arXiv Machine Learning June 17, 2026 By Lingjing Kong, Xin Liu, Guangyi Chen, Martin Q. Ma, Xiangchen Song, Yuekai Sun, Mikhail Yurochkin, Taylor W. Killian, Ruslan Salakhutdinov, Kun Zhang, Eric P. Xing, Zhengzhong Liu

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning

Read the original on arXiv Machine Learning →

arXiv:2606. 18089v1 Announce Type: new Abstract: Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming large language models (LLMs) into robust reasoners.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 9

RL Post-Training Builds Compositional Reasoning Strategies

arXiv:2607. 07646v1 Announce Type: new Abstract: Does RL post-training merely amplify primitive skills already latent in a base model, or can it compose primitive skills into new higher-level strategies?

By Azwar Abdulsalam, Nishil Patel, Andrew Saxe

llms reinforcement-learning fine-tuning

arXiv AI

Jun 6

ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces

arXiv:2606. 05402v1 Announce Type: cross Abstract: Large reasoning models (LRMs) produce reasoning traces with non-linear structures, such as backtracking and self-correction, that complicate the evaluation and monitoring of the reasoning process.

By Jinu Lee, Shivam Agarwal, Amruta Parulekar, Siddarth Madala, Dilek Hakkani-Tur, Julia Hockenmaier

llms

arXiv AI

1d ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

arXiv:2604. 06628v2 Announce Type: replace Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes.

By Qihan Ren, Peng Wang, Ruikun Cai, Shuai Shao, Dadi Guo, Yuejin Xie, Yafu Li, Quanshi Zhang, Xia Hu, Jing Shao, Dongrui Liu

llms reinforcement-learning fine-tuning safety data-engineering

arXiv AI

Jun 3

Inducing Reasoning Primitives from Agent Traces

arXiv:2606. 02994v1 Announce Type: new Abstract: ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads.

By Zhihan Lei, Jiarui Yan, Joshua Momo, William W. Cohen

llms agents

arXiv Machine Learning

Jun 10

How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs

arXiv:2606. 10646v1 Announce Type: new Abstract: Token-level credit assignment remains a key obstacle for reinforcement learning (RL) in large language models (LLMs), where RL recipes typically treat all tokens equally, failing to distinguish decisive reasoning steps from routine formatting or fluent filler.

By Zhichen Dong, Yang Li, Yuhan Sun, Weixun Wang, Yijia Luo, Zinian Peng, Taiheng Ye, Chao Yang, Wenbo Su, Yu Cheng, Bo Zheng, Junchi Yan

llms reinforcement-learning efficiency

arXiv Machine Learning

Jun 5

SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions

arXiv:2604. 08477v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved reasoning in formal domains such as mathematics and code, but extending these gains beyond STEM remains challenging.

By Ashima Suvarna, Kendrick Phan, Mehrab Beikzadeh, Hritik Bansal, Saadia Gabriel

llms reinforcement-learning benchmarks

Related stories

RL Post-Training Builds Compositional Reasoning Strategies

ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Inducing Reasoning Primitives from Agent Traces

How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs

SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions