving a marked performance leap…
TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents
Hang Yan, Xinyu Che, Fangzhi Xu +7
Recent advances in autonomous LLM agents demonstrate their ability to improve performance through iterative interaction with the environment. We define this paradigm as Test-Time I…
SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding
Yifei Li, Lingling Zhang, Hang Yan +4
Traditional knowledge graph (KG) embedding methods aim to represent entities and relations in a low-dimensional space, primarily focusing on static graphs. However, real-world KGs…
MUR: Momentum Uncertainty guided Reasoning for Large Language Models
Hang Yan, Fangzhi Xu, Rongman Xu +8
Large Language Models have achieved impressive performance on reasoning-intensive tasks, yet optimizing their reasoning efficiency remains an open challenge. While Test-Time Scalin…
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
Fangzhi Xu, Hang Yan, Chang Ma +6
Advancing LLM reasoning skills has captivated wide interest. However, current post-training techniques rely heavily on supervisory signals, such as outcome supervision or auxiliary…
-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
Fangzhi Xu, Hang Yan, Chang Ma +4
Inference-time optimization scales computation to derive deliberate reasoning steps for effective performance. While previous search-based strategies address the short-sightedness…