Related papers: Think in Parallel, Answer as One: Logit Averaging …

A standard technique for scaling inference-time reasoning is Self-Consistency, whereby multiple candidate answers are sampled from an LLM and the most common answer is selected. More recently, it has been shown that weighted majority voting…

Large Reasoning Models (LRMs) achieve strong performance on mathematical reasoning tasks but remain unreliable on challenging instances. Existing test-time scaling methods, such as repeated sampling, self-correction, and tree search,…

Chain-of-thought reasoning is often treated as a monotone way to improve language-model accuracy by letting a model think longer. We identify a countervailing effect, the coupling tax: when reasoning traces and final answers share one…

Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks, yet their ability to perform multi-step logical reasoning remains an open challenge. Although Chain-of-Thought prompting has…

We introduce ThinkTwice, a simple two-phase framework that jointly optimizes LLMs to solve reasoning problems and refine the answers, based on Group Relative Policy Optimization (GRPO). In each pair of training steps, ThinkTwice first…

Large reasoning models (LRMs) have shown significant progress in test-time scaling through chain-of-thought prompting. Current approaches like search-o1 integrate retrieval augmented generation (RAG) into multi-step reasoning processes but…

We introduce DeepSeek-Prover-V2, an open-source large language model designed for formal theorem proving in Lean 4, with initialization data collected through a recursive theorem proving pipeline powered by DeepSeek-V3. The cold-start…

Using logical clauses to represent patterns, Tsetlin Machines (TMs) have recently obtained competitive performance in terms of accuracy, memory footprint, energy, and learning speed on several benchmarks. Each TM clause votes for or against…

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

Large language models have made significant progress in mathematical reasoning, which serves as an important testbed for AI and could impact scientific research if further advanced. By scaling reasoning with reinforcement learning that…

Recently, scaling test-time compute on Large Language Models (LLM) has garnered wide attention. However, there has been limited investigation of how various reasoning prompting strategies perform as scaling. In this paper, we focus on a…

Compressing long chain-of-thought (CoT) from large language models (LLMs) is an emerging strategy to improve the reasoning efficiency of LLMs. Despite its promising benefits, existing studies equally compress all thoughts within a long CoT,…

Recent advancements in Large Language Models (LLMs) have revealed a significant performance gap between closed-source and open-source models, particularly in tasks requiring complex reasoning and precise instruction following. This paper…

Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption. Current test-time scaling methods treat execution feedback merely as an external signal for filtering or…

Recently, Large Reasoning Models (LRMs) have gradually become a research hotspot due to their outstanding performance in handling complex tasks. Among them, DeepSeek R1 has garnered significant attention for its exceptional performance and…

Existing LLM test-time scaling laws emphasize the emergence of self-reflective behaviors through extended reasoning length. Nevertheless, this vertical scaling strategy often encounters plateaus in exploration as the model becomes locked…

Large language models (LLMs) now give reasoning before answering, excelling in tasks like multiple-choice question answering (MCQA). Yet, a concern is that LLMs do not solve MCQs as intended, as work finds LLMs sans reasoning succeed in…

Large language models often solve complex reasoning tasks more effectively with Chain-of-Thought (CoT), but at the cost of long, low-bandwidth token sequences. Humans, by contrast, often reason softly by maintaining a distribution over…

Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths. In this setting, correctness is no longer tied to a single reasoning trace but to the aggregation rule over a pool…

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of…