English
Related papers

Related papers: Why Do Reasoning Models Lose Coverage? The Role of…

200 papers

The remarkable capabilities of modern large reasoning models are largely unlocked through post-training techniques such as supervised fine-tuning (SFT) and reinforcement learning (RL). However, the architectural mechanisms behind such…

Artificial Intelligence · Computer Science 2026-04-15 Yein Park , Minbyul Jeong , Jaewoo Kang

Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this work, we hypothesize that current limitations in reasoning stem, in part, from insufficient…

Artificial Intelligence · Computer Science 2025-05-26 Wang Yang , Zirui Liu , Hongye Jin , Qingyu Yin , Vipin Chaudhary , Xiaotian Han

Supervised Fine-Tuning (SFT) on long Chain-of-Thought (CoT) trajectories has become a pivotal phase in building large reasoning models. However, how CoT trajectories from different sources influence the generalization performance of models…

Computation and Language · Computer Science 2026-04-07 Zhaoyi Li , Xiangyu Xi , Zhengyu Chen , Wei Wang , Gangwei Jiang , Ranran Shen , Linqi Song , Ying Wei , Defu Lian

Large Language Models have achieved remarkable performance on reasoning tasks, motivating research into how this ability evolves during training. Prior work has primarily analyzed this evolution via explicit generation outcomes, treating…

Computation and Language · Computer Science 2026-02-03 Siyuan Zhang , Jialian Li , Yichi Zhang , Xiao Yang , Yinpeng Dong , Hang Su

We study how reasoning evolves in a language model -- from supervised fine-tuning (SFT) to reinforcement learning (RL) -- by analyzing how a set of theoretically-inspired datasets influences language model performance in chess. We find that…

Machine Learning · Computer Science 2026-05-05 Lucas Dionisopoulos , Nicklas Majamaki , Prithviraj Ammanabrolu

We analyze reasoning in language models during task-specific fine-tuning and draws parallel between reasoning tokens--intermediate steps generated while solving problem and the human working memory. Drawing from cognitive science, we align…

Computation and Language · Computer Science 2025-12-01 Mukul Singh , Ananya Singha , Arjun Radhakrishna , Sumit Gulwani

Large Language Models (LLMs) with reasoning capabilities have achieved state-of-the-art performance on a wide range of tasks. Despite its empirical success, the tasks and model scales at which reasoning becomes effective, as well as its…

Computation and Language · Computer Science 2025-09-29 Nicolas Boizard , Hippolyte Gisserot-Boukhlef , Kevin El-Haddad , Céline Hudelot , Pierre Colombo

A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT with long chain-of-thought (CoT) supervision and find that…

Artificial Intelligence · Computer Science 2026-04-09 Qihan Ren , Peng Wang , Ruikun Cai , Shuai Shao , Dadi Guo , Yuejin Xie , Yafu Li , Quanshi Zhang , Xia Hu , Jing Shao , Dongrui Liu

Mathematical reasoning is a challenging task for large language models (LLMs), while the scaling relationship of it with respect to LLM capacity is under-explored. In this paper, we investigate how the pre-training loss, supervised data…

Computation and Language · Computer Science 2023-09-14 Zheng Yuan , Hongyi Yuan , Chengpeng Li , Guanting Dong , Keming Lu , Chuanqi Tan , Chang Zhou , Jingren Zhou

Recent advances in vision-language models (VLMs) reasoning have been largely attributed to the rise of reinforcement Learning (RL), which has shifted the community's focus away from the supervised fine-tuning (SFT) paradigm. Many studies…

The prevailing paradigm for enhancing the reasoning abilities of LLMs revolves around post-training on high-quality, reasoning-intensive data. While emerging literature suggests that reasoning data is increasingly incorporated also during…

The training dynamics of deep neural networks often defy expectations, even as these models form the foundation of modern machine learning. Two prominent examples are grokking, where test performance improves abruptly long after the…

Machine Learning · Computer Science 2026-01-28 Keitaro Sakamoto , Issei Sato

Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on ordinary instruction-response data that contains no such traces. We show that this…

Machine Learning · Computer Science 2026-05-21 Lukas Twist , Helen Yannakoudakis , Jie M. Zhang

Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains underexplored. We evaluate nine frontier reasoning models under…

Artificial Intelligence · Computer Science 2026-03-13 Yubo Li , Ramayya Krishnan , Rema Padman

We present the surprising finding that a language model's reasoning capabilities can be improved by training on synthetic datasets of chain-of-thought (CoT) traces from more capable models, even when all of those traces lead to an incorrect…

Artificial Intelligence · Computer Science 2026-01-26 Abhranil Chandra , Ayush Agrawal , Arian Hosseini , Sebastian Fischmeister , Rishabh Agarwal , Navin Goyal , Aaron Courville

Large language models have recently demonstrated significant gains in reasoning ability, often attributed to their capacity to generate longer chains of thought and engage in reflective reasoning. However, the contribution of reflections to…

Artificial Intelligence · Computer Science 2025-10-10 Liwei Kang , Yue Deng , Yao Xiao , Zhanfeng Mo , Wee Sun Lee , Lidong Bing

The reasoning abilities of Large Language Models (LLMs) are becoming a central focus of study in NLP. In this paper, we consider the case of syllogistic reasoning, an area of deductive reasoning studied extensively in logic and cognitive…

Computation and Language · Computer Science 2024-10-18 Leonardo Bertolazzi , Albert Gatt , Raffaella Bernardi

Do reasoning models have "Aha!" moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden mid-trace realizations that lead to accurate outputs, implying an intrinsic capacity for self-correction. Yet, it remains unclear…

Artificial Intelligence · Computer Science 2026-04-21 Liv G. d'Aliberti , Manoel Horta Ribeiro

Frontier reasoning models are produced by posttraining base language models with reinforcement learning. Recent work has challenged this by showing that sampling from a sharpened version of the base model's distribution, a so-called power…

Machine Learning · Computer Science 2026-05-29 Felix Zhou , Anay Mehrotra , Quanquan C. Liu

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Machine Learning · Computer Science 2026-01-01 Haoyue Bai , Yiyou Sun , Wenjie Hu , Shi Qiu , Maggie Ziyu Huan , Peiyang Song , Robert Nowak , Dawn Song
‹ Prev 1 2 3 10 Next ›