Related papers: Meta-Awareness Enhances Reasoning Models: Self-Ali…
Modern large language models (LLMs) are often evaluated and deployed under a one-shot, greedy inference protocol, especially in professional settings that require deterministic behavior. This regime can systematically under-estimate a fixed…
Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…
Recent advances in prompt optimization, exemplified by methods such as TextGrad, enable automatic, gradient-like refinement of textual prompts to enhance the performance of large language models (LLMs) on specific downstream tasks. However,…
Large language models have been shown to suffer from reasoning inconsistency issues. That is, they fail more in situations unfamiliar to the training data, even though exact or very similar reasoning paths exist in more common cases that…
Self-evaluation, a model's ability to assess the correctness of its own output, is crucial for Large Multimodal Models (LMMs) to achieve self-improvement in multi-turn conversations, yet largely absent in foundation models. Recent work has…
Meta-learning algorithms enable rapid adaptation to new tasks with minimal data, a critical capability for real-world robotic systems. This paper evaluates Model-Agnostic Meta-Learning (MAML) combined with Trust Region Policy Optimization…
Reinforcement learning scaling enhances the reasoning capabilities of large language models, with reinforcement learning serving as the key technique to draw out complex reasoning. However, key technical details of state-of-the-art…
Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered…
Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models, but it suffers from two critical limitations: gradient vanishing and diversity collapse.…
We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning trajectories as pseudo-gradient descent updates to the LLM's…
Large Language Models (LLMs) have demonstrated promising capabilities in solving mathematical reasoning tasks, leveraging Chain-of-Thought (CoT) data as a vital component in guiding answer generation. Current paradigms typically generate…
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…
As strong general reasoners, large language models (LLMs) encounter diverse domains and tasks, where the ability to adapt and self-improve at test time is valuable. We introduce MASS, a meta-learning framework that enables LLMs to…
Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as…
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of reasoning tasks. Recent methods have further improved LLM performance in complex mathematical reasoning. However, when extending these methods…
Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…
Mathematical reasoning is a fundamental capability for large language models (LLMs), yet achieving high performance in this domain remains a significant challenge. The auto-regressive generation process often makes LLMs susceptible to…
Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcome-based supervision to strengthen internal LLM reasoning,…
Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited:…
Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks. However, these advancements have predominantly benefited "first-class" languages such as English and Chinese, leaving many other languages…