1 citations · 1 across the 6 of their papers we have counts for
8 papers
Harness Evolution as Learning: Approximation, Generalization, and Optimization Limits of Self-Improving Personal Agents
Zeyu Gan, Zixuan Gong, Yong Liu
As the capabilities of large language models (LLMs) continue to advance, increasing attention is turning to how to translate their abilities into useful behavior. Personal agents b…
Normalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training
Zixuan Gong, Zeyu Gan, Jiaye Teng +1
Matrix optimizers have emerged as a promising direction, with Muon standing out as a prominent design. Revisiting Muon through its full-Gram representation, we observe that it join…
Statistical Priors for Implicit Preferences: Decoupling Skill Selection as a Local Harness in Personal Agents
Zeyu Gan, Huayi Tang, Yong Liu
As Large Language Model (LLM) capabilities advance, locally deployed personal agents relying on API-based remote models and external skills have emerged as a novel paradigm. With t…
Beyond the Black Box: A Survey on the Theory and Mechanism of Large Language Models
Zeyu Gan, Ruifeng Ren, Wei Yao +9
The rapid emergence of Large Language Models (LLMs) has precipitated a profound paradigm shift in Artificial Intelligence, delivering monumental engineering successes that increasi…
Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents
Guoqing Wang, Sunhao Dai, Guangze Ye +5
Large language model (LLM)-based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments through tool use,…
Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought
Zeyu Gan, Hao Yi, Yong Liu
Test-time scaling, primarily manifested through multi-step Chain-of-Thought (CoT) reasoning via Reinforcement Learning (RL), has emerged as a pivotal paradigm for enhancing the rea…
Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
Zeyu Gan, Yun Liao, Yong Liu
Test-time scaling, which is also often referred to as slow-thinking, has been demonstrated to enhance multi-step reasoning in large language models (LLMs). However, despite its wid…
Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective
Zeyu Gan, Yong Liu
Synthetic data has become a pivotal resource in post-training tasks for large language models (LLMs) due to the scarcity of high-quality, specific data. While various methods have…