Academic

Academic

Academic · 1 min

RAGEN-2: Reasoning Collapse in Agentic RL

arXiv:2604.06268v1 Announce Type: new Abstract: RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used …

Zihan Wang, Chi Gui, Xing Jin, Qineng Wang, Licheng Liu, Kangrui Wang, Shiqi Chen, Linjie Li, Zhengyuan Yang, Pingyue Zhang, Yiping Lu, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li
89 views
Academic · 1 min

Does a Global Perspective Help Prune Sparse MoEs Elegantly?

arXiv:2604.06542v1 Announce Type: new Abstract: Empirical scaling laws for language models have encouraged the development of ever-larger LLMs, despite their growing computational and memory costs. …

Zeliang Zhang, Nikhil Ghosh, Jiani Liu, Bin Yu, Xiaodong Liu
49 views
Academic · 1 min

Multi-objective Evolutionary Merging Enables Efficient Reasoning Models

arXiv:2604.06465v1 Announce Type: new Abstract: Reasoning models have demonstrated remarkable capabilities in solving complex problems by leveraging long chains of thought. However, this more deliberate …

Mario Iacobelli, Adrian Robert Minut, Tommaso Mencattini, Donato Crisostomi, Andrea Santilli, Iacopo Masi, Emanuele Rodol\`a
38 views
Academic · 1 min

Drifting Fields are not Conservative

arXiv:2604.06333v1 Announce Type: new Abstract: Drifting models generate high-quality samples in a single forward pass by transporting generated samples toward the data distribution using a …

Leonard Franz, Sebastian Hoffmann, Georg Martius
52 views