Knowledge catalogue
arXiv:2604.13759v1 Announce Type: cross Abstract: Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Cu
arXiv:2505.14264v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as an effective approach for enhancing the reasoning capabilities of large language models (LLMs), esp
arXiv:2604.12660v1 Announce Type: new Abstract: In nonmonotonic reasoning from conditional belief bases, an inference operator satisfying syntax splitting postulates allows for taking only the relevan
arXiv:2602.00181v3 Announce Type: replace-cross Abstract: Understanding camera dynamics is a fundamental pillar of video spatial intelligence. However, existing multimodal models predominantly treat t
arXiv:2604.12896v1 Announce Type: new Abstract: Multimodal language models (MLLMs) are increasingly paired with vision tools (e.g., depth, flow, correspondence) to enhance visual reasoning. However, d
Databricks explores how agentic AI systems can reason over both structured data (such as tables and databases) and unstructured data (such as documents and text) to answer complex business questions.
arXiv:2604.00013v2 Announce Type: replace-cross Abstract: Multimodal sentiment analysis aims to integrate textual, acoustic, and visual information for deep emotional understanding. Despite the progre
arXiv:2604.10420v1 Announce Type: new Abstract: Large language models (LLMs) enable waveform-to-text ECG interpretation and interactive clinical questioning, yet most ECG-LLM systems still rely on wea
arXiv:2604.10681v1 Announce Type: cross Abstract: Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior backdo
arXiv:2604.11177v1 Announce Type: new Abstract: We benchmark how internal reasoning traces, which we call thought streams, affect video scene understanding in vision-language models. Using four config
arXiv:2604.11137v1 Announce Type: new Abstract: The integration of Large Language Models (LLMs) into clinical decision support is critically obstructed by their opaque and often unreliable reasoning.
arXiv:2604.09907v1 Announce Type: cross Abstract: To improve crop genetics, high-throughput, effective and comprehensive phenotyping is a critical prerequisite. While such tasks were traditionally per
arXiv:2507.00748v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image re
arXiv:2601.22361v2 Announce Type: replace-cross Abstract: Assessing the veracity of online content has become increasingly critical. Large language models (LLMs) have recently enabled substantial prog
arXiv:2604.11411v1 Announce Type: new Abstract: Reasoning video object segmentation predicts pixel-level masks in videos from natural-language queries that may involve implicit and temporally grounded
arXiv:2604.10511v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for causal and counterfactual reasoning, yet their reliability in real-world policy evaluation remain
arXiv:2604.10386v1 Announce Type: new Abstract: Accurate estimation of cancer risk from longitudinal electronic health records (EHRs) could support earlier detection and improved care, but modeling su
arXiv:2511.08947v5 Announce Type: replace Abstract: Time series forecasting plays a crucial role in decision-making across many real-world applications. Despite substantial progress, most existing met
arXiv:2604.09069v1 Announce Type: cross Abstract: Court Judgment Prediction and Explanation (CJPE) aims to predict a judicial decision and provide a legally grounded explanation for a given case based
arXiv:2604.06262v1 Announce Type: cross Abstract: Contextual clinical reasoning demands robust inference grounded in complex, heterogeneous clinical records. While state-of-the-art fine-tuning, in-con
arXiv:2604.06501v1 Announce Type: new Abstract: Analogical reasoning is a hallmark of human intelligence, enabling us to solve new problems by transferring knowledge from one situation to another. Yet
arXiv:2610.20832v1 Announce Type: cross Abstract: Despite their extensive pretraining knowledge and strong reasoning capabilities, large language models (LLMs) struggle to adaptively gather informatio
arXiv:2610.22067v1 Announce Type: new Abstract: Long-context language models support ever longer context windows, and evaluations typically treat context length as the main indicator of difficulty. Ho
arXiv:2610.21151v1 Announce Type: cross Abstract: Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured by conventional technical ass
arXiv:2606.18947v2 Announce Type: replace Abstract: Production LLM agents increasingly depend on real-time search, yet native search grounding bundles retrieval policy, provider choice, evidence injec
arXiv:2610.20085v1 Announce Type: cross Abstract: Automatic prompt optimization (APO) has shown strong effectiveness for text-based LLMs and LLM systems, but its application to audio-visual understand
arXiv:2610.20370v1 Announce Type: new Abstract: Hate speech has become increasingly prevalent on social media, raising concerns about its detection, interpretation, and moderation. Persian, a relative
arXiv:2610.15091v1 Announce Type: cross Abstract: Argument structures represent how individual arguments interact within a discourse. However, leveraging these structures to infer meaningful knowledge
Nemotron 3.5 Super VL from @NVIDIAAI is live in LM Studio! • 120B total / 12B active MoE • Supports vision input, reasoning • Trained for visual understanding, tool use Requires ~70GB RAM to run local
arXiv:2610.17271v1 Announce Type: new Abstract: Propaganda detection systems usually operate as black boxes, lacking explanations. To address this, we hypothesise that persuasive techniques contain de
arXiv:2610.16315v1 Announce Type: new Abstract: Test-time agentic computation can improve multimodal large language models (MLLMs) through planning, tool use, iterative perception, and reflection, but
arXiv:2610.14679v1 Announce Type: new Abstract: We introduce HumanPhys, a human-centric benchmark for real-world physical perception, and a training corpus emitted by the same pipeline. Each question
arXiv:2610.17900v1 Announce Type: cross Abstract: Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers wi
arXiv:2610.18025v1 Announce Type: cross Abstract: Test-time scaling has enabled LLMs to solve increasingly complex reasoning, discovery, and optimization tasks. However, existing approaches often gath
arXiv:2610.14403v1 Announce Type: new Abstract: Learning reusable skills can improve visual reasoning agents, yet applying a skill still requires the agent to implement or invoke a procedure and produ
arXiv:2610.13098v1 Announce Type: new Abstract: Visual agents for symbolic graphics reasoning depend on executable world representations, yet continued improvement remains bottlenecked by ambiguous su
arXiv:2610.12022v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sociotechnical systems where social attribution, the reasoning process attributing external
arXiv:2610.08966v2 Announce Type: replace Abstract: Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek det
arXiv:2610.10893v1 Announce Type: new Abstract: Video-language models commonly assume that more temporal observations lead to more reliable reasoning. We question this assumption and argue that the ke
arXiv:2610.12402v1 Announce Type: cross Abstract: Existing spatial reasoning benchmarks mainly test spatial perception: reading off relations already visible in the input. Yet real-world spatial intel
arXiv:2610.09520v1 Announce Type: new Abstract: Large vision-language models (VLMs) provide powerful open-world perception and reasoning for autonomous driving, but their high computational cost and i
arXiv:2610.05685v2 Announce Type: replace Abstract: Reasoning models write most of their KV cache while decoding long chains of thought (CoT), so the cache has to be compressed online under a fixed me
arXiv:2610.09118v1 Announce Type: new Abstract: Topology reasoning jointly detects 3D lanes and traffic elements from multi-view images and infers their structural connectivity. Current methods model
arXiv:2610.08680v1 Announce Type: cross Abstract: Endpoint accuracy on abstract-reasoning benchmarks does not reveal whether a language model has acquired a transferable rule or fit distribution-speci
arXiv:2610.08563v1 Announce Type: new Abstract: Sequence-level power sampling has recently emerged as a training-free approach to reasoning by sampling from a sharpened output distribution of a base l
arXiv:2610.06896v1 Announce Type: new Abstract: Frontier multimodal large language models (MLLMs) are increasingly positioned as general purpose visual reasoners as part of the quest for artificial ge
arXiv:2610.07255v1 Announce Type: new Abstract: Neural algorithmic reasoning, or aligning a neural network with an algorithmic paradigm, has emerged as an approach to solving polynomial-time-solvable
arXiv:2610.08761v1 Announce Type: new Abstract: Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges constr
arXiv:2610.06861v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become the dominant paradigm for eliciting multi-step reasoning in large language models, an
arXiv:2610.04777v1 Announce Type: new Abstract: Inflammatory bowel disease (IBD) requires frequent imaging-based assessment, yet interpretation of modalities such as wireless capsule endoscopy (WCE) a
arXiv:2610.02351v1 Announce Type: new Abstract: ReAct-based agents typically rely on a single LLM policy to propose actions, interact with the environment, and decide when a task is complete. This cou
Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active. - Frontier reasoning efficiency - Advances the Western open frontier on coding & agentic tasks - Trai
arXiv:2606.13176v2 Announce Type: replace Abstract: Mental health problems such as anxiety, depression, and suicide remain urgent global challenges, where timely and accurate assessment is critical fo
arXiv:2610.00047v1 Announce Type: new Abstract: Diversity collapse in parallel chain-of-thought has motivated inference-time interventions built on a natural design: when a process reward model (PRM)
arXiv:2610.01729v1 Announce Type: new Abstract: Algorithmic mathematical reasoning requires reliable decomposition, computation, and aggregation. Final-answer rewards provide limited guidance on inter
arXiv:2602.12486v2 Announce Type: replace-cross Abstract: Humans appear to represent objects when reasoning about physics with coarse, volumetric 'bodies' that smooth concavities, trading fine visual
arXiv:2610.01140v1 Announce Type: new Abstract: Sampling multiple solutions spends computation on intermediate deductions and unfinished arguments as well as final answers. We introduce ReSolve, a tra
arXiv:2609.39473v1 Announce Type: new Abstract: Autonomous agents increasingly rely on memory to generalize beyond their training environments. However, agents are bounded by what they have seen and b
arXiv:2609.39021v1 Announce Type: new Abstract: Reinforcement learning (RL) has substantially improved the reasoning ability of multimodal language models through verifiable rewards and increasingly f
arXiv:2511.00421v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise in medical applications, but their ability to detect and correct errors in clinical texts remains un