Related papers: Structure Enables Effective Self-Localization of E…

Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-training share the core objective: iteratively leveraging…

Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning steps. Providing these steps for prompting demonstrations is called chain-of-thought (CoT) prompting. CoT prompting has two major paradigms. One…

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought prompting that elicits verbalized reasoning. However, LLMs often generate text with obvious…

Recent advancements in large language models (LLMs) have significantly advanced complex reasoning capabilities, particularly through extended chain-of-thought (CoT) reasoning that incorporates mechanisms such as backtracking,…

Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs), where LLMs refine their solutions using self-generated critiques that pinpoint the errors. This work explores whether…

Planning remains a core challenge for large language models (LLMs), particularly in domains that require coherent multi-step action sequences grounded in external constraints. We introduce SymPlanner, a novel framework that equips LLMs with…

Recent reasoning models, such as OpenAI's O1 series, have demonstrated exceptional performance on complex reasoning tasks and revealed new test-time scaling laws. Inspired by this, many people have been studying how to train models to…

While Pre-trained Language Models (PLMs) internalize a great amount of world knowledge, they have been shown incapable of recalling these knowledge to solve tasks requiring complex & multi-step reasoning. Similar to how humans develop a…

When humans solve complex problems, they typically create a sequence of ideas (involving an intuitive decision, reflection, error correction, etc.) in order to reach a conclusive decision. Contrary to this, today's models are mostly trained…

Learning internal reasoning processes is crucial for developing AI systems capable of sustained adaptation in dynamic real-world environments. However, most existing approaches primarily emphasize learning task-specific outputs or static…

System 2 reasoning is one of the defining characteristics of intelligence, which requires slow and logical thinking. Human conducts System 2 reasoning via the language of thoughts that organizes the reasoning process as a causal sequence of…

Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the…

Chain-of-Thought (CoT) prompting has been used to enhance the reasoning capability of LLMs. However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly under structured human evaluation.…

When performing reasoning tasks with user-specific requirements, such as strict output formats, large language models (LLMs) often prioritize reasoning over adherence to detailed instructions. Fine-tuning LLMs on supervised datasets to…

Large Language Models (LLMs) have succeeded remarkably in various natural language processing (NLP) tasks, yet their reasoning capabilities remain a fundamental challenge. While LLMs exhibit impressive fluency and factual recall, their…

Large language models (LLMs) have shown exceptional performance as general-purpose assistants, excelling across a variety of reasoning tasks. This achievement represents a significant step toward achieving artificial general intelligence…

This work addresses the 3D situated reasoning task which aims to answer questions given egocentric observations in a 3D environment. The task remains challenging as it requires comprehensive 3D perception and complex reasoning skills.…

When writing and talking, people sometimes pause to think. Although reasoning-focused works have often framed reasoning as a method of answering questions or completing agentic tasks, reasoning is implicit in almost all written text. For…

We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge…