Siqian Tong — accepted AI-conference papers

2026

AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning

Siqian Tong, Xuan Li, Yiwei Wang, Baolong Bi, Yujun Cai, Shenghua Liu +2

ICML 2026poster

Large Audio Language Models (LALMs) excel at perception but struggle with complex reasoning requiring precise acoustic measurements. While external tools can extract fine-grained features like exact tempo or pitch, effective integration remains challenging: naively using all tools causes information…

Cited by 0 Source ↗Scholar ↗

2026

Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning

Baolong Bi, Shenghua Liu, Yiwei Wang, Siqian Tong, Lingrui Mei, Yuyao Ge +3

ICML 2026spotlight

Recent advances in reinforcement learning (RL) have significantly improved the complex reasoning capabilities of large language models (LLMs). Despite these successes, existing methods mainly focus on single-domain RL (e.g., mathematics) with verifiable rewards (RLVR), and their reliance on purely o…

Cited by 0 Source ↗Scholar ↗