Related papers: Good SFT Optimizes for SFT, Better SFT Prepares fo…

Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities under the widely adopted SFT+RLVR paradigm, which first performs Supervised Fine-Tuning (SFT) on human-annotated reasoning trajectories (rationales) to…

Reinforcement learning with AI feedback (RLAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models. RLAIF first performs supervised fine-tuning (SFT) using demonstrations from a…

Reinforcement learning (RL) is often credited with improving language model reasoning and generalization at the expense of degrading memorized knowledge. We challenge this narrative by observing that RL-enhanced models consistently…

Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, preference alignment, and multi-step reasoning. Reinforcement learning with verifiable rewards…

Preference learning provides a promising solution to address the limitations of supervised fine-tuning (SFT) for code language models, where the model is not explicitly trained to differentiate between correct and incorrect code. Recent…

Instruct LLM provide a paradigm used in large scale language model to align LLM to human preference. The paradigm contains supervised fine tuning and reinforce learning from human feedback. This paradigm is also used in downstream scenarios…

Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redistributes probability mass over solutions the base model…

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…

Test-time scaling has proven effective in further enhancing the performance of pretrained Large Language Models (LLMs). However, mainstream post-training methods (i.e., reinforcement learning (RL) with chain-of-thought (CoT) reasoning)…

Existing post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement learning (RL) methods; the former is stable during training but suffers from limited generalization, while the latter, despite its…

Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing…

Reinforcement learning (RL) has emerged as a promising strategy for improving the reasoning capabilities of language models (LMs) in domains such as mathematics and coding. However, most modern RL algorithms were designed to target robotics…

Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instructions. To address this, we adopt a reinforcement learning…

The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR). However, SFT introduces distributional…

A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward…

As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether…

Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even…

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…

Automated Program Repair (APR) aims to fix bugs by generating patches. And existing work has demonstrated that "pre-training and fine-tuning" paradigm enables Large Language Models (LLMs) improve fixing capabilities on APR. However,…

Reinforcement learning (RL) post-training is crucial for LLM alignment and reasoning, but existing policy-based methods, such as PPO and DPO, can fall short of fixing shortcuts inherited from pre-training. In this work, we introduce…