7 papers
Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents
Xinze Li, Yuhang Zang, Yixin Cao +1
Markdown skill libraries for LLM agents ship as free-form prose, forcing the agent to re-derive both the input schema and the concrete invocation syntax on every retrieval. We obse…
The Network Structure of Mathlib
Xinze Li, Nanyun Peng, Simone Severini +1
The ongoing development of Lean 4's Mathlib has produced a macroscopic structural complexity that interweaves logical, mathematical, and infrastructural dependencies. We present a…
Astrolabe: A Content-Addressable Hypergraph for Semantic Knowledge Management
Xinze Li
Existing knowledge management tools either preserve prose but lose structural relationships, or capture relationships but restrict edge semantics to fixed vocabularies. We introduc…
EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents
Xinze Li, Ziyue Zhu, Siyuan Liu +4
We introduce EMemBench, a programmatic benchmark for evaluating long-term memory of agents through interactive games. Rather than using a fixed set of questions, EMemBench generate…
What Do LLM Agents Know About Their World? Task2Quiz: A Paradigm for Studying Environment Understanding
Siyuan Liu, Hongbang Yuan, Xinze Li +3
Large language model (LLM) agents have demonstrated remarkable capabilities in complex decision-making and tool-use tasks, yet their ability to generalize across varying environmen…
Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks
Yixin Cao, Shibo Hong, Xinze Li +24
Large Language Models (LLMs) are advancing at an amazing speed and have become indispensable across academia, industry, and daily applications. To keep pace with the status quo, th…