相关论文: Language as a Latent Variable for Reasoning Optimi…

Although recent Massively Multilingual Language Models (MMLMs) like mBERT and XLMR support around 100 languages, most existing multilingual NLP benchmarks provide evaluation data in only a handful of these languages with little linguistic…

Large language models (LLMs) have shown to be increasingly capable of performing reasoning tasks, but their ability to make sequential decisions under uncertainty only using natural language remains underexplored. We introduce a novel…

Large Language Models (LLMs) are important tools for reasoning and problem-solving, while they often operate passively, answering questions without actively discovering new ones. This limitation reduces their ability to simulate human-like…

While existing benchmarks probe the reasoning abilities of large language models (LLMs) across diverse domains, they predominantly assess passive reasoning, providing models with all the information needed to reach a solution. By contrast,…

Large Language Models (LLMs) have been used to make decisions in complex scenarios, where they need models to think deeply, reason logically, and decide wisely. Many existing studies focus solely on multi-round conversations in social tasks…

When asked a question in a language less seen in its training data, current reasoning large language models (RLMs) often exhibit dramatically lower performance than when asked the same question in English. In response, we introduce…

Realignment is a promising strategy to improve cross-lingual transfer in multilingual language models. However, empirical results are mixed and often unreliable, particularly for typologically distant or low-resource languages (LRLs)…

Despite the widespread multilingual deployment of large language models, post-training pipelines remain predominantly English-centric, contributing to performance disparities across languages. We present a systematic, controlled study of…

This paper investigates Reinforcement Learning (RL) approaches to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-horizon, multi-turn scenarios. Although RL algorithms such as Group Relative Policy…

Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent…

This paper considers the challenges Large Language Models (LLMs) face when reasoning over text that includes information involving uncertainty explicitly quantified via probability values. This type of reasoning is relevant to a variety of…

Recent advances in reasoning with large language models (LLMs) have demonstrated strong performance on complex mathematical tasks, including combinatorial optimization. Techniques such as Chain-of-Thought and In-Context Learning have…

Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than…

Large language models (LLMs) with Chain-of-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream tasks. As most research mainly focuses on English, with few explorations in a…

This position paper argues that large language model (LLM) reasoning should be studied as latent-state trajectory formation rather than as faithful surface chain-of-thought (CoT). This matters because claims about faithfulness,…

Large language models (LLMs) exhibit in-context learning abilities which enable the same model to perform several tasks without any task-specific training. In contrast, traditional adaptation approaches, such as fine-tuning, modify the…

Recent advancements in large language models (LLMs), such as DeepSeek-R1 and OpenAI-o1, have demonstrated the significant effectiveness of test-time scaling, achieving substantial performance gains across various benchmarks. These advanced…

Group-Relative Policy Optimization (GRPO) is a key technique for training large reasoning models, yet it suffers from a critical vulnerability: the \emph{Think-Answer Mismatch}, where noisy reward signals corrupt the learning process. This…

In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has highlighted the…

Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and scale performance with test-time compute. In this paper, we present a framework for…