← Search

Zhiyi Lyu

2 accepted papers

2025

Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs

NeurIPS 2025poster

Large Language Models (LLMs) with inference-time scaling techniques show promise for code generation, yet face notable efficiency and scalability challenges. Construction-based tree-search methods suffer from rapid growth in tree size, high token consumption, and lack of anytime property. In contras…

Cited by 0SourceScholar
2025

Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning

ICML 2025poster

Online fine-tuning vision-language model (VLM) agents with reinforcement learning (RL) has shown promise for equipping agents with multi-step, goal-oriented capabilities in dynamic environments. However, their open-ended textual action space and non-end-to-end nature of action generation present sig…