12 papers
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Zongxia Li, Zhongzhi Li, Yucheng Shi +10
The paper presents Long-Horizon-Terminal-Bench, a benchmark of 46 extended tasks with fine-grained intermediate rewards to evaluate AI agents' long-horizon planning and debugging a…
COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows
Zongxia Li, Dawei Liu, Fuxiao Liu +6
Agents are increasingly used to construct workflows and assist humans in completing recurring tasks more efficiently. As these workflows become repeated and domain-specific, agent…
Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models
Qingzi Wang, Xiyang Wu, Guangyao Shi +3
Safe social navigation requires robots to distinguish people from ordinary obstacles and to react before danger becomes imminent. We show that pretrained Vision-Language-Action (VL…
Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
Dawei Liu, Zongxia Li, Hongyang Du +4
Modern LLM agents increasingly rely on reusable skills, and as they interact with personal applications, web browsers, and other interfaces, skill libraries can scale to thousands…
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
Xiyang Wu, Zongxia Li, Guangyao Shi +5
Long horizon interactive environments are a testbed for evaluating agents skill usage abilities. These environments demand multi step reasoning, the chaining of multiple skills ove…
MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models
Xiyang Wu, Zongxia Li, Jihui Jin +7
Vision Language Models (VLMs) perform well on standard video tasks but struggle with physics-related reasoning involving motion dynamics and spatial interactions. We present a nove…