Knowledge catalogue
Luna non-reasoning is a bit better than GPT 4o which was sota 2 years ago. Luna (medium) thinking is a bit better than GPT-5 (High) which was sota 1 year ago. Now free to everyone unlimited Sol Max/Fa
arXiv:2608.04385v1 Announce Type: new Abstract: Vision-Language Models (VLMs) often lose visual grounding during multi-step reasoning: as reasoning chains grow longer, later inference steps rely incre
arXiv:2608.05139v1 Announce Type: new Abstract: Long-horizon reasoning in recent LLMs demands that the model switch between distinct skills inside a reasoning chain, such as first doing a math derivat
arXiv:2505.14744v3 Announce Type: replace-cross Abstract: Traditionally, in Programming-by-example (PBE) the goal is to synthesize a program from a small set of input-output examples. Lately, PBE has
NVIDIA Alpamayo 2 Super is a publicly available 34‑billion‑parameter vision–language–action model that merges a 32‑B Cosmos 3 Super Reasoner with a 2‑B action‑expert diffusion network. It produces uni
arXiv:2608.01328v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are rapidly evolving with expanded context windows and stronger reasoning capabilities, enabling multi-chart un
arXiv:2608.02449v1 Announce Type: new Abstract: Deploying vision-language models (VLMs) for safety-critical spatial reasoning on resource-constrained autonomous driving platforms requires both compact
Amazon Bedrock now supports automatic Automated Reasoning policy refinement. The refinement engine diagnoses failing tests and proposes formal-logic fixes for rule issues and language issues, and you
arXiv:2607.15776v2 Announce Type: replace Abstract: OWL ontologies provide a formal knowledge representation framework that enables semantic reasoning, and have been widely adopted across domains such
arXiv:2607.26952v1 Announce Type: new Abstract: We introduce CreditCardQA, the first financial literacy benchmark for numerical reasoning derived from real credit card agreements. The dataset contains
arXiv:2603.26807v2 Announce Type: replace-cross Abstract: The performance of language models is commonly limited by insufficient knowledge and constrained reasoning. Prior approaches such as Retrieval
arXiv:2607.26119v1 Announce Type: cross Abstract: Large reasoning models trained via reinforcement learning (RL) have been increasingly shown to outperform their supervised fine-tuned (SFT) counterpar
arXiv:2607.24789v1 Announce Type: cross Abstract: We present NEXT (Next-interest EXploration Transformer), a reasoning-driven video recommendation framework that reasons over the video a user has just
arXiv:2506.21571v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs), which autonomously produce a reasoning Chain of Thought (CoT) before producing final responses, offer a promisi
From the description: 'Reasoning-Medical-27B is designed for universal advanced medical reasoning in professional medicine, medical genetics, college biology/medicine, and clinical knowledge. The mode
arXiv:2607.22713v1 Announce Type: new Abstract: Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historic
arXiv:2509.06278v4 Announce Type: replace Abstract: Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations. Although recent large lang
arXiv:2606.13751v4 Announce Type: replace Abstract: This paper presents the participation of team PSL in the QIAS 2026 Shared Task on Arabic Islamic inheritance reasoning. The task evaluates the abili
arXiv:2506.13553v4 Announce Type: replace Abstract: Road topology reasoning is fundamental for autonomous driving, requiring both accurate perception of road elements and understanding of their comple
arXiv:2607.21949v1 Announce Type: new Abstract: Continual temporal knowledge graph (TKG) reasoning aims to continuously incorporate newly emerging facts while preserving previously acquired knowledge.
arXiv:2607.20440v1 Announce Type: cross Abstract: Proprietary large language models (LLMs) entail substantial intellectual and financial investment, making them valuable intellectual property (IP). Ho
arXiv:2602.13904v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety. However, CoT
arXiv:2607.20448v1 Announce Type: new Abstract: We introduce Domyn-Small, a 10-billion-parameter open-weight reasoning language model released under the MIT license. Domyn-Small is the product of an i
arXiv:2603.01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising t
arXiv:2607.20952v1 Announce Type: cross Abstract: Latent, or silent, reasoning lets language models carry out intermediate computation in continuous vector space instead of words, and is widely assume
arXiv:2509.21028v4 Announce Type: replace Abstract: We introduce SciTrek, a synthetic question-answering dataset for assessing and improving long-context numerical reasoning in large language models (
In this post, we explore an idea for generating thinking tokens for datasets that lack reasoning traces in SFT customization. We first examine the reasoning suppression problem, then introduce Self-Di
arXiv:2607.14049v1 Announce Type: new Abstract: The emergence of Chain-of-Thought (CoT) reasoning has significantly enhanced the ability of large language models (LLMs) to tackle complex, multi-step t
arXiv:2607.13501v1 Announce Type: new Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and har
arXiv:2607.12650v1 Announce Type: cross Abstract: Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions
arXiv:2607.11875v2 Announce Type: replace-cross Abstract: We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous wo
arXiv:2607.12815v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting is widely used as a test-time scaling strategy for Vision-Language Models (VLMs), but it remains unclear what is extend
arXiv:2412.07259v5 Announce Type: replace Abstract: DatalogMTL is a powerful rule-based language for temporal reasoning. Due to its high expressive power and flexible modeling capabilities, it is suit
arXiv:2602.23802v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual reasoning and understanding tasks but still struggle to capture th
arXiv:2602.23615v3 Announce Type: replace Abstract: Current Large Multimodal Models (LMMs) struggle with high-resolution visual inputs during the reasoning process, as the number of image tokens incre
arXiv:2607.07391v1 Announce Type: new Abstract: Mathematical reasoning benchmarks typically provide all facts needed to solve each problem, while interactive benchmarks often mix reasoning with tools,
arXiv:2607.07492v1 Announce Type: new Abstract: Many reasoning tasks are not well described by a single left-to-right chain: a solver may need to pursue a plausible branch, observe delayed failure, an
arXiv:2607.05716v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong perception and reasoning capabilities. However, most existing models focus on isolated
arXiv:2508.21010v3 Announce Type: replace-cross Abstract: Existing Causal-Why Video Question Answering (VideoQA) models often struggle with higher-order reasoning, relying on opaque, monolithic pipeli
arXiv:2607.04096v1 Announce Type: new Abstract: Current agentic workflows usually involve decomposing user requests into sequences of tool calls with correctly resolved parameters, the results of whic
arXiv:2602.16512v2 Announce Type: replace Abstract: Prompting schemes such as Chain of Thought, Tree of Thoughts, and Graph of Thoughts can significantly enhance the reasoning capabilities of large la
arXiv:2607.02921v1 Announce Type: cross Abstract: Quantitative 3D spatial reasoning from egocentric RGB-D video is a critical capability for next-generation wearable assistants. Yet existing benchmark
arXiv:2511.07403v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial rea
arXiv:2607.05131v1 Announce Type: new Abstract: Among the five primary human senses, tactile is arguably the most fundamental to survival, as it enables the perception of physical contact and interact
Must-read research by Anthropic. Here is the simple explanation and why this is a big deal. We suspect LLMs perform 'internal reasoning'. But little is known or do good methods exist to understand it.
arXiv:2601.01095v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved impressive progress in vision-language reasoning, yet their ability to understand tempo
arXiv:2603.02112v2 Announce Type: replace-cross Abstract: Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning. We id
arXiv:2607.01170v1 Announce Type: cross Abstract: Generative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-thought before re-ordering a candidate list, but they ar
arXiv:2607.00341v1 Announce Type: cross Abstract: Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT). How
arXiv:2511.06160v2 Announce Type: replace Abstract: While recent safety guardrails effectively suppress overtly biased outputs, subtler forms of social bias emerge during complex logical reasoning tas
arXiv:2607.00544v1 Announce Type: new Abstract: Reasoning segmentation requires localizing targets based on complex, implicit queries. Current end-to-end models typically entangle perception and deduc
arXiv:2607.00461v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens whi
arXiv:2606.31608v1 Announce Type: new Abstract: Large Language Models (LLMs) achieve strong results on many medical benchmarks, but their clinical reasoning remains difficult to evaluate reliably. A c
arXiv:2511.18242v3 Announce Type: replace Abstract: Egocentric video understanding requires procedural reasoning under partial observability and continuously shifting viewpoints. Current multimodal la
arXiv:2606.31599v1 Announce Type: cross Abstract: Vision-language models (VLMs) combining reinforcement learning (RL) ignite remarkable progress in multimodal reasoning, yet still struggle with medica
arXiv:2506.13932v3 Announce Type: replace-cross Abstract: The rise of large language models (LLMs) has led to dramatic improvements across a wide range of natural language tasks. Their performance on
arXiv:2511.19119v2 Announce Type: replace Abstract: Spatial reasoning (SR), the ability to infer 3D spatial information from 2D inputs, is essential for real-world applications such as embodied AI and
arXiv:2606.29971v1 Announce Type: new Abstract: A growing body of work suggests that the reasoning capabilities of large language models are largely latent in their base form, with post-training prima
arXiv:2606.28589v1 Announce Type: new Abstract: Current approaches to enhance Large Language Model (LLM) reasoning, such as Chain-of-Thought and 'Wait' prompts, primarily encourage models to think mor
NEW paper worth reading. Reasoning-data curation is expensive because scoring a trace usually means reading it to the end. This new work from UCLA shows you may not have to. The quality of a reasoning