8 papers
Neos: Learning to Interleave Search and Visual Reasoning
Ekko He, Jack Hong, Shilin Yan +8
Recent multimodal deep search agents have advanced tool use and visual content retrieval, yet they still struggle to convert intermediate visual evidence into actionable guidance f…
LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation
Chenrun Wang, Mingxuan Zhu, Tiancheng Huang +6
With the rapid advancement of large language models (LLMs), research idea generation has attracted increasing attention. Existing approaches enable LLMs to retrieve relevant litera…
XS-VLA: Teaching Tiny Vision-Language-Action Models with Spatial Supervision and Demonstration Conditioning
Iok Tong Lei, Ying Jie Yap, Wei Huang +5
How can richer training supervision improve robot control while keeping the deployed policy compact? We present XS-VLA, a staged training framework using teacher-derived spatial la…
ACE: Agentic Control for Embodied Manipulation via Zero-shot Workflow Reasoning
Iok Tong Lei, QianZhi Li, Ying Jie Yap +5
General-purpose manipulation requires both semantic reasoning over task constraints and reliable execution of contact-rich actions. We present ACE, an agentic manipulation harness…
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
Haoran Sun, Wenjie Li, Yujie Zhang +8
Medical agent systems are increasingly expected to support interactive clinical decision making rather than only static question answering. In such settings, effective agents must…
MedScope: Incentivizing "Think with Videos" for Clinical Reasoning via Coarse-to-Fine Tool Calling
Wenjie Li, Yujie Zhang, Haoran Sun +11
Long-form clinical videos are central to visual evidence-based decision-making, with growing importance for applications such as surgical robotics and related settings. However, cu…
RSAgent: Learning to Reason and Act for Text-Guided Segmentation via Multi-Turn Tool Invocations
Xingqi He, Yujie Zhang, Shuyong Gao +6
Text-guided object segmentation requires both cross-modal reasoning and pixel grounding abilities. Most recent methods treat text-guided segmentation as one-shot grounding, where t…
Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection
Fanrui Zhang, Qiang Zhang, Sizhuo Zhou +10
Existing image forgery detection (IFD) methods either exploit low-level, semantics-agnostic artifacts or rely on multimodal large language models (MLLMs) with high-level semantic k…