Related papers: Wait, We Don't Need to "Wait"! Removing Thinking T…

Recent advancements in large language models (LLMs), such as DeepSeek-R1 and OpenAI-o1, have demonstrated the significant effectiveness of test-time scaling, achieving substantial performance gains across various benchmarks. These advanced…

Large Language Models (LLMs) rely on generating extensive intermediate reasoning units (e.g., tokens, sentences) to enhance final answer quality across a wide range of complex tasks. While this approach has proven effective, it inevitably…

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…

Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning tasks by employing test-time scaling. However, they often generate over-long chains-of-thought that, driven by substantial reflections such as…

Chain of Thought (CoT) reasoning enhances logical performance by decomposing complex tasks, yet its multimodal extension faces a trade-off. The prevailing Thinking with Images paradigm achieves visual refocusing by explicitly cropping image…

The emergence of Large Reasoning Language Models (LRMs) has paved the way for tackling complex reasoning tasks through test-time scaling by generating long-form Chain-of-Thought (CoT) trajectories during inference. Meanwhile, these…

Chain of Thought (CoT) reasoning enhances language models' performance but often leads to inefficient "overthinking" on simple problems. We identify that existing approaches directly penalizing reasoning length fail to account for varying…

Test-time scaling improves the reasoning performance of large language models but often results in token-inefficient overthinking, where models continue reasoning beyond what is necessary for a correct answer. Existing dynamic early-exit…

Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consistency and scalability. As conversations lengthen, essential information becomes sparse and…

Large reasoning models, such as OpenAI o1 or DeepSeek R1, have demonstrated remarkable performance on reasoning tasks but often incur a long reasoning path with significant memory and time costs. Existing methods primarily aim to shorten…

Recent reasoning models show the ability to reflect, backtrack, and self-validate their reasoning, which is crucial in spotting mistakes and arriving at accurate solutions. A natural question that arises is how effectively models can…

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…

Recent advances have established a new machine learning paradigm based on scaling up compute at inference time as well as at training time. In that line of work, a combination of Supervised Fine-Tuning (SFT) on synthetic demonstrations and…

Humans do not just find mistakes after the fact -- we often catch them mid-stream because 'reflection' is tied to the goal and its constraints. Today's large language models produce reasoning tokens and 'reflective' text, but is it…

Large Language Models (LLMs) have emerged as powerful tools for generating coherent text, understanding context, and performing reasoning tasks. However, they struggle with temporal reasoning, which requires processing time-related…

We introduce thoughts of words (ToW), a novel training-time data-augmentation method for next-word prediction. ToW views next-word prediction as a core reasoning task and injects fine-grained thoughts explaining what the next word should be…

Recent advances in Large Audio-Language Models (LALMs) have made real-time, streaming spoken interaction increasingly practical. In this setting, reasoning quality and responsiveness are tightly coupled: delaying reasoning until the speech…

Large language models (LLMs) have achieved strong performance on medical question answering (medical QA), and chain-of-thought (CoT) prompting has further improved results by eliciting explicit intermediate reasoning; meanwhile,…

As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no longer tell whether those tokens buy useful reasoning, recovery from hard instances, or unnecessary…

OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the…