Search: “reasoning”

arXiv:2511.21667v4 Announce Type: replace-cross Abstract: Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers. However, many real-w

arXiv:2604.17297v1 Announce Type: new Abstract: Long Chain-of-Thought (CoT) reasoning is pivotal for the success of recent reasoning models but suffers from high computational overhead and latency. Wh

arXiv:2604.15210v1 Announce Type: cross Abstract: Humor is one of the few cognitive tasks where getting the reasoning right matters as much as getting the answer right. While recent work evaluates hum

arXiv:2604.07165v1 Announce Type: new Abstract: Reinforcement learning for Large Language Model agents is often hindered by sparse rewards in multi-step reasoning tasks. Existing approaches like Group

Friday's big release was Qwen 3.8 27B, an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba's Qwen research lab. I've been looking forward to this one: 27B is an excellent size for runni

arXiv:2604.22266v1 Announce Type: new Abstract: Large Language Models often achieve strong performance by generating long intermediate chain-of-thought reasoning. However, it remains unclear when a mo

arXiv:2604.20413v1 Announce Type: new Abstract: Large language models perform well on many reasoning tasks, yet they often lack awareness of whether their current knowledge or reasoning state is compl

arXiv:2604.16917v1 Announce Type: new Abstract: Languages encode distinct abstractions and inductive priors, yet most large language models (LLMs) overlook this diversity by reasoning in a single domi

arXiv:2509.20868v2 Announce Type: replace-cross Abstract: Structured reasoning can improve the inference performance of large language models (LLMs), but it also introduces computational cost and cont

arXiv:2604.11193v1 Announce Type: new Abstract: Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning

arXiv:2610.14982v1 Announce Type: new Abstract: Recurrent algorithmic reasoners are trained with per-step hints on small graphs and run for many more steps on large ones. On breadth-first search in SA

arXiv:2610.07342v1 Announce Type: new Abstract: On-policy reinforcement learning has become a central paradigm for improving the reasoning abilities of large language models. However, its effectivenes

arXiv:2609.27511v1 Announce Type: cross Abstract: We present NV-Reason-CT, a generative vision--language model for chest and abdominal CT combining native 3D visual encoding with radiologist-guided re

arXiv:2609.17248v1 Announce Type: new Abstract: Multimodal Large Language Models have demonstrated impressive video understanding, yet their ability to reason over long-form narratives is often masked

I know why Qwen3.8 27B shipped with xhigh reasoning as default, it's to do its best in benchmarks. Models from top labs often get benchmarked at multiple reasoning levels, but that same treatment does

arXiv:2607.28336v3 Announce Type: replace Abstract: On-policy distillation provides dense supervision for multimodal reasoners, but its trajectory-level reward cannot determine whether a failed answer

I'm actually fairly bearish on frontier lab valuations. I've never seen the reasons articulated to my satisfaction, so before I go to sleep, I wanted to quickly jot down my thinking here. The basic is

arXiv:2607.24649v1 Announce Type: new Abstract: Large language models are increasingly used as social simulators, including as synthetic survey respondents. Most evaluations ask whether simulated outc

arXiv:2606.13148v2 Announce Type: replace Abstract: Climate and environmental decision-making increasingly requires reasoning across heterogeneous inputs, including gridded physical data, satellite im

arXiv:2512.02456v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effecti

arXiv:2606.26686v1 Announce Type: new Abstract: In order to screen a prompt or a response, the recent guardrail methods generate a chain-of-thought (CoT) before they issue a verdict. This design follo

arXiv:2605.22873v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: wh

arXiv:2605.08817v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) recently thrives in large language model (LLM) reasoning tasks. However, the reward sparsity and t

Boston Dynamics just gave its robot dog a brain that reasons about the physical world. Google DeepMind's Gemini Robotics model is now running inside Spot, the four-legged robot already deployed at tho

arXiv:2610.05417v1 Announce Type: new Abstract: Recent works augment Vision-Language Models with geometry features from pretrained 3D models, expecting that the geometric signal will boost spatial rea

arXiv:2609.30352v1 Announce Type: cross Abstract: Self-consistency has become a popular technique for enhancing the reasoning abilities of large language models by generating multiple reasoning paths

arXiv:2609.27763v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) rely on explicit chain-of-thought (CoT) reasoning and large context windows to achieve strong performance on complex tasks

arXiv:2609.09766v1 Announce Type: new Abstract: Churn models typically identify high-risk customers but do not specify which feasible retention action should be considered or why that action is approp

arXiv:2609.01600v1 Announce Type: cross Abstract: Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility brings a new reasoning burden: a loc

arXiv:2608.25449v1 Announce Type: new Abstract: Formal theorem proving enables machine-verifiable evaluation of mathematical reasoning, yet existing benchmarks often emphasize aggregate proof accuracy

arXiv:2510.07364v4 Announce Type: replace Abstract: What do thinking language models learn during training that their base models lack? We first present an unsupervised method that discovers a model's

arXiv:2511.00602v4 Announce Type: replace Abstract: Recent advances in large language model (LLM) reasoning through reinforcement learning rely on annotated datasets for verifiable rewards, which may

arXiv:2606.26488v1 Announce Type: new Abstract: Recursive reasoning models can solve complex structured tasks with only a few million parameters by repeatedly updating a latent state. Deploying these

arXiv:2603.20190v2 Announce Type: replace Abstract: Composed Video Retrieval (CoVR) aims to find a target video given a reference video and a textual modification. Prior work assumes the modification

arXiv:2606.07069v1 Announce Type: new Abstract: We introduce mmPISA-bench, a compact high-quality multilingual reasoning benchmark derived from the OECD Programme for International Student Assessment

arXiv:2510.11194v3 Announce Type: replace Abstract: Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current met

arXiv:2602.22190v2 Announce Type: replace-cross Abstract: Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a

arXiv:2605.20284v1 Announce Type: new Abstract: Industrial anomaly detection has been significantly advanced by Large Multimodal Models (LMMs), enabling diverse human instructions beyond detection, pa

arXiv:2507.16806v2 Announce Type: replace-cross Abstract: When language models (LMs) are trained via reinforcement learning (RL) to generate natural language 'reasoning chains', their performance impr

arXiv:2604.19780v1 Announce Type: new Abstract: Scaling test-time compute via extended reasoning has become a key paradigm for improving the capabilities of large language models (LLMs). However, exis

arXiv:2604.15529v1 Announce Type: new Abstract: Current large language models reason in isolation. Although it is common to sample multiple reasoning paths in parallel, these trajectories do not inter

arXiv:2509.21823v2 Announce Type: replace Abstract: Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods strugg

arXiv:2512.01925v2 Announce Type: replace-cross Abstract: Recent advancements in large language models (LLMs) have been driven by their emergent reasoning capabilities, particularly through long chain

arXiv:2610.21588v1 Announce Type: new Abstract: Audio-visual large language models (AV-LLMs) have made strong progress in multimodal understanding, yet most treat audio as monaural semantic content, l

arXiv:2504.18225v2 Announce Type: replace Abstract: We introduce a new generation of small reasoning models for RAG, search, and source summarization. Pleias-RAG-350m and Pleias-RAG-1B are mid-trained

arXiv:2510.01581v2 Announce Type: replace-cross Abstract: Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in li