Author

Zhi Zheng

h-index 6 View on Semantic Scholar

We have 6 of 11 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.

Preprint Oct 2026

Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?

Learning from experience is essential for LLM agents to adapt to unfamiliar and dynmaic environments. Evaluating this ability is therefore important for understanding how effectively agents acquire and use new knowledge. Existing benchmarks have sought to evaluate this ability, but they primarily evaluate tasks whose r...

Yi-Bo Li, Jin-Hang Qiu, Zhi Zheng et al. · 1 citation

#machine learning Preprint Sep 2026

AIM-ZO: Activation-Informed Subspace Maintenance for Zeroth-Order LLM Fine-Tuning

AIM-ZO is proposed, a ZO fine-tuning method based on Activation-Informed Subspace Maintenance that uses forward activations as local directional information and continuously integrates them into a broad, evolving subspace over training.

Yue Xie, Zhi Zheng, Yun-Peng Ba et al. · 0 citations

#machine learning Preprint Sep 2026

GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills

GraphSkillEvo is introduced, a population-based evolutionary optimization framework with mutation and crossover operators for graph-structured skills that enables broader and more comprehensive exploration of the structured skill space than purely LLM-based iterative self-refinement.

Rui Sun, Zhi Zheng, Zhen-Kun Wang et al. · 0 citations

Preprint Aug 2026

Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction Merging

This work proposes Hyper-ES, a subspace-based ES framework that avoids the weakness of ES in full-parameter search while exploiting its strength in low-dimensional optimization, and consistently outperforms GRPO-LoRA while requiring 10% fewer space-consuming gradient updates.

Yuntian Gu, Zhi Zheng, Yun-Peng Ba et al. · 0 citations

#machine learning Preprint Aug 2026

Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO

These findings position ES as a distinct reasoning post-training paradigm rather than a less effective, memory-efficient alternative to GRPO, and study how hyperparameter design affects the effectiveness of ES, demonstrating that ES requires a smaller population size in a larger LLM.

Yunpeng Ba, Zhi Zheng, Yue Xie et al. · 0 citations

#machine learning Preprint Aug 2026

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

Reinforcement Learning (RL) has been promising in single-turn LLM fine-tuning. However, long-horizon agentic reasoning introduces increasingly branching interactions and sparse rewards, exposing several limitations of RL: its heavyweight backpropagation-based training stack makes it impractical to fine-tune larger LLMs...

Zhi Zheng, Rong-Sheng Chen, Yunpeng Ba et al. · 1 citation