18 papers
Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection
Senjie Jin, Peixin Wang, Boyang Liu +8
While token-level entropy is commonly recognized as effective for credit assignment in text-only reinforcement learning with verifiable rewards (RLVR), it remains unclear whether t…
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
Yuming Yang, Mingyoung Lai, Wanxu Zhao +13
Long chain-of-thought (CoT) trajectories provide rich supervision signals for distilling reasoning from teacher to student LLMs. However, both prior work and our experiments show t…
Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
Junjie Ye, Changhao Jiang, Zhengyin Du +8
Effective tool use is essential for large language models (LLMs) to interact with their environment. However, progress is limited by the lack of efficient reinforcement learning (R…
SpeechRole: A Large-Scale Dataset and Benchmark for Evaluating Speech Role-Playing Agents
Changhao Jiang, Jiajun Sun, Yifei Cao +15
Speech is essential for realistic role-playing, yet existing work on role-playing agents largely centers on text, leaving Speech Role-Playing Agents (SRPAs) underexplored and witho…
Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective
Zhihao Zhang, Qiaole Dong, Qi Zhang +12
Post-training algorithms such as Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) are widely used to adapt (multimodal) large language models to downstream tasks. W…
ChartE: A Comprehensive Benchmark for End-to-End Chart Editing
Shuo Li, Jiajun Sun, Zhekai Wang +9
Charts are a fundamental visualization format for structured data analysis. Enabling end-to-end chart editing according to user intent is of great practical value, yet remains chal…