Knowledge catalogue
arXiv:2609.16076v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at programming tasks but frequently fail at deterministic, fine-grained reasoning in natural language, relying heav
arXiv:2609.16055v1 Announce Type: cross Abstract: Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasoning
arXiv:2609.15169v1 Announce Type: new Abstract: Driving vision-language-action (VLA) models increasingly reason before acting, but their intermediate reasoning is often weakly grounded in physical sce
arXiv:2608.26442v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have shown that increased inference-time reasoning can improve performance on complex tasks. However, ma
arXiv:2602.20159v3 Announce Type: replace-cross Abstract: Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grou
arXiv:2608.22622v1 Announce Type: cross Abstract: Clinical decision-making relies on identifying relevant patient information to guide diagnosis and treatment, a challenge that is especially difficult
arXiv:2608.21265v1 Announce Type: new Abstract: Large language models often rely on Chain-of-Thought (CoT) reasoning to solve complex tasks, but verbose reasoning traces introduce substantial inferenc
arXiv:2608.20670v1 Announce Type: new Abstract: Many agentic systems must repeatedly choose between acting and abstaining, making faithful reasoning important for oversight: an explanation is useful o
arXiv:2604.04930v2 Announce Type: replace-cross Abstract: Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial com
arXiv:2608.08889v1 Announce Type: new Abstract: Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference. As Large L
arXiv:2604.04902v2 Announce Type: replace Abstract: Latent reasoning models (LRMs) have attracted significant research interest due to their low inference cost (relative to explicit reasoning models)
arXiv:2608.04124v1 Announce Type: cross Abstract: Video question answering requires models to ground language queries in visual evidence and, when necessary, reason over that evidence across time. Exi
arXiv:2608.05148v1 Announce Type: new Abstract: Procedural generators produce useful verifiable reasoning problems at scale, but have received less attention as data for completion-supervised fine-tun
Outlook where frontier AI is headed next 18 months: The AI reasoning training + harness loop works if you can produce enough data and reasoning traces (via verifiers). Proven with code and math result
arXiv:2608.03401v1 Announce Type: cross Abstract: Large language models often reason at length before answering, increasing cost and latency. Prompts and trained settings can shorten this reasoning, b
arXiv:2607.06522v1 Announce Type: new Abstract: Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, particularly under unseen tasks and environments. Two key failur
arXiv:2606.11046v1 Announce Type: new Abstract: Instruction-tuned LLMs are increasingly converted into reasoning models through post-training to improve multi-step task performance. This conversion is
arXiv:2604.01161v2 Announce Type: replace Abstract: Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remar
arXiv:2602.02909v2 Announce Type: replace Abstract: Inference-time scaling via chain-of-thought (CoT) reasoning is a major driver of state-of-the-art LLM performance, but it comes with substantial lat
arXiv:2605.25745v1 Announce Type: new Abstract: Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost d
arXiv:2605.12163v1 Announce Type: new Abstract: In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewis
arXiv:2604.21409v1 Announce Type: new Abstract: We present S1-VL, a multimodal reasoning model for scientific domains that natively supports two complementary reasoning paradigms: Scientific Reasoning
arXiv:2604.20564v1 Announce Type: new Abstract: While LLMs demonstrate impressive reasoning capabilities, they remain fragile in multi-step logical deduction, where a single transition error can propa
arXiv:2504.02181v2 Announce Type: replace Abstract: The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such a
arXiv:2604.19937v1 Announce Type: cross Abstract: Assessing chronic wound infection from photographs is challenging because visual appearance varies across wound etiologies, anatomical locations, and
arXiv:2601.14750v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting has achieved remarkable success in unlocking the reasoning capabilities of Large Language Models (LLMs). Although C
arXiv:2603.23404v2 Announce Type: replace-cross Abstract: Existing Multimodal Large Language Models (MLLMs) struggle with 3D spatial reasoning, as they fail to construct structured abstractions of the
arXiv:2610.06366v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed for automated software vulnerability analysis. Binary classification alone is insufficient; pra
arXiv:2604.05114v2 Announce Type: replace-cross Abstract: We study a QA curation pipeline for improving long-context complex reasoning in large language models (LLMs). Our approach, pi^2, constructs h
arXiv:2610.00571v1 Announce Type: cross Abstract: Large reasoning models (LRMs) have achieved substantial improvements in solving complex mathematical problems, but often produce lengthy, repetitive,
arXiv:2606.13607v3 Announce Type: replace Abstract: When large language models (LLMs) fail to generalize or make content-sensitive errors in reasoning, it is often taken as evidence that LLMs are not
arXiv:2610.01938v1 Announce Type: cross Abstract: Exam-style accuracy does not establish whether large language models (LLMs) reason well over clinical records. We define clinical reasoning as integra
arXiv:2609.38717v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) commonly perform spatial reasoning through chain-of-thought (CoT), encoding intermediate reasoning as autoregress
arXiv:2609.29560v1 Announce Type: new Abstract: Reasoning-enhanced universal multimodal embeddings (UME) improve heterogeneous retrieval, but plausible rationales do not necessarily produce discrimina
arXiv:2608.07417v1 Announce Type: cross Abstract: Real-world video reasoning often involves multimodal, multi-source inputs, whereas existing video reasoning tasks typically assume a simplified video-
arXiv:2607.19932v1 Announce Type: new Abstract: Spoken language models (SLMs) enable natural human-computer interaction, but their reasoning ability still lags behind that of text-based large language
arXiv:2601.18383v2 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) excel at solving complex problems by explicitly generating a reasoning trace before deriving the final answer. H
arXiv:2606.02835v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) improve performance by generating explicit intermediate reasoning traces through increased test-time compute, yet the assu
arXiv:2510.20956v2 Announce Type: replace-cross Abstract: We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaki
arXiv:2604.19716v1 Announce Type: new Abstract: Large Language Models (LLMs) still struggle with multi-step logical reasoning. Existing approaches either purely refine the reasoning chain in natural l
arXiv:2604.15490v1 Announce Type: new Abstract: Recent developments in reasoning capabilities have enabled large language models to solve increasingly complex mathematical, symbolic, and logical tasks
arXiv:2603.21094v3 Announce Type: replace Abstract: Human annotation is central to NLP evaluation, yet subjective tasks often exhibit substantial variability across annotators. While large language mo
arXiv:2506.18831v2 Announce Type: replace Abstract: Large Language Models employing extended chain-of-thought (CoT) reasoning often suffer from the overthinking phenomenon, generating excessive and re
arXiv:2512.12623v3 Announce Type: replace-cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced cross-modal understanding and reasoning by incorpo
arXiv:2610.15810v1 Announce Type: new Abstract: The introduction of long chain-of-thought (CoT) reasoning and external tools has substantially improved the performance of multimodal large language mod
arXiv:2610.18834v1 Announce Type: new Abstract: Visual reasoning is an important capability for vision-language models (VLMs) to understand visual evidence, spatial structure, constraints, and state c
arXiv:2610.10405v1 Announce Type: cross Abstract: Monitoring the chain-of-thought of reasoning artificial intelligence (AI) models remains a key approach to detecting deception and other forms of misb
arXiv:2610.02703v1 Announce Type: new Abstract: On-policy distillation (OPD) improves large language model reasoning by training students on their own rollouts with dense token-wise supervision from t
arXiv:2609.31121v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising safety technique for reasoning models, enabling detection of problematic reasoning before models act. A
arXiv:2609.27156v1 Announce Type: new Abstract: Large reasoning models can produce correct yet unnecessarily long reasoning traces. Existing methods improve reasoning efficiency with trajectory-level
arXiv:2604.02007v3 Announce Type: replace Abstract: Building general-purpose reasoning models using reinforcement learning with verifiable rewards (RLVR) across diverse domains has been widely adopted
arXiv:2609.03633v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning improves large reasoning models (LRMs) on complex tasks but often produces long, redundant traces. Recent training-fr
arXiv:2512.15662v4 Announce Type: replace Abstract: Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions.
arXiv:2608.30214v1 Announce Type: new Abstract: Scientific reasoning remains challenging for open-source models, largely due to the lack of high-quality scientific reasoning data. Existing datasets ar
arXiv:2608.12325v1 Announce Type: new Abstract: Autonomous reasoning is among the most scientifically and economically motivating topics in AI today. Historically the purview of symbolic AI, recent ad
arXiv:2608.12391v1 Announce Type: cross Abstract: Graph reasoning provides a promising testbed for evaluating the reasoning ability of large language models (LLMs), as graph instances can be programma
arXiv:2608.01631v1 Announce Type: new Abstract: KV cache compression is commonly evaluated by final-answer accuracy, implicitly assuming that preserving the answer also preserves the reasoning that su
arXiv:2602.05307v2 Announce Type: replace Abstract: Large reasoning models (LRMs) achieve strong performance by producing long chains of thought, but their inference costs are high and often generate
arXiv:2607.27304v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) generate chain-of-thought (CoT) reasoning before answering clinical questions, but whether this reasoning causal
arXiv:2603.25629v2 Announce Type: replace Abstract: While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, m