Agentic Large Language Models
arXiv:2610.13455v1 Announce Type: new Abstract: Large language models (LLMs) have taken the world by storm. Their ability to communicate with us in our own language, and to reason about our world, has
Knowledge catalogue
arXiv:2610.13455v1 Announce Type: new Abstract: Large language models (LLMs) have taken the world by storm. Their ability to communicate with us in our own language, and to reason about our world, has
arXiv:2603.03753v2 Announce Type: replace-cross Abstract: The ongoing shift of Artificial Intelligence (AI) from centralized cloud application programming interfaces (APIs) to local inference on edge
arXiv:2610.13361v1 Announce Type: cross Abstract: As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their us
arXiv:2610.13335v1 Announce Type: new Abstract: Tool-using agents increasingly require a common substrate for building, training, evaluating, distilling, and maintaining agentic systems, yet existing
arXiv:2610.13303v1 Announce Type: cross Abstract: LLM judges are increasingly deployed as panels, and disagreement among panel members is often read as a symptom of an unclear rubric. We test a label-
As enterprises move from debating artificial intelligence adoption to deploying it, AI governance has become the harder question. Autonomous agents now run around the clock across a sprawl of platform
I designed a node to align any pair of images trying to correct the pixel drift on Qwen Image 2.1 https://github.com/zuanfilm/Qalign workflow This node don't need any model or text encoder Qalign is a
arXiv:2610.12917v1 Announce Type: new Abstract: AI shopping assistants increasingly influence which products consumers consider. We study retail assortment planning under AI mediation, where a retaile
arXiv:2610.13928v1 Announce Type: new Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilit
arXiv:2610.12494v1 Announce Type: new Abstract: In this article, we propose algebraic integer number formats (AINF) as a framework for highly configurable and accurate compressed computation. A key pr
arXiv:2610.13354v1 Announce Type: new Abstract: The NIST Assembly Task Board #1 remains a challenging benchmark for learning-based methods in robotic manipulation. Over short horizons, it demands prec
arXiv:2610.13627v1 Announce Type: new Abstract: Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph pr
arXiv:2610.12679v1 Announce Type: new Abstract: Efficient sampling from Bayesian posterior distributions in high dimensions remains a hard problem, despite advances in theory and algorithms. Multiple
arXiv:2610.13724v1 Announce Type: cross Abstract: Counterfactual inference asks how an observed outcome might have differed under different circumstances, such as whether a patient would have recovere
arXiv:2610.12571v1 Announce Type: new Abstract: Most systems trained by equilibrium propagation or coupled learning are in the same class as multi-layer perceptrons: while they may be universal functi
arXiv:2610.12496v1 Announce Type: cross Abstract: Sequence models with a fixed-size state avoid the quadratic cost of attention, but face a design choice. An input-dependent state transition gives con
Madhumita Murgia / Financial Times: An interview with ex-DeepMind scientist David Silver on his startup Ineffable, building an AI “super learner” using RL as an alternative path to LLMs, and more — Th
Anthropic: Anthropic researchers say small AI models may be months away from being able to self-replicate on IoT devices like smart ovens and off-brand Android TV boxes — Our experiments suggest that
Anthropic: Anthropic says new measures like preserved thinking in Fable 5.1 and Opus 5.5 have reduced data harvesting through distillation attacks by about 90% to 99% — In recent months, we've made su
arXiv:2610.12843v1 Announce Type: cross Abstract: Fewer latent tokens promise cheaper diffusion. Yet aggressive latent compression creates a reconstruction-generation dilemma: adding channels improves
arXiv:2610.13623v1 Announce Type: cross Abstract: Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and busine
arXiv:2510.00734v2 Announce Type: replace-cross Abstract: Bayesian optimal experimental design provides a principled framework for selecting experimental configurations that maximize obtained informat
arXiv:2602.01709v3 Announce Type: replace Abstract: Current test-time scaling (TTS) techniques enhance large language model (LLM) performance by allocating additional computation at inference time, ye
arXiv:2610.13518v1 Announce Type: cross Abstract: In machine learning, a self-attention dynamics describes the attention mechanism of transformers, and is obtained treating the layer index of a transf
At AI Engineer New York, Anthropic's @cjav_dev & @HarrisonStall from @ClaudeDevs drew on lessons from Unix and Linux to explain how agents can tackle bigger projects without overwhelming developers. h
arXiv:2610.13572v1 Announce Type: new Abstract: Humanoid tennis requires reactive whole-body coordination under rapidly changing ball dynamics, yet collecting task-specific motion-capture demonstratio
arXiv:2610.13078v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires d
arXiv:2610.13600v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) achieve strong performance on speech-text tasks, but standard audio encoders produce hundreds of tokens for even s
arXiv:2505.15738v3 Announce Type: replace-cross Abstract: Large language models are increasingly deployed in user-facing products that handle sensitive personal data while interacting with untrusted e
arXiv:2610.13643v1 Announce Type: new Abstract: Automating biological laboratories requires robots to perform dexterous tool interactions under realistic visual conditions while handling dynamic exper
arXiv:2603.07427v3 Announce Type: replace Abstract: As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costl
arXiv:2610.12545v1 Announce Type: cross Abstract: Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revi
hexagon: add IM2COL_3D (#30305) hexagon: add IM2COL_3D support Assisted-by: OpenCode hexagon: add DMA paths for IM2COL_3D Assisted-by: OpenCode hexagon: avoid scalar fp16 conversions in IM2COL Assiste
vulkan: fix buffer logging on 32-bit platforms after source split (#30326) Move the vk::Buffer stream operator to the shared header so it is visible to ggml-vulkan-debug.cpp. Website: https://llama.ap
ggml: Change default visibility of symbols to hidden (#30014) See discussion in #29997. This prevents a handful of internal symbols leaking via GGML_API. Website: https://llama.app Attestations: https
vulkan: use ternary expressions to avoid switch lowering for CM2 quant block size (#30164) vulkan: specialize quant block size for CM2 matmul vulkan: use ternary expressions to avoid switch lowering f
sycl: guard DMMV reads at row tails (#29338) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54988744 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Sil
llama : report compute graph reallocations during inference (#30329) Add an optional ggml_backend_sched_realloc_callback that user code registers with ggml_backend_sched_set_realloc_callback to be not
metal : fix mul_mat_id with duplicate ids (#30373) metal : fix mul_mat_id limits and kernel name metal : fix mul_mat_id with duplicate ids kernel_mul_mm_id_map0 assumed at most one match per token and
tests : link each test against only the libraries it uses (#30299) Give llama_build() and llama_build_and_test() a LINK keyword (default: llama-common) so call sites can declare what a test actually n
model: support vllm decision 2 model (#30378) models: support pplx-decider vllm d2 update clarify naming rule stricter validation fix ci rm redundant filter_tensors Website: https://llama.app Attestat
model: support vllm d3 models (#30383) models: support pplx-decider vllm d2 update clarify naming rule stricter validation d3 Website: https://llama.app Attestations: https://github.com/ggml-org/llama
vulkan: pack FMA for f16 accumulation, no dot product op (#29877) vulkan: pack FMA for f16 accumulation, no dot product op vulkan: dot_product packs two rows per f16 FMA vulkan: rename dot_product to
metal: fix metal tensor kernel_mul_mm error for large tensor (#28748) metal: fix metal tensor kernel_mul_mm error for large tensor Assisted-by: Codex Update ggml/src/ggml-metal/kernels/mul_mm.metal Co
The no-cache path builds a [n_tokens, n_tokens] mask and passes K and V unpadded, so FLASH_ATTN_EXT sees K->ne[1] == n_tokens. The CUDA kernels for head size 512 require a multiple of FATTN_KQ_STRIDE,
model: fix vllm d3 multi seq case (#30408) model: fix vllm d3 multi seq case add TODO Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/55219202 macOS/iOS: ma
arXiv:2501.18560v2 Announce Type: replace Abstract: We consider bandits with anytime knapsacks (BwAK), a novel version of the BwK problem where there is an extit{anytime} cost constraint instead of a
arXiv:2512.01093v2 Announce Type: replace Abstract: Multipurpose batch processes become increasingly popular in manufacturing industries since they adapt to low-volume, high-value products and shiftin
arXiv:2610.12527v1 Announce Type: new Abstract: Distribution operators need visibility of behind-the-meter photovoltaic (PV) generation, yet most residential customers are observed only through net sm
arXiv:2610.13087v1 Announce Type: new Abstract: People often learn how an unfamiliar object moves through a small exploratory push, using its response to guide their next motion. Inspired by this beha
arXiv:2610.12997v1 Announce Type: new Abstract: Prior-art retrieval systems are structurally organized around classification codes, making cross-code discovery difficult. This paper asks if an unsuper
arXiv:2610.13121v1 Announce Type: new Abstract: Cyberbullying is a growing concern in online communities, yet existing Bengali corpora remain limited in contextual information, annotation transparency
arXiv:2610.13212v1 Announce Type: cross Abstract: Actions specify what a robot should execute, but do not describe what those commands will achieve. Vision-language-action (VLA) policies nevertheless
arXiv:2610.12598v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary
arXiv:2610.13521v1 Announce Type: new Abstract: Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) by routing domain-specific data to specialized teachers, integrating th
arXiv:2602.01667v2 Announce Type: replace Abstract: Prediction-set size offers a coarse summary of conformal uncertainty. We develop a richer perspective through the geometry of credal sets: families
arXiv:2610.12919v1 Announce Type: cross Abstract: We consider online binary prediction with paid stochastic features, where the learner can spend resources to obtain better observations of the underly
arXiv:2610.12977v1 Announce Type: new Abstract: Generative recommendation (GR) of social media platforms commonly retrieves items by autoregressively decoding discrete Semantic IDs (SIDs) with finite-
arXiv:2610.13522v1 Announce Type: new Abstract: Action-conditioned world models offer a promising foundation for generalist robotic intelligence by predicting the consequences of actions. However, exi
arXiv:2610.13504v1 Announce Type: cross Abstract: Generative Recommenders increasingly use Reinforcement Learning (RL) to optimize outcomes that may appear hundreds or thousands of interactions after