Related papers: GlimpRouter: Efficient Collaborative Inference by …

While reasoning large language models (LLMs) demonstrate remarkable performance across various tasks, they also contain notable security vulnerabilities. Recent research has uncovered a "thinking-stopped" vulnerability in DeepSeek-R1, where…

Large Reasoning Models (LRMs) have achieved remarkable performance on complex tasks by engaging in extended reasoning before producing final answers, yet this strength introduces the risk of overthinking, where excessive token generation…

Large Reasoning Models (LRMs) achieve strong performance through explicit chain-of-thought reasoning but suffer from \textit{overthinking}: generating excessive reasoning tokens even for trivial queries. {Beyond inflating cost, overthinking…

Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling. PRMs require step-level supervision, making them expensive to train. This work aims to build data-efficient PRMs as…

With the widespread adoption of large language models (LLMs) in practical applications, selecting an appropriate model requires balancing not only performance but also operational cost. The emergence of reasoning-capable models has further…

While Large Reasoning Models (LRMs) have demonstrated success in complex reasoning tasks through long chain-of-thought (CoT) reasoning, their inference often involves excessively verbose reasoning traces, resulting in substantial…

Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness Paradox: the reasoning process itself can be misused to…

Mathematical reasoning has been challenging for large language models (LLMs), and the introduction of step-by-step Chain-of-Thought (CoT) inference has significantly advanced the mathematical capabilities of LLMs. However, current…

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 (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model…

Generative Reward Models (GRMs) provide greater flexibility than scalar reward models in capturing human preferences, but their effectiveness is limited by poor reasoning capabilities. This often results in incomplete or overly speculative…

Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this lengthy reasoning process incurs substantial computational and latency overheads, hindering the…

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 language models (LLMs) have achieved remarkable multi-step reasoning capabilities across various domains. However, LLMs still face distinct challenges in complex logical reasoning, as (1) proof-finding requires systematic exploration…

Recent advances in natural language processing highlight two key factors for improving reasoning in large language models (LLMs): (i) allocating more test-time compute tends to help on harder problems but often introduces redundancy in the…

Human cognition operates through two complementary modes: fast intuitive thinking and slow deliberate thinking. Vanilla large language models (LLMs) predominantly follow the fast-thinking paradigm, producing immediate responses; while…

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…

Reasoning segmentation is a challenging vision-language task that aims to output the segmentation mask with respect to a complex, implicit, and even non-visual query text. Previous works incorporated multimodal Large Language Models (MLLMs)…

Reasoning Language Models, capable of extended chain-of-thought reasoning, have demonstrated remarkable performance on tasks requiring complex logical inference. However, applying elaborate reasoning for all queries often results in…

Chain-of-thought has been proven essential for enhancing the complex reasoning abilities of Large Language Models (LLMs), but it also leads to high computational costs. Recent advances have explored the method to route queries among…