Knowledge catalogue
arXiv:2603.01121v2 Announce Type: replace Abstract: While deep learning-based weather forecasting paradigms have made significant strides, addressing extreme weather diagnostics remains a formidable c
arXiv:2607.04344v1 Announce Type: cross Abstract: While Large Vision-Language Models (VLMs) demonstrate remarkable generic capabilities, their clinical reasoning in specialized domains like ocular sur
arXiv:2607.05013v1 Announce Type: new Abstract: Although LLMs have made significant progress in mathematical reasoning, determining whether a mathematical problem is solvable remains a fundamental yet
arXiv:2603.23844v2 Announce Type: replace Abstract: Recent work provides overwhelming evidence that LLMs, even those trained to scale their reasoning trace, quickly deteriorate at planning as problems
arXiv:2607.05188v1 Announce Type: new Abstract: A coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests, yet little is known about what the
arXiv:2603.17484v2 Announce Type: replace Abstract: Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on l
arXiv:2603.13334v4 Announce Type: replace-cross Abstract: Lipschitz-based robustness certification bounds a network's sensitivity through concrete numerical computation rather than symbolic reasoning,
arXiv:2607.04332v1 Announce Type: new Abstract: In this paper, we consider the setting where large language models (LLMs) are trained using reinforcement learning (RL) to simultaneously improve reason
arXiv:2601.09097v3 Announce Type: replace Abstract: Multi-constraint planning involves identifying, evaluating, and refining candidate plans while satisfying multiple, potentially conflicting constrai
arXiv:2607.03825v1 Announce Type: cross Abstract: Audio-Visual Question Answering (AVQA) extends classical VQA by requiring joint reasoning over video and synchronized audio. However, many AVQA system
For years, enterprise AI has been synonymous with conversational AI — the customer service bots and digital assistants we interact with every day. But today, the market has shifted. We’ve officially m
arXiv:2607.03591v1 Announce Type: cross Abstract: Recent studies on multimodal traffic accident understanding have mainly relied on infrastructure-camera footage, satellite imagery, or structured cras
arXiv:2509.10656v2 Announce Type: replace-cross Abstract: For groups of autonomous agents to achieve a particular goal, they must engage in coordination and long-horizon reasoning. Rather than relying
arXiv:2607.02402v2 Announce Type: replace Abstract: Vision-language models (VLMs) can follow complex textual instructions, yet they struggle to reason from purely visual context. In particular, curren
arXiv:2603.20659v2 Announce Type: replace Abstract: Large scale pre-training on text and image data along with diverse robot demonstrations has helped Vision Language Action models (VLAs) to generaliz
The year 2026 could be remembered as the moment when storage technology received a massive promotion. The reason is that the current transition from simple chatbots to agentic AI systems has raised th
arXiv:2601.04387v2 Announce Type: replace Abstract: Negotiation is a core component of social intelligence, requiring agents to balance strategic reasoning, cooperation, and social norms. Recent work
arXiv:2607.04969v1 Announce Type: cross Abstract: The training paradigm of large language models has shifted from traditional one-pass training to multi-epoch training, as reasonable reuse of limited
arXiv:2607.05394v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on ev
arXiv:2607.03461v1 Announce Type: new Abstract: World models aim to capture environment dynamics in ways that support perception, reasoning, and action, and have recently become a central direction in
In this post, we present a multi-step pipeline directed by Amazon Nova, which uses its contextual vision reasoning to coordinate complementary tools, including Meta’s open-source Segment Anything Mode
b9870 is a llama.cpp release dated July 3, 2026 , which includes fixes for StepFun parser chat handling to address long reasoning loops . The release provides pre-built binaries for multiple platforms
arXiv:2607.02222v1 Announce Type: cross Abstract: Vision-Language Navigation has increasingly emphasized high-level instruction reasoning, memory, global map construction, and instruction decompositio
arXiv:2607.01490v1 Announce Type: cross Abstract: Reinforcement learning post-training dramatically improves LLM reasoning, but suffers from training instability and diversity collapse. Advantage func
arXiv:2607.02376v1 Announce Type: new Abstract: Recent advances in agentic AI are producing increasingly complex autonomous systems that integrate large language models, world models, optimization eng
arXiv:2506.01623v4 Announce Type: replace Abstract: Humans excel at analogical reasoning - applying knowledge from one task to a related one with minimal relearning. In contrast, reinforcement learnin
arXiv:2607.02277v1 Announce Type: new Abstract: Safe landing-site assessment in unstructured environments remains a key challenge for autonomous UAV deployment, as vision-only learning approaches ofte
arXiv:2607.01306v1 Announce Type: new Abstract: Counterfactual explanations explain machine learning predictions by identifying minimal input changes that would alter a model's decision. Although many
arXiv:1808.07645v5 Announce Type: replace-cross Abstract: The 20 Questions (Q20) game is a well known game which encourages deductive reasoning and creativity. In the game, the answerer first thinks o
arXiv:2607.01595v1 Announce Type: new Abstract: As the scale and complexity of cloud-based AI systems continue to escalate, ensuring service reliability through rapid fault detection and adaptive reco
arXiv:2607.01612v1 Announce Type: new Abstract: Training large language models (LLMs) with reinforcement learning (RL) has significantly advanced their performance on reasoning and question-answering
arXiv:2607.00062v1 Announce Type: cross Abstract: High pass rates on established programming benchmarks such as HumanEval and LiveCodeBench do not always show whether a model can reason about algorith
arXiv:2607.00152v1 Announce Type: cross Abstract: Three of the most popular methods for training language models to reason look like three different tricks. They are not. All three adjust a single num
arXiv:2602.03370v2 Announce Type: replace Abstract: Handwritten mathematical expression recognition (HMER) requires reasoning over diverse symbols and structures, yet autoregressive models struggle wi
arXiv:2601.14660v2 Announce Type: replace-cross Abstract: Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data. These abilities are enabling t
arXiv:2512.20907v2 Announce Type: replace Abstract: 3D Visual Grounding (3DVG) is a critical bridge from vision-language perception to robotics, requiring both language understanding and 3D scene reas
arXiv:2607.00444v1 Announce Type: cross Abstract: Spatiotemporal motion planning, especially in multi-robot settings, requires robots to reason about collision-free regions that change over time, whic
arXiv:2607.00465v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) rely extensively on Visual Instruction Tuning (VIT) to elicit their multimodal reasoning capabilities. However, w
arXiv:2607.00339v1 Announce Type: new Abstract: Conversational data is increasingly used as a persistent source of user state for long-running assistants and AI agents. However, querying this data rem
arXiv:2407.18950v5 Announce Type: replace Abstract: Kant's Critique of Pure Reason, a major contribution to the history of epistemology, proposes a table of categories to elucidate the structure of th
François Chollet observed that all leading contenders on the ARC-AGI-3 benchmark employ a similar methodological approach, suggesting a convergence in techniques for solving abstract reasoning tasks.
You really need your own benchmarks. If you are translating hieroglyphics, use Gemini 3.5 Flash. If you are running a vending machine use Opus 4.8. (This is one reason why I am skeptical of just swapp
arXiv:2606.30877v1 Announce Type: cross Abstract: Recent literature shows that large language models (LLMs) are useful for general-purpose tasks yet perform poorly on specific domain ones. One reason
arXiv:2606.31229v1 Announce Type: new Abstract: Ideation plays a pivotal role in scientific discovery. Recent LLM, especially AI Scientist systems, show promising potential for automated ideation. How
arXiv:2606.31200v1 Announce Type: new Abstract: Generalizable robotic grasping in cluttered environments is essential for deploying manipulators in unstructured human spaces, yet existing VLM-based me
Autoresearch describes a feedback mechanism where AI agents can evaluate their own outputs and use that introspection to iteratively improve their reasoning and decision-making capabilities. This conc
arXiv:2606.31134v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated exceptional capabilities in mathematical reasoning, they frequently produce subtle errors that evad
arXiv:2606.31493v1 Announce Type: new Abstract: Visual signals play a crucial role in policy learning by enabling models to capture object motion and interaction dynamics. Just as humans reason about
arXiv:2606.31432v1 Announce Type: new Abstract: Medical multiple-choice question answering requires parameter-efficient adaptation across heterogeneous knowledge domains and reasoning operations. A me
arXiv:2606.31497v1 Announce Type: new Abstract: Cloud-hosted foundation models enable robots to use semantic reasoning beyond onboard computational limits. In this setting, the robot executes a curren
arXiv:2606.31654v1 Announce Type: cross Abstract: Recent advances in multimodal large models have significantly improved UAV vision-language navigation (UAV-VLN) by enhancing high-level perception and
In this post, you will learn how Inscribe developed an agentic AI system using Amazon Bedrock that reasons across documents the way an expert fraud analyst would. With this new agentic AI system, Insc
arXiv:2606.12634v2 Announce Type: replace-cross Abstract: Long-horizon tool-use reinforcement learning learns from outcome verification, but trajectory-level advantages are broadcast over reasoning, A
arXiv:2606.31037v1 Announce Type: new Abstract: Laboratory automation has made remarkable progress through robotic platforms and AI-driven scientific reasoning. However, many laboratory operations (e.
arXiv:2606.31187v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have rapidly advanced video understanding, achieving strong zero-shot and few-shot recognition across standard
arXiv:2606.30789v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has become a standard tool for improving the reasoning ability of large language models, yet its training dyna
arXiv:2606.30851v1 Announce Type: cross Abstract: Improving the reliability of large language models (LLMs) at inference time is a central challenge in structured reasoning tasks such as Text-to-SQL.
arXiv:2603.16250v2 Announce Type: replace-cross Abstract: LVLMs encounter significant challenges in image understanding and visual reasoning, leading to critical perception failures. Visual prompts, w
Ahmad Osman discusses the technological and practical reasons why locally-run AI models are becoming increasingly competitive with cloud-based alternatives, likely covering improvements in model effic
arXiv:2606.28467v1 Announce Type: cross Abstract: Appliance-level energy monitoring in office buildings produces noisy alerts that non-expert facility managers struggle to use. This paper proposes an