相关论文: SkillFactory: Self-Distillation For Learning Cogni…

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of…

R1-style Reinforcement Learning (RL) significantly enhances Large Language Models' reasoning capabilities, yet the mechanism behind rule-based RL remains unclear. We found that small-scale SFT has substantial influence on RL but shows poor…

Multimodal Large Language Models (MLLMs) already achieve state-of-the-art results across a wide range of tasks and modalities. To push their reasoning ability further, recent studies explore advanced prompting schemes and post-training…

Debates about large language model post-training often treat supervised fine-tuning (SFT) as imitation and reinforcement learning (RL) as discovery. But this distinction is too coarse. What matters is whether a training procedure increases…

Does Reinforcement Learning (RL) merely amplify existing skills, or synthesize novel skills? We investigate this question through the lens of Complementary Reasoning: the critical practical capability of integrating internal knowledge with…

Despite success in many challenging problems, reinforcement learning (RL) is still confronted with sample inefficiency, which can be mitigated by introducing prior knowledge to agents. However, many transfer techniques in reinforcement…

Large vision-language models (VLMs) increasingly adopt post-training techniques such as long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL) to elicit sophisticated reasoning. While these methods exhibit…

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…

Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs' deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains…

Post-training algorithms such as Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) are widely used to adapt (multimodal) large language models to downstream tasks. While effective at task adaptation, their impact on retaining…

The rapid advancement of large language models (LLMs) has significantly enhanced their reasoning abilities, enabling increasingly complex tasks. However, these capabilities often diminish in smaller, more computationally efficient models…

Since the advent of reasoning-based large language models, many have found great success from distilling reasoning capabilities into student models. Such techniques have significantly bridged the gap between reasoning and standard LLMs on…

Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) is a standard post-training recipe for improving Large Language Models (LLM) reasoning, but why it works remains unclear. We revisit the common claim that ``SFT memorizes,…

Training on model-generated synthetic data is a promising approach for finetuning LLMs, but it remains unclear when it helps or hurts. In this paper, we investigate this question for math reasoning via an empirical study, followed by…

The rapid advancement of large language models (LLMs) has significantly advanced the capabilities of artificial intelligence across various domains. However, their massive scale and high computational costs render them unsuitable for direct…

Long context reasoning in large language models (LLMs) has demonstrated enhancement of their cognitive capabilities via chain-of-thought (CoT) inference. Training such models is usually done via reinforcement learning with verifiable…

Training reasoning language models (LMs) with reinforcement learning (RL) for one-hot correctness inherently relies on the LM being able to explore and solve its task with some chance at initialization. Furthermore, a key use case of…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated notable success in enhancing the reasoning performance of large language models (LLMs), particularly on mathematics and programming tasks. Similar to how…

The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…

Fine-tuning foundation models has emerged as a powerful approach for generating objects with specific desired properties. Reinforcement learning (RL) provides an effective framework for this purpose, enabling models to generate outputs that…