Nan Cheng
Nan Cheng has 2 papers in our library, in 2025–2026, most of them on Reasoning; often with Feng Chen, Surya Ganguli, Yang Deng.
OpenAlex · h-index 3 · 10 works · 16 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 9 times in our library · ⭐ Paper Stars ranking: #12056
Affiliations
🏢China Mobile Group Design Institute Co., Ltd.Beijing ·
China2009–2026 · 9 papers🏢China MobileBeijing ·
China2026 · 1 paper
Fields, topics and concepts
📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksComputer Science · 2 worksArts and Humanities · 1 workLanguage and Linguistics · 1 work
🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1 work
Works by year
2020s
Papers
- Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning (2025 · 9 citations)
Test-time strategies such as pass@N let a model try N times while a verifier checks each attempt. Fine-tuning, however, usually ignores this. The authors ask whether standard supervised fine-tuning with cross-entropy (CE) loss suits such strategies. - Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents (2026 · 1 citation)
LLM agents that solve multi-step interactive tasks usually feed the model the entire, ever-growing record of past observations and actions.
Co-authors here
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
- Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2025
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/nan-cheng/