相关论文: ReMiT: RL-Guided Mid-Training for Iterative LLM Ev…

Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e.g., chain-of-thought prompting. However, these intermediate inference steps may be inappropriate…

Large Language Models (LLMs) have shown remarkable capabilities in reasoning, exemplified by the success of OpenAI-o1 and DeepSeek-R1. However, integrating reasoning with external search processes remains challenging, especially for complex…

The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability…

Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or…

Reinforcement Learning (RL) algorithms often require long training to become useful, especially in complex environments with sparse rewards. While techniques like reward shaping and curriculum learning exist to accelerate training, these…

Reasoning has substantially improved the performance of large language models (LLMs) on complicated tasks. Central to the current reasoning studies, Process Reward Models (PRMs) offer a fine-grained evaluation of intermediate reasoning…

Recent advancements in Chain of Thought (COT) generation have significantly improved the reasoning capabilities of Large Language Models (LLMs), with reinforcement learning (RL) emerging as an effective post-training approach. Multimodal…

Teaching large language models (LLMs) to reason during post-training typically relies on reinforcement learning with explicit outcome- or process-based reward functions. However, in many real-world settings, obtaining or defining such…

Reinforcement learning from expert demonstrations has long remained a challenging research problem, and existing state-of-the-art methods using behavioral cloning plus further RL training often suffer from poor generalization, low sample…

Multimodal Large Language Models (MLLMs) are widely regarded as crucial in the exploration of Artificial General Intelligence (AGI). The core of MLLMs lies in their capability to achieve cross-modal alignment. To attain this goal, current…

As Large Language Models (LLMs) achieve remarkable empirical success through scaling model and data size, pretraining has become increasingly critical yet computationally prohibitive, hindering rapid development. Despite the availability of…

Reasoning post-training improves Large Language Models (LLMs) on complex tasks such as mathematics and coding, but its benefits across diverse multimodal tasks remains uncertain. The trend of releasing parallel "Instruct" and "Thinking"…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as…

The evolving sophistication and intricacies of Large Language Models (LLMs) yield unprecedented advancements, yet they simultaneously demand considerable computational resources and incur significant costs. To alleviate these challenges,…

Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multimodal LLMs (MLLMs) through verbose rationales yields limited…

The automatic evaluation of instruction following typically involves using large language models (LLMs) to assess response quality. However, there is a lack of comprehensive evaluation of these LLM-based evaluators across two dimensions:…

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…

Recent advances in large language models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated the effectiveness of test-time scaling, where extended reasoning processes substantially enhance model performance. Despite this, current…

While Large Language Models (LLMs) have revolutionized code generation, standard ``System 1'' approaches that generate solutions in a single forward pass often hit a performance ceiling on complex algorithmic tasks. Existing iterative…

Reward models (RMs) play a critical role in enhancing the reasoning performance of LLMs. For example, they can provide training signals to finetune LLMs during reinforcement learning (RL) and help select the best answer from multiple…