Search: “reasoning”

arXiv:2604.08615v1 Announce Type: cross Abstract: Fine-grained visual understanding and high-level reasoning in real-world open-water environments remain under-explored due to the lack of dedicated be

arXiv:2602.01997v2 Announce Type: replace-cross Abstract: Recent work has shown that layer pruning can effectively compress large language models (LLMs) while retaining strong performance on classific

arXiv:2510.07517v5 Announce Type: replace Abstract: Multi-agent debate (MAD) aims to improve large language model (LLM) reasoning by letting multiple agents exchange answers and then aggregate their o

arXiv:2602.13235v2 Announce Type: replace-cross Abstract: Visual Retrieval-Augmented Generation (VRAG) enhances Vision-Language Models (VLMs) by incorporating external visual documents to address a gi

arXiv:2604.08209v1 Announce Type: new Abstract: To extend the reinforcement learning post-training paradigm to omni-modal models for concurrently bolstering video-audio understanding and collaborative

arXiv:2604.06401v1 Announce Type: new Abstract: The large language models (LLMs) might produce a persuasive argument within mathematical and logical fields, although such argument often includes some

arXiv:2505.00017v2 Announce Type: replace Abstract: With the rapid development of large language models (LLMs), their application to cell type annotation has drawn increasing attention. However, gener

arXiv:2506.01062v4 Announce Type: replace Abstract: We introduce SealQA, a new challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields con

arXiv:2604.07801v1 Announce Type: new Abstract: Large language models are trained and evaluated on quantitative reasoning tasks written in clean, emotionally neutral language. However, real-world quer

arXiv:2610.20012v1 Announce Type: new Abstract: Chemistry evaluation has moved past multiple-choice probes toward open-ended expert problems, yet the benchmarks that define the current frontier still

arXiv:2610.18127v1 Announce Type: new Abstract: Looped language models (LMs) reuse one block of layers several times per token generation, promising more latent computation at no additional storage co

arXiv:2610.16709v1 Announce Type: new Abstract: Language models have recently solved open Erdos problems and achieved gold-medal level performance on International Mathematical Olympiad problems. But

arXiv:2610.17183v1 Announce Type: cross Abstract: Current chemistry benchmarks primarily evaluate outcome prediction or reaction pathway generation, but rarely test whether a model can explain why an

arXiv:2610.16449v1 Announce Type: cross Abstract: Pseudonymous accounts and complex smart-contract ecosystems substantially hinder the tracing of illicit cryptocurrency fund flows. Existing Graph Neur

arXiv:2610.18613v1 Announce Type: new Abstract: Self-distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as correct

arXiv:2610.14123v1 Announce Type: cross Abstract: AI-assisted scientific discovery increasingly seeks to move beyond generating plausible ideas toward reproducible, constraint-aware workflows that can

arXiv:2601.21590v2 Announce Type: replace Abstract: Reinforcement learning (RL) post-training is a dominant approach for improving the reasoning performance of large language models (LLMs), yet growin

arXiv:2610.15258v1 Announce Type: cross Abstract: We introduce Sequent-Prover, a family of verifier-using language-model agents, and the post-training framework that produces them. Agents reason in an

Very cool to see Embedding Gemma 2 by @Google, number on trending on HF! The media and silicon valley bubble only talks about reasoning LLMs when there is a much bigger variety of AI models that are s

arXiv:2610.12168v1 Announce Type: new Abstract: We introduce a self-improvement loop for reasoning models based on the following observation: Even when the difficulty of a problem exceeds the model's

arXiv:2610.12333v1 Announce Type: cross Abstract: Accurate simulation of rigid-body interactions is essential for predictive physical world models. Despite recent progress in modeling object dynamics,

arXiv:2610.09440v1 Announce Type: new Abstract: Pre-trained vision encoders contain layer-wise visual representations that differ in spatial granularity, semantic abstraction, and sensitivity to local

arXiv:2610.07423v1 Announce Type: new Abstract: Field-effect transistor (FET) layouts on exfoliated two-dimensional flakes are typically drawn by hand for each flake, placing contacts and gates to mat

Mistral Large 4 against the field: efficiently reasoning over diverse complex challenges. CTF speedrun: 19 challenges, with tool calls and solve times grounded in actual runs. It solved 18 of the 19.

arXiv:2610.04602v1 Announce Type: new Abstract: Primitive-based 3D segmentation offers a compact and explicit alternative to dense surface prediction, naturally supporting structural abstraction and b

arXiv:2603.13725v2 Announce Type: replace Abstract: Memristor-based analog compute-in-memory (CIM) architectures provide a promising substrate for the efficient deployment of Large Language Models (LL

arXiv:2610.03015v1 Announce Type: cross Abstract: Accurate 3D detection is essential for mobile embodied agents, while Vision Foundation Models (VFMs) offer transferable visual and geometric priors. Y

Our new extraction agents are extremely good at reasoning over tables that span multiple pages sometimes a record starts on one page and finishes on the next. extremely common for real world docs (ins

arXiv:2610.01847v1 Announce Type: cross Abstract: Model specifications define how large language models (LLMs) should behave, guiding alignment training, inference-time behavior, and evaluation. Yet t

arXiv:2610.00737v1 Announce Type: cross Abstract: Personalized image generation has remained narrowly focused on conditional synthesis from curated visual exemplars, rather than capturing who a user i

arXiv:2609.39150v1 Announce Type: new Abstract: Omni-modal large language models deployed in real-world environments encounter external noise that can interfere with their perception and understanding

arXiv:2609.40265v1 Announce Type: new Abstract: Real-world time-series applications increasingly require models that can handle time series forecasting, context-conditioned prediction, and language-ba

I put an old RTX 3090 to work as a local coding agent with Qwen3.8-27B, llama.cpp, and OpenCode. Here are the setup and results, including what failed. This is a summary of my own blog post, linked be

arXiv:2609.38869v1 Announce Type: new Abstract: In finance, interpreting machine learning predictions is essential, yet the numerical outputs of explainable AI can be difficult for non-experts to unde

arXiv:2512.00329v2 Announce Type: replace-cross Abstract: Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose an approach that recasts the task

Dean Takahashi / GamesBeat: General Intuition, which trains AI agents in spatial reasoning via gameplay footage, raised 220M at a 6.2B valuation, for 650M+ in total funding — General Intuition has rai

arXiv:2609.32456v1 Announce Type: new Abstract: World modeling under partial observation requires reasoning about the complete worlds that remain compatible with limited visual evidence. Occluded obje

arXiv:2609.35497v1 Announce Type: new Abstract: Long video understanding relies on video memory to overcome the context limits of multimodal large language models. Existing methods follow a build-then

arXiv:2609.33200v1 Announce Type: new Abstract: On-policy self-distillation trains reasoning models on their own trajectories using dense token distribution guidance from a privileged teacher with acc

arXiv:2609.28813v1 Announce Type: new Abstract: Cinematography, the craft of visual storytelling through framing, lighting, and camera operation, fundamentally shapes how audiences perceive and emotio

arXiv:2609.29109v1 Announce Type: new Abstract: Reasoning-capable language models often produce long chains of thought when direct answers suffice, wasting inference compute. Many dual-mode models lea

arXiv:2609.29278v1 Announce Type: cross Abstract: Chain-of-thought (CoT) instructions can distort multiple-choice VLM evaluation when a scorer appends a reasoning cue but reads answer-label logits bef

arXiv:2609.28682v1 Announce Type: new Abstract: Post-training hybrid reasoning models in NoThink mode has attracted growing interest as a way to improve performance while keeping inference fast. Howev

arXiv:2609.27526v1 Announce Type: new Abstract: Long-horizon navigation requires an agent to revise its intermediate objectives as evidence accumulates. Full visual histories are costly to process, wh

arXiv:2609.27173v1 Announce Type: new Abstract: Solving complex tasks in domains such as science, medicine, law, and finance often requires assembling interdependent information scattered across vast,

arXiv:2609.26820v1 Announce Type: cross Abstract: Physiological time series such as electrocardiograms (ECG) and electroencephalograms (EEG) exhibit complex temporal structure, substantial acquisition