← Search

Jiangweizhi Peng

2 accepted papers

2026

HiPER: Hierarchical Plan–Execute RL for Multi-Turn LLM Agents

ICML 2026poster

Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful feedback. Most existing reinforcement learning (RL) methods …

Cited by 0SourceScholar
2025

Inference-Time Alignment of Diffusion Models with Direct Noise Optimization

ICML 2025poster

In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of images. The central goal of the alignment problem is to adjust the distribution…

Cited by 0SourcePDFScholar