Knowledge catalogue
arXiv:2509.23108v2 Announce Type: replace Abstract: Can visual imagery be driven solely by language? This idea goes against cognitive science's traditional view that visual mental imagery is only poss
arXiv:2510.01499v2 Announce Type: replace-cross Abstract: With the rapid progress of multi-agent large language model (LLM) reasoning, how to effectively aggregate answers from multiple LLMs has emerg
arXiv:2605.19436v1 Announce Type: cross Abstract: When a model produces a correct solution under reinforcement learning with verifiable rewards (RLVR), every token receives the same reward signal rega
arXiv:2605.18868v1 Announce Type: cross Abstract: While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversari
arXiv:2605.19604v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly act inside real workspaces, where tools and skills determine whether model reasoning becomes reliable act
arXiv:2605.18822v1 Announce Type: cross Abstract: Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, prefere
arXiv:2605.19522v1 Announce Type: new Abstract: Pairwise image quality assessment (IQA) in professional photography requires a model not only to identify the preferred image between two candidates, bu
arXiv:2605.19644v1 Announce Type: cross Abstract: Knowledge Graphs (KGs) are a powerful representation of linked data, offering flexibility, semantic richness, and support for knowledge enrichment and
arXiv:2605.19815v1 Announce Type: cross Abstract: Legal proposition generation is central to legal reasoning and doctrinal scholarship, yet remain under-examined in Legal NLP. This paper investigates
arXiv:2605.18838v1 Announce Type: cross Abstract: Scaling laws predict loss from compute but not how capabilities interact. We measure the coupling between reasoning and truthfulness across 63 base mo
arXiv:2605.19330v1 Announce Type: new Abstract: LLM agents organize behavior through skills - structured natural-language specifications governing how an agent reasons, retrieves, and responds. Unlike
arXiv:2605.19660v1 Announce Type: cross Abstract: The rapid advancement toward long-context reasoning and multi-modal intelligence has made the memory footprint of the Key-Value (KV) cache a dominant
arXiv:2605.19351v1 Announce Type: cross Abstract: Generative agents based on large language models reproduce believable human behavior in cooperative settings, but how they should reason in situations
arXiv:2605.19943v1 Announce Type: new Abstract: Tiny Recursive Models (TRM) solve complex reasoning tasks with a fraction of the parameters of modern large language models (LLMs) by iteratively refini
arXiv:2605.19193v1 Announce Type: new Abstract: Multi-agent LLM debate improves factuality and reasoning, but most recipes pick a fixed round count, over-spending on easy items and under-spending on h
arXiv:2505.23747v2 Announce Type: replace-cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving
arXiv:2605.18840v1 Announce Type: cross Abstract: Leaderboards rank frontier models on independent axes but do not reveal whether capabilities reinforce or trade off across releases -- and at the fron
arXiv:2605.19035v1 Announce Type: new Abstract: The rapid advancement of Large Language Models has given rise to autonomous LLM-based agents capable of complex reasoning and execution. As these agents
arXiv:2605.19444v1 Announce Type: cross Abstract: Test-time reinforcement learning (TTRL) reports substantial accuracy gains on mathematical reasoning benchmarks using majority vote as a pseudo-label
arXiv:2605.19425v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for advanced reasoning in Large Language Models (LLMs), but rol
arXiv:2601.22569v2 Announce Type: replace-cross Abstract: Large language model (LLM) based agents are increasingly used to automate financial transactions, yet their reliance on contextual reasoning e
arXiv:2605.16291v1 Announce Type: cross Abstract: With the growing adoption of AI systems, reasoning about how society can exert control over AI becomes an increasingly urgent problem. Existing work o
arXiv:2605.18529v1 Announce Type: new Abstract: The alignment of Large Language Models (LLMs) for complex reasoning heavily relies on Reinforcement Learning with Verifiable Rewards (RLVR). However, st
arXiv:2605.18133v1 Announce Type: cross Abstract: LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These ca
arXiv:2603.23566v2 Announce Type: replace-cross Abstract: Optimizing AscendC (Ascend C) operators for Ascend NPUs is difficult for two reasons. First, unlike CUDA, the ecosystem offers few public kern
arXiv:2605.16280v1 Announce Type: cross Abstract: Automating legal reasoning forces a choice between imperfect alternatives: symbolic systems offer transparency but struggle with ambiguity, whereas ne
arXiv:2603.00876v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical
arXiv:2605.17965v1 Announce Type: cross Abstract: Bug localization remains a key bottleneck in downstream software maintenance tasks, including root cause analysis, triage, and automated program repai
arXiv:2605.17255v1 Announce Type: new Abstract: Formal theorem-proving benchmarks enable mechanically verifiable evaluation of mathematical reasoning in large language models. However, existing benchm
arXiv:2605.17214v1 Announce Type: new Abstract: While Large Language Models (LLMs) have revolutionized scientific text processing, they exhibit a significant capability gap when interpreting chemical
arXiv:2605.18202v1 Announce Type: cross Abstract: Neuro-Symbolic Concept-based Models (NeSy-CBMs) are a family of architectures that integrate neural networks with symbolic reasoning for enhanced reli
arXiv:2605.17826v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) excel at multimodal reasoning, yet it remains unclear whether their answers are grounded in visual evidence or driven by
arXiv:2510.21712v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs) through the dyna
arXiv:2605.17295v1 Announce Type: cross Abstract: Modern reasoning agents are increasingly evaluated on their ability to generate multiple valid solution paths, plans, or tool-use traces for a given i
arXiv:2601.13839v2 Announce Type: replace Abstract: Social media imagery provides a low-latency source of situational information during natural and human-induced disasters, enabling rapid damage asse
arXiv:2502.02463v3 Announce Type: replace-cross Abstract: While Bayesian inference provides a principled framework for reasoning under uncertainty, its widespread adoption is limited by the intractabi
arXiv:2605.11223v2 Announce Type: replace Abstract: Vision-Language(-Action) Models (VLMs) are increasingly applied to interactive environments, yet existing benchmarks often overlook the complex phys
arXiv:2601.21841v3 Announce Type: replace Abstract: While Large Language Models (LLMs) have demonstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundam
At Google Cloud Next ‘26, we unveiled the blueprint for the Agentic Enterprise, sharing our eighth-generation TPUs, Gemini Enterprise Agent Platform, a fully reimagined Agentic Data Cloud, Workspace I
arXiv:2605.18421v1 Announce Type: cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agen
arXiv:2510.08886v3 Announce Type: replace Abstract: Going beyond simple text processing, financial auditing requires detecting semantic, structural, and numerical inconsistencies across large-scale di
arXiv:2605.17682v1 Announce Type: new Abstract: Future 3D semantic occupancy forecasting and motion planning are central to autonomous driving, as they require models to reason about how surrounding s
arXiv:2605.18419v1 Announce Type: cross Abstract: Vision-language models (VLMs) can couple visual perception with open-ended clinical reasoning, making them attractive for computational histopathology
arXiv:2602.23058v2 Announce Type: replace Abstract: Energy-based predictive world models provide a powerful approach for multi-step visual planning by reasoning over latent energy landscapes rather th
arXiv:2605.18663v1 Announce Type: new Abstract: As LLM benchmarks saturate, the evaluation community has pursued two strategies to increase difficulty: escalating knowledge demands (GPQA, HLE) or remo
Google just announced agentic coding in search. Based on your search, Gemini processes your ask, decides whether it should build a new interface, reasons through the steps, and creates a personalized
Google launches new Omni model. Google says that today Omni can create and edit (yes, edit!!) video but eventually it is to go from “any input to any output”. Even more of a reason to believe that Sor
Google LLC today introduced two new generative artificial intelligence models that push its Gemini family further into AI agents and multimodal creation: Gemini 3.5 Flash, a fast reasoning model desig
arXiv:2605.16439v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning t
arXiv:2605.17003v1 Announce Type: cross Abstract: Reinforcement Learning (RL) post-training has emerged as the dominant paradigm for eliciting mathematical reasoning in Large Language Models (LLMs), y
arXiv:2410.13846v3 Announce Type: replace-cross Abstract: Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. M
arXiv:2604.00634v2 Announce Type: replace-cross Abstract: Panoptic segmentation is a key enabler for robotic perception, as it unifies semantic understanding with object-level reasoning. However, the
arXiv:2605.17596v1 Announce Type: new Abstract: We present NeuSymMS, an adaptive memory system that enables large language model (LLM) agents to learn, remember, and reason about users across sessions
arXiv:2605.17679v1 Announce Type: cross Abstract: Cancer survivors face elevated rates of depression, anxiety, and general emotional distress, yet the precise moments they most need support are often
arXiv:2511.20353v3 Announce Type: replace Abstract: Reasons for mapping an unknown environment with autonomous robots are wide-ranging, but in practice, they are often overlooked when developing plann
arXiv:2501.17549v2 Announce Type: replace Abstract: Graph-structured data plays a vital role in numerous domains, such as social networks, citation networks, commonsense reasoning graphs and knowledge
arXiv:2605.16411v1 Announce Type: cross Abstract: Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible y
arXiv:2506.05442v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) offer a promising approach to end-to-end autonomous driving due to their human-like reasoning capabilities. Howe
arXiv:2605.17915v1 Announce Type: new Abstract: Surgical Video Question Answering (VideoQA) provides a promising paradigm for dynamic intraoperative interpretation, enabling real-time decision support
arXiv:2511.04070v3 Announce Type: replace Abstract: As LLMs are deployed in knowledge-intensive settings (e.g., surgery, astronomy, therapy), users are often domain experts who expect not just answers