Related papers: RLP: Reinforcement as a Pretraining Objective
Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce substantial computational overhead and latency,…
Enhancing the reasoning capabilities of large language models (LLMs) typically relies on massive computational resources and extensive datasets, limiting accessibility for resource-constrained settings. Our study investigates the potential…
Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances overall reasoning…
Large Language Models (LLMs) have shown strong reasoning capabilities, particularly when enhanced through Reinforcement Learning (RL). While prior work has successfully applied RL to mathematical reasoning -- where rules and correctness are…
Code reasoning is a fundamental capability for large language models (LLMs) in the code domain. It involves understanding and predicting a program's execution behavior, such as determining the output for a given input or whether a specific…
Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving. More recently, RL has been leveraged to create sophisticated LLM-based…
Reinforcement learning (RL) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). While RL has demonstrated substantial performance gains, it still faces key challenges, including low…
OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the…
Large Language Models (LLMs) have shown remarkable performance on complex reasoning tasks, especially when equipped with long chain-of-thought (CoT) reasoning. However, eliciting long CoT typically requires large-scale reinforcement…
Reinforcement Learning (RL) has shown promise in improving the reasoning abilities of Large Language Models (LLMs). However, the specific challenges of adapting RL to multimodal data and formats remain relatively unexplored. In this work,…
Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve model performances at inference time via search. However,…
Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…
Code reasoning refers to the task of predicting the output of a program given its source code and specific inputs. It can measure the reasoning capability of large language models (LLMs) and also benefit downstream tasks such as code…
Large language models (LLMs) excel at complex tasks thanks to advances in their reasoning abilities. However, existing methods overlook the trade-off between reasoning effectiveness and efficiency, often encouraging unnecessarily long…
Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about safety alignment and are easily biased when a flawed premise…
Large Reasoning Models (LRMs) achieve explicit chain-of-thought expansion by imitating deep thinking behaviors of humans, demonstrating excellent performance in complex task scenarios. However, the deep-thinking mode often leads to…
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…
Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reasoning capabilities of large language models, yet performance remains sensitive to the…
Improving Multi-modal Large Language Models (MLLMs) in the post-training stage typically relies on supervised fine-tuning (SFT) or reinforcement learning (RL), which require expensive and manually annotated multi-modal data--an ultimately…
In this work, we propose Reinforced Functional Token Tuning (RFTT), a novel reinforced fine-tuning framework that empowers Large Language Models (LLMs) with self-play learn-to-reason capabilities. Unlike prior prompt-driven reasoning…