1 citations · 2 across the 5 of their papers we have counts for
Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds?
Yang Chen, Bin Wen, Danyang Peng +3
Recent multimodal agents have shown promising progress in embodied planning and web interaction. However, existing evaluations often rely on simplified tasks with limited combinato…
cs.AI2026
RLHarness: Co-evolving Procedural Skills with Reinforcement Learning for Long-horizon Multimodal Reasoning
Ziqiao Shang, Zian Xu, Ji-Chen Yan +6
Multimodal reasoning requires models to preserve visual evidence through long decision chains while selecting appropriate procedures across diverse scenarios and rules. When learni…
cs.AI2026
GraphSkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback
Ziqiao Shang, Ling-Yue Ge, Lan-Zhe Guo
External skills provide domain knowledge and procedures without updating model parameters, but flat collections obscure skill applicability, dependencies, and composition. Graphs o…