Related papers: SCRIBE: Structured Mid-Level Supervision for Tool-…

Learning reward models from human preference datasets and subsequently optimizing language models via reinforcement learning has emerged as a fundamental paradigm for aligning LLMs with human preferences. The performance of the reward model…

Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel method that aligns LLMs…

Large Reasoning Models (LRMs) excel at multi-step reasoning but often suffer from inefficient reasoning processes like overthinking and overshoot, where excessive or misdirected reasoning increases computational cost and degrades…

Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric learning that rely on expensive parameter updates in the…

Query rewriting is pivotal for enhancing dense retrieval, yet current methods demand large-scale supervised data or suffer from inefficient reinforcement learning (RL) exploration. In this work, we first establish that guiding Large…

Existing Vision-Language Models often struggle with complex, multi-question reasoning tasks where partial correctness is crucial for effective learning. Traditional reward mechanisms, which provide a single binary score for an entire…

We tackle the question of how to scale more efficiently across the many, ever-growing stages of current LLM training pipelines. Our guiding intuition stems from the fact that the dynamics of later stages of the pipeline, e.g. post-training,…

Scalable AI tutoring for procedural skill learning requires structured knowledge representations, yet constructing these representations remains a labor-intensive bottleneck. This paper introduces a new LLM-assisted text-to-model (TTM)…

Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance performance, the computational overhead is a critical issue. In…

Large language models (LLMs) have recently demonstrated impressive performance on complex, multi-step reasoning tasks, especially when post-trained with outcome-rewarded reinforcement learning Guo et al. 2025. However, it has been observed…

Through reinforcement learning (RL) with outcome correctness rewards, large reasoning models (LRMs) with scaled inference computation have demonstrated substantial success on complex reasoning tasks. However, the one-sided reward, focused…

Rubric-based text evaluation increasingly uses large language models (LLMs) as scalable judges, but aligning frozen black-box models with human scoring standards remains challenging. We formulate this challenge as a criteria-transfer…

Pointwise reward modeling offers critical signals for LLM post-training, yet struggles with absolute scoring in subjective, non-verifiable settings. Rubric-based methods address this by decomposing evaluation into explicit criteria, but…

The progress of AI is bottlenecked by the quality of evaluation, making powerful LLM-as-a-Judge models a core solution. The efficacy of these judges depends on their chain-of-thought reasoning, creating a critical need for methods that can…

Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable…

Large Language Models (LLMs) have shown significant potential in designing reward functions for Reinforcement Learning (RL) tasks. However, obtaining high-quality reward code often involves human intervention, numerous LLM queries, or…

Large Language Model (LLM)-based agents demonstrate advanced reasoning capabilities, yet practical constraints frequently limit outputs to single responses, leaving significant performance potential unrealized. This paper introduces MARINE…

Large language models (LLMs) achieve high performance on mathematical reasoning, but these results can be inflated by training data leakage or superficial pattern matching rather than genuine reasoning. To this end, an adversarial…

Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to…

Large Language Models (LLMs) are increasingly adopted as evaluators, offering a scalable alternative to human annotation. However, existing supervised fine-tuning (SFT) approaches often fall short in domains that demand complex reasoning.…