相关论文: Missing Premise exacerbates Overthinking: Are Reas…

Reasoning with a chain-of-thought (CoT) enables Large Language Models (LLMs) to solve complex tasks but incurs significant inference costs due to the generation of long rationales. We propose Thinking States, a method that performs…

A major drawback of reasoning models is their excessive token usage, inflating computational cost, resource demand, and latency. We show this verbosity stems not from deeper reasoning but from reinforcement learning loss minimization when…

The test-time compute strategy, such as Chain-of-Thought (CoT), has significantly enhanced the ability of large language models to solve complex tasks like logical reasoning. However, empirical studies indicate that simply increasing the…

The capability of Large Language Models (LLMs) to plan remains a topic of debate. Some critics argue that strategies to boost LLMs' reasoning skills are ineffective in planning tasks, while others report strong outcomes merely from training…

Recent research has highlighted that Large Language Models (LLMs), even when trained to generate extended long reasoning steps, still face significant challenges on hard reasoning problems. However, much of the existing literature relies on…

This paper investigates the mathematical reasoning capabilities of large language models (LLMs) using 50 newly constructed high-school-level word problems. Unlike prior studies that focus solely on answer correctness, we rigorously analyze…

We challenge the prevailing assumption that complex reasoning in large language models (LLMs) necessitates massive training data. We demonstrate that sophisticated mathematical reasoning can emerge with only a few examples. Specifically,…

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in…

Test-time scaling, which is also often referred to as slow-thinking, has been demonstrated to enhance multi-step reasoning in large language models (LLMs). However, despite its widespread utilization, the mechanisms underlying slow-thinking…

Over the past few years, the abilities of large language models (LLMs) have received extensive attention, which have performed exceptionally well in complicated scenarios such as logical reasoning and symbolic inference. A significant…

Contemporary progress in large language models (LLMs) has revealed notable inferential capacities via reinforcement learning (RL) employing verifiable reward, facilitating the development of O1 and R1-like reasoning models. Directly…

Enhancing the reasoning capabilities of Large Language Models (LLMs) is a key strategy for building Agents that "think then act." However, recent observations, like OpenAI's o3, suggest a paradox: stronger reasoning often coincides with…

Thinking Tokens (TT) have been proposed as an unsupervised method to facilitate reasoning in language models. However, despite their conceptual appeal, our findings show that TTs marginally improves performance and consistently…

Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances overall reasoning…

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…

Large Language Models (LLMs) have shown remarkable performance in various natural language processing tasks but face challenges in mathematical reasoning, where complex problem-solving requires both linguistic understanding and mathematical…

Recent advancements in large reasoning models (LRMs) have significantly enhanced language models' capabilities in complex problem-solving by emulating human-like deliberative thinking. However, these models often exhibit overthinking (i.e.,…

Large Reasoning Models (LRMs) excel at complex reasoning but are traditionally evaluated in static, "frozen world" settings: model responses are assumed to be instantaneous, and the context of a request is presumed to be immutable over the…

While state-of-the-art large language models (LLMs) demonstrate advanced reasoning capabilities-achieving remarkable performance on challenging competitive math and coding benchmarks-they also frequently fail on tasks that are easy for…

Large Reasoning Models (LRMs) excel at multi-step reasoning but often suffer from inefficient reasoning processes like overthinking and overshoot, where excessive or misdirected reasoning increases computational cost and degrades…