7 papers · 1 filter
Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature
Zheng Liu, Mengjie Liu, Siwei Wen +4
Using entropy as a measure of heterogeneity to guide optimization has emerged as a crucial research direction in Reinforcement Learning for LLMs. However, existing methods typicall…
Let's Verify Math Questions Step by Step
Chengyu Shen, Zhen Hao Wong, Runming He +8
Large Language Models (LLMs) have recently achieved remarkable progress in mathematical reasoning. To enable such capabilities, many existing works distill strong reasoning models…
Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL
Qifeng Cai, Hao Liang, Chang Xu +3
The data-centric paradigm has emerged as a pivotal direction in artificial intelligence (AI), emphasizing the role of high-quality training data. This shift is especially critical…
PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning
Keer Lu, Chong Chen, Xili Wang +3
Large Language Models (LLMs) have shown remarkable advancements in tackling agent-oriented tasks. Despite their potential, existing work faces challenges when deploying LLMs in age…
Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL Queries
Zhengren Wang, Dongwen Yao, Bozhou Li +7
The proliferation of unstructured data poses a fundamental challenge to traditional database interfaces. While Text-to-SQL has democratized access to structured data, it remains in…
DARO: Difficulty-Aware Reweighting Policy Optimization
Jingyu Zhou, Lu Ma, Hao Liang +3
Recent advances in large language models (LLMs) have shown that reasoning ability can be significantly enhanced through Reinforcement Learning with Verifiable Rewards (RLVR). Group…