8 papers
ReSight: Task-Driven Self-Improving Memory for Embodied Agents
Lirong Che, Yang Chen, Yimeng Su +8
Robots can use historical observations to answer spatiotemporal queries in familiar environments, but the presence of relevant evidence does not imply that existing tools support t…
HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
Yang Chen, Lirong Che, Zhenyu Huang +7
Embodied navigation requires agents to ground instructions or object goals in spatial observations and translate plans into successful execution. As multimodal large language model…
Language-Guided Terrain-Adaptive Neural MPC for Autonomous Traversal of Articulated Tracked Robots
Zhenfeng Gan, Yanbo Chen, Lirong Che +4
In urban search and rescue, articulated tracked robots (ATRs) must traverse structured but contact-rich environments such as stairwells and cluttered building interiors. Reliable a…
CoCoBench: A Cooperative Coordination Benchmark for Embodied Multi-Agent Task Planning
Yang Chen, Ye-Xin Xie, Lirong Che +8
Agent systems powered by multimodal large language models (MLLMs) have advanced rapidly in recent years, yet existing embodied-agent benchmarks still lack fine-grained diagnostics…
The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning
Haolong Qian, Xianliang Yang, Yinuo ma +6
Knowledge distillation from powerful reasoning models is widely used to improve Small Language Models (SLMs) on mathematical reasoning, often assuming that traces with higher rewar…
DemoEvolve: Demonstration-Guided Harness Evolution under Sparse Feedback
Lirong Che, Yuzhe yang, Peiwen lin +4
Harness evolution enables frozen language model agents to adapt to unfamiliar tasks by modifying the external programs that govern their behavior. For long-horizon tasks, each roll…
PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding
Lirong Che, Zhenfeng Gan, Yanbo Chen +2
Embodied agents for creative tasks like photography must bridge the semantic gap between high-level language commands and geometric control. We introduce PhotoAgent, an agent that…
MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks
Lirong Che, Shuo Wen, Shan Huang +5
Real-world robotic tasks are long-horizon and often span multiple floors, demanding rich spatial reasoning. However, existing embodied benchmarks are largely confined to single-flo…