Knowledge catalogue
arXiv:2511.11984v2 Announce Type: replace Abstract: Fine-grained glomerular subtyping is essential for kidney biopsy interpretation, yet it presents a harder setting than the broad organ- or disease-l
arXiv:2410.12537v4 Announce Type: replace Abstract: Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current
arXiv:2610.16224v1 Announce Type: new Abstract: Text-to-image models have made remarkable progress in visual fidelity and instruction following, yet complex compositional generation remains challengin
arXiv:2610.14117v1 Announce Type: new Abstract: GPT-6 Astra provides robust embodied reasoning, but frequent external queries increase inference time and token costs. We equip a frozen pi_{0.5} policy
arXiv:2511.17366v2 Announce Type: replace-cross Abstract: Building a generalist robot that can perceive, reason, and act across diverse tasks remains an open challenge, especially for dexterous manipu
arXiv:2610.18677v1 Announce Type: new Abstract: Online decision-making faces a tension between efficient inference and long-horizon reasoning. Value-based methods rely on short-horizon bootstrapping t
arXiv:2610.16355v1 Announce Type: new Abstract: Generalist robot manipulation can benefit from pretrained vision-language models (VLMs) for semantic reasoning and video generation models (VGMs) for wo
arXiv:2610.16967v1 Announce Type: new Abstract: Physical AI is commonly formulated around an explicitly specified task: given a goal or instruction, a system perceives, reasons, and acts. In many real
arXiv:2603.19844v3 Announce Type: replace Abstract: Multimodal MRI provides complementary information for brain tumor segmentation, but high accuracy alone does not reveal whether a model relies on cl
arXiv:2610.14572v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves the reasoning capabilities of large language models, but remains computationally expensive and s
arXiv:2605.05965v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a key approach for improving the reasoning abilities of large language models. Howe
arXiv:2606.12956v2 Announce Type: replace Abstract: Long-horizon robot mobile manipulation requires continual reasoning about localization, environment changes, and task progress, all of which are cha
arXiv:2610.17189v1 Announce Type: cross Abstract: Soft tokens have so far been used to replace discrete chain-of-thought in latent reasoning methods. These approaches typically require multi-stage tra
arXiv:2606.16767v2 Announce Type: replace Abstract: Existing image editing methods can be generally categorized into textual instruction-based and visual prompt-based ones. Textual instructions are se
arXiv:2610.16165v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in solving complex tasks in coding, mathematical logic, and iterative reasoning
arXiv:2610.15389v1 Announce Type: new Abstract: Video understanding agents rely on a harness to acquire evidence, use tools, and reason, but improving it requires substantial effort. Recent self evolu
arXiv:2610.13653v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved LLM reasoning, yet growing evidence suggests it mainly performs distr
arXiv:2610.13144v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have emerged as a promising paradigm for enhancing complex reasoning through role specialization and collaboration,
arXiv:2610.13236v1 Announce Type: cross Abstract: Recent advances have significantly improved the performance of Abstract Meaning Representation (AMR) parsers, yet determining when their outputs can b
arXiv:2610.12575v1 Announce Type: cross Abstract: Modern video-language models are increasingly treated as general-purpose video reasoners, yet it remains unclear whether they robustly capture tempora
arXiv:2606.16215v2 Announce Type: replace-cross Abstract: Multi-turn tool-use agents must reason, call tools, and adapt to observations across several interaction turns. Post-training such agents is c
arXiv:2610.13438v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a key paradigm for improving large language model (LLM) agents, enabling stronger reasoning, planning, and to
arXiv:2610.12596v1 Announce Type: new Abstract: Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short a
arXiv:2610.12828v1 Announce Type: new Abstract: Outcome-supervised group-relative policy optimization (GRPO) assigns the same advantage to every token in an LLM agent trajectory, leaving useful and un
arXiv:2610.12832v1 Announce Type: new Abstract: Pretrained vision-language models (VLMs) already exhibit strong visual, spatial and reasoning capabilities relevant to robotic manipulation. The key cha
arXiv:2610.13605v1 Announce Type: new Abstract: Dynamic vocabularies built on-the-fly via Lempel-Ziv-Welch (LZW) compression let a language model represent the same text in fewer tokens, but prior wor
I wanted to compare gemma 4 31b qat q4 and qwen3.8 27b iq4_nl, so I run SWEBench verfied on them. The original gemma 4 chat template doesn't work with preserve reasoning, so google released an update
I was looking into finalizing my daily driver and it was not clear which one to chose. I have a 5060ti 16GB so I picked the following contenders, which seem to be working at a reasonable speed on my h
arXiv:2610.12008v1 Announce Type: new Abstract: Abstract argumentation frameworks (AFs) introduced by Dung provide a formal foundation for non-monotonic reasoning in artificial intelligence. While dec
arXiv:2610.11299v1 Announce Type: new Abstract: Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, whil
arXiv:2606.18810v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative
arXiv:2610.12303v1 Announce Type: new Abstract: Declarative logic programs offer a powerful and interpretable abstraction for encoding relational structure and neurosymbolic reasoning, by expressing d
arXiv:2610.12458v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are rapidly evolving toward continuous audio--visual reasoning, creating an urgent need for evaluations that ex
arXiv:2603.07980v2 Announce Type: replace-cross Abstract: As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks
arXiv:2610.11529v1 Announce Type: new Abstract: Self-distillation can improve reasoning without a separately trained, more capable teacher, but its effectiveness depends on how the self-teacher gains
arXiv:2610.10624v1 Announce Type: cross Abstract: Spatial audio-visual understanding requires models to recognize not only what is present, but also where events occur and how they relate across modal
arXiv:2610.11366v1 Announce Type: new Abstract: Spatial coding agents significantly improve spatial reasoning in Multimodal Large Language Models (MLLMs) by using external tools to generate verified e
arXiv:2610.11450v1 Announce Type: new Abstract: We study how a coding agent learns across a sequence of abstract reasoning tasks. The agent runs on a frozen foundation model inside a fixed harness and
arXiv:2602.02639v2 Announce Type: replace-cross Abstract: LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process i
arXiv:2610.08840v1 Announce Type: new Abstract: Large language models (LLMs) often abandon a correct answer, or endorse a user's position, once the user pushes back. This behavior, called sycophancy,
arXiv:2610.10438v1 Announce Type: new Abstract: Embodied and assistive agents must do more than recognize objects: they must reason about where an object belongs given the layout of an environment and
arXiv:2610.09684v1 Announce Type: new Abstract: Test-time scaling (TTS) improves the reasoning capabilities of large language models by allocating additional inference computation. Existing approaches
arXiv:2610.09914v1 Announce Type: new Abstract: Reinforcement learning is crucial for improving large language models' reasoning and generalization. It relies on massive rollouts whose lengths become
arXiv:2610.09152v1 Announce Type: new Abstract: Multilingual LLM benchmarks omit Slovak, a morphologically rich West Slavic language of five million speakers, or cover it only by machine translation.
arXiv:2610.09087v1 Announce Type: new Abstract: Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to ig
arXiv:2607.11119v2 Announce Type: replace Abstract: Robot manipulation is a complex task that requires visual perception, physical reasoning, planning, and closed-loop control. General-purpose foundat
Editor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your
arXiv:2610.08552v1 Announce Type: new Abstract: Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretable concepts, but originally requ
arXiv:2610.07601v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) provides a natural framework for adapting pretrained models to video temporal grounding, where gen
arXiv:2610.07480v1 Announce Type: new Abstract: Software-based legal assistance systems have leveraged many different forms of knowledge representation and reasoning. This article explores how documen
arXiv:2610.08482v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly being applied to three-dimensional medical imaging, but their application to knee MRI remains limited,
arXiv:2610.07706v1 Announce Type: cross Abstract: Autoregressive large language models (LLMs) have rapidly advanced in capability, but their increasing scale comes with substantial computational and m
arXiv:2610.05281v2 Announce Type: replace Abstract: Modern agents increasingly ground their reasoning in observations returned by tools, such as file contents read from a workspace. However, the data
arXiv:2609.33155v2 Announce Type: replace Abstract: Test-time scaling and post-training have improved LLM performance in coding and mathematical reasoning, but their effectiveness for individual stanc
arXiv:2610.05303v1 Announce Type: new Abstract: A large language model (LLM) agent solves long-horizon tasks through many reasoning-action turns, with one verification signal at termination. Deployed
Banger paper from Meta AI on research agents that decide what to investigate next. (bookmark it) If you run long-horizon research agents, choosing the next investigation is hard to learn, because thos
arXiv:2610.04662v1 Announce Type: cross Abstract: Temporal logic provides designers a formal reasoning tool for specifying complex spatio-temporal behaviors and tasks for autonomous systems. Many tech
arXiv:2610.05615v1 Announce Type: cross Abstract: Multi-agent debate (MAD) has emerged as an effective paradigm to improve the reasoning capabilities of large language models (LLMs) and is increasingl
arXiv:2610.06671v1 Announce Type: new Abstract: Small language models are often post-trained as students on reasoning traces from stronger teacher models to efficiently learn new skills. However, toke
arXiv:2610.05538v1 Announce Type: new Abstract: We introduce Loop Flow Transformers (LiFT), a family of looped generative models that scales computation by repeatedly applying a shared Diffusion Trans