Author

Liangming Pan

Observed name: Pan, Liangming

Institutions: Peking University, Beijing Academy of Artificial Intelligence

Observed institutions: University of California, Santa Barbara, Peking University, Beijing Academy of Artificial Intelligence

OpenAlex ID: A5140755923

Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement

2024 · Yin, Xunjian, Wang, Xinyi, et al. · arXiv (Cornell University) · 2

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units

2026 · Chen, Jianhui, Luo, Yuzhang, et al. · arXiv (Cornell University) · 1

From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution

2026 · Luo, Yuzhang, Wang, Chenpeng, et al. · arXiv (Cornell University)

LEDOM: Reverse Language Model

2026 · Association for Computational Linguistics 2026, Cheng, Sitao, et al. · Underline Science Inc.

Towards Intrinsic Interpretability of Large Language Models: A Survey of Design Principles and Architectures

2026 · Association for Computational Linguistics 2026, Gao, Yutong, et al. · Underline Science Inc.

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures

2026 · Association for Computational Linguistics 2026, Chen, Jianhui, et al. · Underline Science Inc.

Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures

2026 · Gao, Yutong, Meng, Qinglin, et al. · arXiv (Cornell University)

Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems

2026 · Zhou, Ruiwen, Song, Maojia, et al. · arXiv (Cornell University)

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures

2026 · Hu, Yi, Gu, Jiaqi, et al. · arXiv (Cornell University)

Works count: 9

Citation count: 3

H-index: 1

I10-index: