3 papers
physics.soc-ph2026
Lost in Aggregation: A Multi-Scale Diagnostic Benchmark for LLM Spatial Navigation
Yuhan jiang, Peng Luo, Liqiu Meng
Large language models (LLMs) are increasingly deployed as planners and assistants in tasks with inherent spatial structure, such as navigation and route planning, yet they remain b…
cs.AI2026
Constructing coherent spatial memory in LLM agents through graph rectification
Puzhen Zhang, Xuyang Chen, Yu Feng +2
Given a map description through global traversal navigation instructions, an LLM can often infer the implicit spatial layout and answer user queries by providing shortest paths. Ho…
math.CO2025
Rowmotion and Echelonmotion
Colin Defant, Yuhan Jiang, Rene Marczinzik +4
Given a linear extension of a finite poset , we consider the permutation matrix indexing the Schubert cell containing the Cartan matrix of with respect to . This yi…