13 papers
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
Zhiheng Xi, Dingwen Yang, Jiaqi Liu +21
Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for rigorous and realistic eval…
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…
Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels
Junjie Ye, Yuming Yang, Yang Nan +7
Large language models (LLMs) acquire substantial world knowledge during pre-training, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). Howe…
Pre-Trained Policy Discriminators are General Reward Models
Shihan Dou, Shichun Liu, Yuming Yang +19
We offer a novel perspective on reward modeling by formulating it as a policy discriminator, which quantifies the difference between two policies to generate a reward signal, guidi…
The Role of Entropy in Visual Grounding: Analysis and Optimization
Shuo Li, Jiajun Sun, Zhihao Zhang +10
Recent advances in fine-tuning multimodal large language models (MLLMs) using reinforcement learning have achieved remarkable progress, particularly with the introduction of variou…
TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
Junjie Ye, Yilong Wu, Sixian Li +9
Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervi…