13 papers
Has GPT-6-Astra Achieved Embodied Intelligence?
SenseNova, Joint Research Team, : +60
GPT-6-Astra demonstrates a level of competence in robotic manipulation and navigation that challenges the conventional paradigm of building specialized models for individual tasks…
Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents
Cong Pang, Jiaqi Su, Chengrui Wu +13
Deep search enables language agents to solve complex information-seeking tasks through iterative web exploration. However, developing robust open-source agents remains challenging…
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…
When History Is Multimodal: Rethinking Context Management for Long-Horizon Agents
Jiaqi Su, Cong Pang, Jiawei Hong +4
Long-horizon agents need a context manager to compress growing interaction histories into a bounded working context, via passive strategies or active strategies that decide how mem…
Paint What You See: Benchmarking Dexterous Visual Tool Use in Multimodal Agents
Shudong Liu, Dongyang Chen, Enci Zhang +3
Evaluation is shifting from static QA toward agentic settings where models act through external tools. We identify a critical yet underexplored capability within this space - dexte…
OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories
Changhao Xiang, Shilin Zhang, Zheng Ma +8
Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe learns this capabili…
ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories
Siyuan Luo, Nairong Zheng, Lin Zhou +6
Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution--properties absent from exist…
InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward
Zhiwei Ning, Wenwen Tong, Xiangli Kong +12
While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-cent…
GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
Jinhao Jing, Zheng Ma, Jinwei Liang +9
Large Multimodal Models (LMMs) often struggle with geometric reasoning due to visual hallucinations and a lack of mathematically precise Chain-of-Thought (CoT) data. To address thi…
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…
FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair
Ruize Ma, Yilei Jiang, Shilin Zhang +7
Multimodal Automated Program Repair (MAPR) extends traditional program repair by requiring models to jointly reason over source code, textual issue descriptions, and visual artifac…
ICA: Information-Aware Credit Assignment for Visually Grounded Long-Horizon Information-Seeking Agents
Cong Pang, Xuyu Feng, Yujie Yi +8
Long-horizon reinforcement learning for information seeking agents remains difficult because terminal rewards reveal whether the final answer is correct, but not which acquired inf…
Towards Fine-Grained Recognition with Large Visual Language Models: Benchmark and Optimization Strategies
Cong Pang, Hongtao Yu, Zixuan Chen +2
Large Vision Language Models (LVLMs) have made remarkable progress, enabling sophisticated vision-language interaction and dialogue applications. However, existing benchmarks prima…