Related papers: R2-Write: Reflection and Revision for Open-Ended W…

Large language models have recently demonstrated remarkable abilities to self-correct their responses through iterative refinement, often referred to as self-consistency or self-reflection. However, the dynamics of this self-correction…

Large language models are often described as capable of reflective reasoning, yet recursive self-evaluation without external feedback frequently yields reformulation rather than progress. We test this prediction in a cross-provider study of…

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on ordinary instruction-response data that contains no such traces. We show that this…

Large reasoning models exhibit remarkable reasoning capabilities via long, elaborate reasoning trajectories. Supervised fine-tuning on such reasoning traces, also known as distillation, can be a cost-effective way to boost reasoning…

Large language models have achieved remarkable capabilities across domains, yet mechanisms underlying sophisticated reasoning remain elusive. Recent reasoning models outperform comparable instruction-tuned models on complex cognitive tasks,…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as…

Recent Large Reasoning Models (LRMs) excel at complex reasoning tasks but often suffer from overthinking, generating overly long and redundant reasoning trajectories. To explore its essence, our empirical analysis reveals that LRMs are…

Recent advances in image editing models have shown remarkable progress. A common architectural design couples a multimodal large language model (MLLM) encoder with a diffusion decoder, as seen in systems such as Step1X-Edit and…

Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior work has attempted to enhance prompts using large language…

Reinforcement learning (RL) training of large language models (LLMs) on unverifiable tasks is challenging even when a reasonable-quality reference answer is available. We propose a constrained RL training framework that (i) optimizes a…

Achieving human-level intelligence requires refining the transition from the fast, intuitive System 1 to the slower, more deliberate System 2 reasoning. While System 1 excels in quick, heuristic decisions, System 2 relies on logical…

Recently, slow-thinking systems like GPT-o1 and DeepSeek-R1 have demonstrated great potential in solving challenging problems through explicit reflection. They significantly outperform the best fast-thinking models, such as GPT-4o, on…

Writing well requires not only expressing ideas but also refining them through revision, a process facilitated by reflection. Prior research suggests that feedback delivered through dialogues, such as those in writing center tutoring…

Reinforcement learning (RL) has recently become the dominant paradigm for strengthening the reasoning abilities of large language models (LLMs). Yet the rule-based reward functions commonly used on mathematical or programming benchmarks…

Although preference optimization methods have improved reasoning performance in Large Language Models (LLMs), they often lack transparency regarding why one reasoning outcome is preferred over another. This limitation is especially critical…

While Large Language Models (LLMs) have revolutionized code generation, standard ``System 1'' approaches that generate solutions in a single forward pass often hit a performance ceiling on complex algorithmic tasks. Existing iterative…

Abstract reasoning ability reflects the intelligence and generalization capacity of LLMs to extract and apply abstract rules. However, accurately measuring this ability remains challenging: existing benchmarks either rely on expensive…

Think-Answer reasoners such as DeepSeek-R1 have made notable progress by leveraging interpretable internal reasoning. However, despite the frequent presence of self-reflective cues like "Oops!", they remain vulnerable to output errors…

Test-time scaling via explicit reasoning trajectories significantly boosts large language model (LLM) performance but often triggers overthinking. To explore this, we analyze reasoning through two lenses: Reasoning Length Dynamics, which…