collaborators

6 papers

cs.LG2026

Transformers Provably Learn to Internalize Chain-of-Thought

Yixiao Huang, Hanlin Zhu, Zixuan Wang +4

Chain-of-Thought (CoT) prompting substantially improves the sample efficiency of transformers, reducing the complexity of tasks like parity learning from exponential to polynomial…

cs.LG2026

Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought

Hanlin Zhu, Shibo Hao, Zhiting Hu +3

Previous work shows that the chain of continuous thought (continuous CoT) improves the reasoning capability of large language models (LLMs) by enabling implicit parallel thinking,…

cs.LG2025

Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought

Hanlin Zhu, Shibo Hao, Zhiting Hu +3

Large Language Models (LLMs) have demonstrated remarkable performance in many applications, including challenging reasoning problems via chain-of-thoughts (CoTs) techniques that ge…

cs.AI2025

GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments

Hanlin Zhu, Tianyu Guo, Song Mei +4

As LLMs are increasingly deployed as agents, agentic reasoning - the ability to combine tool use, especially search, and reasoning - becomes a critical skill. However, it is hard t…

cs.LG2025

Safe Learning Under Irreversible Dynamics via Asking for Help

Benjamin Plaut, Juan Liévano-Karim, Hanlin Zhu +1

Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, w…

cs.LG2025

Avoiding Catastrophe in Online Learning by Asking for Help

Benjamin Plaut, Hanlin Zhu, Stuart Russell

Most learning algorithms with formal regret guarantees assume that all mistakes are recoverable and essentially rely on trying all possible behaviors. This approach is problematic…