7 papers
WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents
Yehang Zhang, Jianchong Su, Haojian Huang +7
To assist humans over extended periods in real homes, embodied agents must remember user routines, world states, and past interactions. Existing long-term memory benchmarks mainly…
RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes
Leyi Wu, Yifan Zhao, Jinjie Zhang +11
Vision-Language Models (VLMs) have shown strong visual understanding and are increasingly deployed in embodied AI systems, where reliable perception under real conditions is essent…
Affordance Agent Harness: Verification-Gated Skill Orchestration
Haojian Huang, Jiahao Shi, Yinchuan Li +1
Affordance grounding requires identifying where and how an agent should interact in open-world scenes, where actionable regions are often small, occluded, reflective, and visually…
Find, Fix, Reason: Context Repair for Video Reasoning
Haojian Huang, Chuanyu Qin, Yinchuan Li +1
Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's kno…
STAR: Mitigating Cascading Errors in Spatial Reasoning via Turn-point Alignment and Segment-level DPO
Pukun Zhao, Longxiang Wang, Chen Chen +4
Structured spatial navigation is a core benchmark for Large Language Models (LLMs) spatial reasoning. Existing paradigms like Visualization-of-Thought (VoT) are prone to cascading…
EvoEmpirBench: Dynamic Spatial Reasoning with Agent-ExpVer
Pukun Zhao, Longxiang Wang, Miaowei Wang +3
Most existing spatial reasoning benchmarks focus on static or globally observable environments, failing to capture the challenges of long-horizon reasoning and memory utilization u…