Skip to content

Author

Cheng-Ze Li

We have 6 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

SkillNEO: Non-Elitist Evolutionary Optimization of Agent Skills

Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience. Building on this, skill evolution iteratively improves skills using execution feedback. However, improvement may require several interdependent edits, so low-reward versions can sti...

En-Ze Ma, Chun-Yu Miao, Yan-Kai Chen et al. · 1 citation
Book Open access Aug 2026

Geometry-aware Test-Time Adaptation on Graphs

Test-time adaptation (TTA) has been a widely-studied paradigm for adapting well-trained models to distributionally shifted test data. Recent works extend TTA to graphs using graph augmentations and self-supervised objectives in Euclidean space. However, graph-structured data often exhibit heterogeneity where semantic s...

Ling-Wei Wei, Dou Hu, Li Sun et al. · 0 citations
#machine learning Preprint Sep 2026

EAVer: Long-Form Factuality Verification as an End-to-End Agentic Policy

This work introduces EAVer, an End-to-end Agentic Verifier that learns to control the complete response-level verification workflow as a unified policy, and construct 794 bidirectional same-trajectory preference pairs that keep claim grouping, search, and evidence fixed, enabling decision-focused Direct Preference Opti...

Ke-Ning Zheng, Ao-Ying Zheng, Zhi-Gang Chang et al. · 0 citations
#natural language process... Preprint Jun 2026

MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recovery

MEMPROBE is the first benchmark to study memory recovery directly, reconstructing the user state a system retains and scoring it against ground truth, and is seen as a step toward an environment where agents are trained to remember their users, growing more faithful the longer they know them.

En-Ze Ma, Yufan Zhou, Wei-Chieh Huang et al. · 4 citations

To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation

PriCoder is proposed, an approach that teaches LLMs to invoke private-library APIs through automatically synthesized data, and alternates between two graph operators that improves data diversity by progressively synthesizing more diverse training samples from basic ones.

Yi-Tong Zhang, Cheng-Ze Li, Rui Chen et al. · 4 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.