8 papers
Project2Task: Graph-Guided Project-Level Planning for Autonomous Research
Huirui Xu, Runtao Xu, Shuo Ren +1
Research agents can increasingly search literature, propose hypotheses, generate code, run experiments, and draft manuscripts from a single topic. However, a research project is no…
EviGraph: Evidence-Guided Autonomous Research Agents
Zhenjiang Ren, Ruiji Li, Xujing Zhang +3
Autonomous research agents can generate hypotheses, execute experiments, and draft manuscripts, yet their outputs often contain unsupported claims and inconsistencies between resea…
SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios
Juntao Cheng, Wanyue Zhang, Zhiwei Yu +7
Tangible control interfaces (TCIs), such as appliance panels, remotes, elevators, and embedded GUIs, are a fundamental component of everyday human-built environments. Interacting w…
World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning
Wanyue Zhang, Wenxiang Wu, Wang Xu +6
Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scene…
Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
Shuo Ren, Can Xie, Pu Jian +3
As scientific research becomes increasingly complex, innovative tools are needed to manage vast data, facilitate interdisciplinary collaboration, and accelerate discovery. Large la…
Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questions
Pu Jian, Donglei Yu, Wen Yang +2
In visual question answering (VQA) context, users often pose ambiguous questions to visual language models (VLMs) due to varying expression habits. Existing research addresses such…