English
Related papers

Related papers: Rethinking Generalization in Reasoning SFT: A Cond…

200 papers

Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet the optimal integration of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remains a fundamental challenge. Through comprehensive analysis…

Computation and Language · Computer Science 2025-06-25 Yuqian Fu , Tinghong Chen , Jiajun Chai , Xihuai Wang , Songjun Tu , Guojun Yin , Wei Lin , Qichao Zhang , Yuanheng Zhu , Dongbin Zhao

Training LLMs to think and reason for longer has become a key ingredient in building state-of-the-art models that can solve complex problems previously out of reach. Recent efforts pursue this in different ways, such as RL fine-tuning to…

Machine Learning · Computer Science 2026-02-03 Yihao Xue , Allan Zhang , Jianhao Huang , Amit Sahai , Baharan Mirzasoleiman

Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising…

Computation and Language · Computer Science 2025-09-03 Xiaomin Li , Zhou Yu , Zhiwei Zhang , Xupeng Chen , Ziji Zhang , Yingying Zhuang , Narayanan Sadagopan , Anurag Beniwal

We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation. Existing research is mixed regarding whether training on easier or harder data…

Computation and Language · Computer Science 2025-11-27 Yeganeh Kordi , Nihal V. Nayak , Max Zuo , Ilana Nguyen , Stephen H. Bach

Generalization in Reinforcement Learning (RL) aims to learn an agent during training that generalizes to the target environment. This paper studies RL generalization from a theoretical aspect: how much can we expect pre-training over…

Machine Learning · Computer Science 2023-06-30 Haotian Ye , Xiaoyu Chen , Liwei Wang , Simon S. Du

Chain-of-Thought (CoT) reasoning in smaller language models is a challenging natural language process problem yet highly desirable in many real-life applications. Existing CoT knowledge distillation methods often suffer from overly…

Machine Learning · Computer Science 2025-01-20 Maxwell J. Yin , Dingyi Jiang , Yongbing Chen , Boyu Wang , Charles Ling

Test-time scaling methods have seen a rapid increase in popularity for its computational efficiency and parameter-independent training to improve reasoning performance on Large Language Models. One such method is called budget forcing, a…

Artificial Intelligence · Computer Science 2025-10-27 Ravindra Aribowo Tarunokusumo , Rafael Fernandes Cunha

With the rapid advancement of large language models (LLMs) technologies, their application in the domain of autonomous driving has become increasingly widespread. However, existing methods suffer from unstructured reasoning, poor…

Artificial Intelligence · Computer Science 2026-01-09 Chang Zhao , Zheming Yang , Yunqing Hu , Qi Guo , Zijian Wang , Pengcheng Li , Wen Ji

Despite recent advances in training and prompting strategies for Large Language Models (LLMs), these models continue to face challenges with complex logical reasoning tasks that involve long reasoning chains. In this work, we explore the…

Computation and Language · Computer Science 2024-12-18 Jiaming Zhou , Abbas Ghaddar , Ge Zhang , Liheng Ma , Yaochen Hu , Soumyasundar Pal , Mark Coates , Bin Wang , Yingxue Zhang , Jianye Hao

Recent advancements in large language models (LLMs) have demonstrated emergent capabilities in complex reasoning, largely spurred by rule-based Reinforcement Learning (RL) techniques applied during the post-training. This has raised the…

Machine Learning · Computer Science 2025-07-22 Sneheel Sarangi , Hanan Salam

We introduce a method to address goal misgeneralization in reinforcement learning (RL), leveraging Large Language Model (LLM) feedback during training. Goal misgeneralization, a type of robustness failure in RL occurs when an agent retains…

Machine Learning · Computer Science 2024-01-17 Houda Nait El Barj , Theophile Sautory

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ fundamentally in their reliance on expert trajectories. To understand the optimal way to harness these…

Machine Learning · Computer Science 2026-05-12 Bowen Ding , Yuhan Chen , Jiayang Lyv , Jiyao Yuan , Qi Zhu , Shuangshuang Tian , Dantong Zhu , Futing Wang , Heyuan Deng , Fei Mi , Lifeng Shang , Tao Lin

Pre-trained Large Language Models (LLMs) require post-training methods such as supervised fine-tuning (SFT) on instruction-response pairs to enable instruction following. However, this process can potentially harm existing capabilities…

Computation and Language · Computer Science 2025-02-04 Yihan Wang , Andrew Bai , Nanyun Peng , Cho-Jui Hsieh

Large language models (LLMs) equipped with chain-of-thought (CoT) achieve strong performance and offer a window into LLM behavior. However, recent evidence suggests that improvements in CoT capabilities often come with redundant reasoning…

Computation and Language · Computer Science 2026-02-03 Yanrui Du , Sendong Zhao , Yibo Gao , Danyang Zhao , Qika Lin , Ming Ma , Jiayun Li , Yi Jiang , Kai He , Qianyi Xu , Bing Qin , Mengling Feng

While the reasoning capabilities of Large Language Models (LLMs) excel in analytical tasks such as mathematics and code generation, their utility for abstractive summarization remains widely assumed but largely unverified. To bridge this…

Computation and Language · Computer Science 2025-12-10 Haohan Yuan , Haopeng Zhang

While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yield superior performance on test sets compared to their…

Computation and Language · Computer Science 2024-03-15 Haoran Yang , Yumeng Zhang , Jiaqi Xu , Hongyuan Lu , Pheng Ann Heng , Wai Lam

Some reinforcement learning (RL) algorithms can stitch pieces of experience to solve a task never seen before during training. This oft-sought property is one of the few ways in which RL methods based on dynamic-programming differ from RL…

Machine Learning · Computer Science 2024-03-13 Raj Ghugare , Matthieu Geist , Glen Berseth , Benjamin Eysenbach

The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of pretraining data. To explore this issue, we…

Computation and Language · Computer Science 2025-03-04 Xinyi Wang , Antonis Antoniades , Yanai Elazar , Alfonso Amayuelas , Alon Albalak , Kexun Zhang , William Yang Wang

Large Language Models (LLMs) that can continually improve beyond their training budgets are able to solve increasingly difficult problems by adapting at test time, a property we refer to as extrapolation. However, standard reinforcement…

Machine Learning · Computer Science 2026-03-24 Ian Wu , Yuxiao Qu , Amrith Setlur , Aviral Kumar

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Binbin Ji , Siddharth Agrawal , Qiance Tang , Yvonne Wu