2 citations · 5 across the 11 of their papers we have counts for
6 papers · 1 filter
A Distribution-Matching Perspective on LLM Training Algorithms
Yanxing Huang, Bingzhang Yan, Zihan Tang +3
In this work, we propose a unified framework for training algorithms across different stages of modern large language model development, based on the perspective of distribution ma…
Learning Individual Scientific Taste with Privileged Hindsight Distillation
Hanwei Fan, Yanqiao Wang, Yiqi Zhu +3
Scientific taste shapes which research directions researchers pursue, and it varies across individuals. Existing work evaluates research directions along multiple evaluation criter…
Learning Simple Test-Time Environments for LLM Web Agents
Junxuan Li, Zijun Liu, Ziyi Huang +4
Large language model (LLM) agents have demonstrated remarkable proficiency in manually constructed environments, yet their performance frequently collapses when transitioned to com…
Benchmarking General Mobile Assistants in Challenging Real-World Scenarios
Yiqi Zhu, Feiyu Gao, Jiaxing Fan +7
Graphical user interfaces have emerged as an important environment for evaluating autonomous AI agents on multimodal interactive tasks. Existing benchmarks such as AndroidWorld and…
State2State: Environment-Derived Mid-Training for LLM Agents
Xuanyu Lei, Yiqi Zhu, Chenliang Li +6
Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with handcrafted verifiers. Thoug…
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
Tianyi Wang, Yixia Li, Long Li +6
Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in th…