activity
20242026
collaborators
Showing cs.LGShow all

14 papers · 1 filter

cs.LG2026

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

Heming Zou, Qi Wang, Yun Qu +9

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. However, rollout-intensive poli…

cs.LG2026

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning

Yixiu Mao, Yun Qu, Qi Wang +2

Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, its effe…

cs.LG2026

Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex

Yun Qu, Qi Wang, Yixiu Mao +11

Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize reasoning capacity. Among existin…

cs.LG2026

Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models

Yixiu Mao, Yun Qu, Qi Wang +2

Reinforcement learning (RL) finetuning has become a key technique for enhancing the reasoning abilities of large language models (LLMs). However, its effectiveness critically depen…

cs.LG2025

Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning

Yixiu Mao, Yun Qu, Qi Wang +1

Offline reinforcement learning (RL) suffers from extrapolation errors induced by out-of-distribution (OOD) actions. To address this, offline RL algorithms typically impose constrai…

cs.LG2025

Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning

Heming Zou, Yixiu Mao, Yun Qu +2

Supervised fine-tuning (SFT) is a commonly used technique to adapt large language models (LLMs) to downstream tasks. In practice, SFT on a full dataset is computationally expensive…