4 citations · 5 across the 12 of their papers we have counts for
17 papers
Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents
Xiyang Wu, Zhichao Liu, Shengxin zhang +4
Long-horizon agents often struggle to recover from failures whose causes lie several steps earlier, beyond what local reflection or backtracking can resolve. We introduce BELIEFWEA…
Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress
Zongxia Li, Zhongzhi Li, Yucheng Shi +14
Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its final state passes a binary che…
ASSEMBLE: Atomic Skills for Evidence-Grounded Video Reasoning
Xiyang Wu, Zongxia Li, Shengxin Zhang +2
Complex video reasoning often depends on evidence scattered across distant moments, entities, and events, yet a correct answer alone does not reveal whether a model relied on the r…
Recursive Agentic Reasoning
Shengxin Zhang, Xiaomin Wu, Xiyang Wu +1
Test-time reasoning methods such as iterative refinement, decomposition, and repeated sampling are often evaluated in isolation, making their gains difficult to compare across mode…
Noise Floor Audit for Agent Benchmarks
Yihang Chen, Pin Qian, Su Wang +4
We audit measurement variability for 3 native tool-calling endpoints across 2 providers on the official BFCL multiple and parallel categories, using matched AST grading. At tempera…
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 +12
AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minu…
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
As LLM agents act across personal applications, web browsers, and other interfaces, their reusable skill libraries can scale to thousands of skills. This scale introduces two chall…
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…
SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models
Xiyang Wu, Guangyao Shi, Qingzi Wang +3
Vision-language-action (VLA) models enable robots to follow natural-language instructions grounded in visual observations, but the instruction channel also introduces a critical vu…
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
Zongxia Li, Hongyang Du, Chengsong Huang +8
Self-evolving has emerged as a key paradigm for improving foundational models such as Large Language Models (LLMs) and Vision Language Models (VLMs) with minimal human intervention…
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…
First Frame Is the Place to Go for Video Content Customization
Jingxi Chen, Zongxia Li, Zhichao Liu +6
What role does the first frame play in video generation models? Traditionally, it's viewed as the spatial-temporal starting point of a video, merely a seed for subsequent animation…
Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation
Zongxia Li, Yapei Chang, Yuhang Zhou +4
Evaluating open-ended long-form generation is challenging because it is hard to define what clearly separates good from bad outputs. Existing methods often miss key aspects like co…
VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
Zongxia Li, Xiyang Wu, Guangyao Shi +6
Vision-Language Models (VLMs) have achieved strong results in video understanding, yet a key question remains: do they truly comprehend visual content or only learn shallow correla…
A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
Zongxia Li, Xiyang Wu, Hongyang Du +3
Large vision-language models (VLMs) have evolved rapidly from contrastive image-text encoders and adapter-based assistants into natively multimodal foundation models that support l…