Search: “reasoning”

arXiv:2509.24711v4 Announce Type: replace Abstract: Current answering paradigms for Large Reasoning Models (LRMs) often fail to account for the fact that some questions may lie beyond the model's oper

arXiv:2608.17414v1 Announce Type: new Abstract: Chart editing requires inferring and modifying visualization code from a reference chart image based on an editing instruction, challenging fine-grained

arXiv:2608.07885v1 Announce Type: new Abstract: Reasoning modes of language models outperform their non-reasoning counterparts on multi-step agentic tasks, but pay a 3-6x premium in output tokens on e

arXiv:2606.09585v1 Announce Type: new Abstract: Chain-of-Thought (CoT) improves the performance of Large Language Models (LLMs) and has been extended to Multimodal Large Language Models (MLLMs). More

arXiv:2605.07021v1 Announce Type: new Abstract: Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To addr

arXiv:2601.05300v2 Announce Type: replace-cross Abstract: Reasoning-oriented language models typically expose explicit reasoning as a long, front-loaded chain of 'thinking' tokens before the main outp

arXiv:2508.01191v5 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting has been shown to be effective in eliciting structured reasoning (i.e., CoT reasoning) from large language models (

arXiv:2603.08291v3 Announce Type: replace Abstract: Multimodal Mathematical Reasoning (MMR) has recently attracted increasing attention for its capability to solve mathematical problems involving both

arXiv:2510.10182v2 Announce Type: replace-cross Abstract: Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamen

arXiv:2610.18388v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown strong potential for remote sensing understanding, yet reliable reasoning remains challenging when t

arXiv:2610.13570v1 Announce Type: new Abstract: Reasoning models can benefit from test-time scaling, but continued reasoning may become ineffective or harmful, a phenomenon termed overthinking. Evalua

arXiv:2610.00562v1 Announce Type: cross Abstract: Longitudinal clinical reasoning requires large language models (LLMs) to identify and integrate relevant evidence distributed across extended patient

arXiv:2609.31619v1 Announce Type: new Abstract: Reasoning models often generate very long reasoning traces, making inference computationally expensive. Existing approaches typically improve efficiency

arXiv:2609.29775v1 Announce Type: cross Abstract: Large Language Models (LLMs) consume and produce a single sequence of text; hence, if text can be added to the beginning of the LLM's response, i.e.,

arXiv:2609.21247v1 Announce Type: new Abstract: Large Reasoning Models increasingly use intermediate traces for machine translation, but it remains unclear when such reasoning helps or hurts. We analy

arXiv:2609.01867v1 Announce Type: cross Abstract: A major question in cognitive modeling concerns the behavioral alignment between large language models and humans across linguistic and non-linguistic

arXiv:2505.15276v2 Announce Type: replace Abstract: Large reasoning models (LRMs) have achieved remarkable success on complex tasks, yet their tendency to 'overthink' leads to inefficiencies. Although

arXiv:2505.16782v3 Announce Type: replace Abstract: Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning. However, conventional CoT

arXiv:2608.14107v1 Announce Type: new Abstract: Reasoning-intensive retrieval requires text representations to capture not only semantic similarity, but also the reasoning needed to determine relevanc

arXiv:2607.26397v1 Announce Type: new Abstract: Enzyme function prediction is a hierarchical, knowledge-intensive form of protein function classification. Existing benchmarks expose an anomaly: genera

arXiv:2606.26797v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) on a small, high-quality set of long reasoning traces is an effective approach for eliciting strong reasoning capabilities

arXiv:2505.22919v3 Announce Type: replace Abstract: Existing benchmarks for evaluating the clinical reasoning capabilities of large language models (LLMs) often lack a clear definition of 'clinical re

arXiv:2610.05097v1 Announce Type: new Abstract: As multimodal large language models (MLLMs) reason for longer, attention to the initial visual input diminishes, weakening visual grounding. Visual memo

arXiv:2607.28154v1 Announce Type: new Abstract: Interleaved multimodal Chain-of-Thought (CoT) improves visual reasoning by incorporating auxiliary visual evidence into intermediate reasoning. However,

arXiv:2604.09890v1 Announce Type: cross Abstract: Across multiple language pairings (English o {Spanish, French, German, Mandarin, Japanese, Urdu, Cantonese}), we find reasoning errors in translation.

arXiv:2610.17540v1 Announce Type: cross Abstract: Textual reasoning before acting has improved vision-language-action (VLA) models, but at the cost of latency: every action conditioned on the reasonin

arXiv:2610.11352v1 Announce Type: new Abstract: Language models (LMs) are commonly trained with Reinforcement Learning with Verifiable Rewards (RLVR) to enhance their reasoning capabilities. However,

arXiv:2607.23019v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting enables large language models (LLMs) to tackle multi-step reasoning tasks, yet the generated intermediate steps are not

arXiv:2507.16863v2 Announce Type: replace-cross Abstract: A common belief in multimodal research is that the perceptual weaknesses of vision--language models can be compensated by stronger language re

arXiv:2509.22193v2 Announce Type: replace Abstract: Distilling reasoning traces from strong teacher models has become the standard recipe for building capable small language models. Yet reasoning trac

arXiv:2606.09303v1 Announce Type: new Abstract: The rapid development of pretrained foundation models has enabled more general image segmentation. Multimodal large language models (MLLMs) have been wi

arXiv:2605.26934v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become central to post-training reasoning models, yet a key limitation of existing studies i

arXiv:2509.22746v2 Announce Type: replace Abstract: Current visual reasoning methods mainly focus on exploring specific reasoning modes. Although improvements can be achieved in particular domains, th

arXiv:2602.06475v2 Announce Type: replace Abstract: Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities. However, existing reward mechanisms remain tightly coup

arXiv:2604.19149v1 Announce Type: cross Abstract: Thinking LLMs produce reasoning traces before answering. Prior activation steering work mainly targets on shaping these traces. It remains less unders

arXiv:2604.15725v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) have demonstrated strong capabilities in generating step-by-step reasoning chains alongside final answers, enabling thei

arXiv:2505.10846v3 Announce Type: replace Abstract: This paper presents AutoRAN, the first framework to automate the hijacking of internal safety reasoning in large reasoning models (LRMs). At its cor

arXiv:2604.11399v1 Announce Type: cross Abstract: Multimodal adaptation equips large language models (LLMs) with perceptual capabilities, but often weakens the reasoning ability inherited from languag

arXiv:2601.07663v3 Announce Type: replace Abstract: Hint-based faithfulness evaluations have established that Large Reasoning Models (LRMs) may not say what they think: they do not always volunteer in

arXiv:2610.07175v1 Announce Type: new Abstract: Visual latent reasoning compresses rendered derivations into compact intermediate states, reducing textual reasoning overhead. Existing approaches diffe

arXiv:2610.05322v1 Announce Type: new Abstract: Test-time compute can improve mathematical reasoning, but can short-budget runs predict how mathematical reasoning scales with additional compute? We in

arXiv:2609.34387v1 Announce Type: new Abstract: Existing adaptive reasoning methods for driving Vision-Language-Action (VLA) models primarily focus on whether to reason, overlooking how reasoning shou

arXiv:2609.15296v1 Announce Type: new Abstract: Universal multimodal embedding (UME) learns unified representations across modalities, enabling a single model to support diverse retrieval tasks. Recen

arXiv:2509.03345v3 Announce Type: replace Abstract: Non-deductive reasoning, encompassing inductive and abductive reasoning, is essential in addressing complex real-world questions. One key feature of

arXiv:2608.26166v1 Announce Type: cross Abstract: Advancing reasoning capabilities allow large language models (LLMs) to tackle increasingly complex problems, while reasoning traces - intermediate ste

arXiv:2604.06156v2 Announce Type: replace-cross Abstract: MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly