Related papers: Lean-STaR: Learning to Interleave Thinking and Pro…

Large Language Models (LLMs) have demonstrated significant improvements in reasoning capabilities through supervised fine-tuning and reinforcement learning. However, when training reasoning models, these approaches are primarily applicable…

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…

Collecting ground-truth rewards or human demonstrations for multi-step reasoning tasks is often prohibitively expensive, particularly in interactive domains such as web tasks. We introduce Self-Taught Lookahead (STL), a reward-free…

Can a model learn to escape its own learning plateau? Reinforcement learning methods for finetuning large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental…

Recently, large language models have presented promising results in aiding formal mathematical reasoning. However, their performance is restricted due to the scarcity of formal theorem-proving data, which requires additional effort to be…

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…

Theorem proving in natural mathematical language - the mixture of symbolic and natural language used by humans - plays a central role in mathematical advances and education, and tests aspects of reasoning that are core to intelligence. Yet…

Recent advancements in large language models (LLMs) have demonstrated that progressive refinement, rather than providing a single answer, results in more accurate and thoughtful outputs. However, existing methods often rely heavily on…

The Stop-Think-AutoRegress Language Diffusion Model (STAR-LDM) integrates latent diffusion planning with autoregressive generation. Unlike conventional autoregressive language models limited to token-by-token decisions, STAR-LDM…

Recently, large language models (LLMs) have shown remarkable reasoning capabilities via large-scale reinforcement learning (RL). However, leveraging the RL algorithm to empower effective multi-tool collaborative reasoning in LLMs remains an…

Multimodal large language models excel across diverse domains but struggle with complex visual reasoning tasks. To enhance their reasoning capabilities, current approaches typically rely on explicit search or post-training techniques.…

Mathematical reasoning presents a significant challenge to the cognitive capabilities of LLMs. Various methods have been proposed to enhance the mathematical ability of LLMs. However, few recognize the value of state transition for LLM…

Pre-trained language models (LMs) are able to perform complex reasoning without explicit fine-tuning. To understand how pre-training with a next-token prediction objective contributes to the emergence of such reasoning capability, we…

We perform a thorough analysis of the formal and informal statements in the miniF2F benchmark from the perspective of an AI system that is tasked to participate in a math Olympiad consisting of the problems in miniF2F. In such setting, the…

How should one judge whether a given large language model (LLM) can reliably perform economic reasoning? Most existing LLM benchmarks focus on specific applications and fail to present the model with a rich variety of economic tasks. A…

The performance of Large Vision Language Models (LVLMs) is dependent on the size and quality of their training datasets. Existing video instruction tuning datasets lack diversity as they are derived by prompting large language models with…

Large Language Models (LLMs) have emerged as powerful tools in mathematical theorem proving, particularly when utilizing formal languages such as LEAN. A prevalent proof method involves the LLM prover iteratively constructing the proof…

Specialized reasoning language models (RLMs) have demonstrated that scaling test-time computation through detailed reasoning traces significantly enhances performance. Although these traces effectively facilitate knowledge distillation into…

Large language models (LLMs) tackle complex tasks by generating long chains of thought or "reasoning traces" that act as latent variables in the generation of an output given a query. A model's ability to generate such traces can be…

Mathematical reasoning demands two critical, complementary skills: constructing rigorous proofs for true statements and discovering counterexamples that disprove false ones. However, current AI efforts in mathematics focus almost…