Knowledge catalogue
There's an interactive chart and some extra data in the blog post if you're interested. There are plenty of KL-divergence benchmarks for GGUF models, but most of them compare one GGUF quant against an
arXiv:2608.06713v1 Announce Type: new Abstract: Biomedical knowledge graphs (KGs) accelerate drug discovery, but standard pipelines assume query molecules already exist as graph entities, leaving unre
arXiv:2608.06968v1 Announce Type: cross Abstract: Language-model agents act on state encodings of their environment, yet these are treated as interchangeable interfaces. Using pretrained language mode
arXiv:2608.06714v1 Announce Type: new Abstract: Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits
arXiv:2608.06704v1 Announce Type: new Abstract: Delegating a web task involves more than asking a question; it requires transferring a policy: what to verify, how to handle uncertainty, which preferen
arXiv:2608.05242v1 Announce Type: cross Abstract: In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning, rather than jointly a
arXiv:2608.05738v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have become the dominant recipe for generalist manipulation, yet they are almost universally trained by behavior clo
arXiv:2608.06346v1 Announce Type: new Abstract: LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging. Crit
Together Serverless Inference gives developers a managed production path for bringing FLUX 3 into creative products and automated media workflows. Start building: https://www.together.ai/models/flux-3
arXiv:2608.03738v1 Announce Type: new Abstract: As Moore's law slows, the industry is turning to three-dimensional integration; yet in merged 3D-IC flows, routed designs expose bond-level defects with
arXiv:2608.03071v1 Announce Type: new Abstract: Large language model agents derive much of their capability from tool use. Existing research on tool use has largely focused on selecting the right tool
arXiv:2607.27703v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task
arXiv:2608.03499v1 Announce Type: new Abstract: Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served b
arXiv:2608.02110v1 Announce Type: new Abstract: Executing long-horizon tool invocations in real-world environments is severely challenged by dynamic user intent noise. Existing methods attempt robustn
arXiv:2608.02358v1 Announce Type: new Abstract: To operate robustly in open-world environments, autonomous agents should be able to infer the behavior of unfamiliar systems through interaction alone,
arXiv:2603.08091v2 Announce Type: replace Abstract: Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by j
AI9Stars has released G9v3-39A5B an open weights language model designed to deliver even stronger reasoning capabilities than ai9stars/G9v3-3B with its 39B and 5 active experts. It is released under t
arXiv:2607.19338v2 Announce Type: replace Abstract: Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect an
arXiv:2607.29246v1 Announce Type: new Abstract: Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases. As a
arXiv:2607.16057v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are improving rapidly as reflected in benchmark scores, yet these AI benchmarks largely test capabilities such as
arXiv:2607.28802v1 Announce Type: new Abstract: Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the
arXiv:2607.28871v1 Announce Type: cross Abstract: When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect. We measure how often that treatment is
arXiv:2607.29377v1 Announce Type: new Abstract: LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermed
arXiv:2607.28595v1 Announce Type: new Abstract: The fundamental goal of agentic visual reasoning is to improve the success rate of multimodal large language models (MLLMs) on complex tasks, rather tha
arXiv:2607.28591v1 Announce Type: cross Abstract: Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a r
arXiv:2607.28225v1 Announce Type: new Abstract: Agentic vision-language models (VLMs), which interleave textual reasoning with explicit tool calls such as cropping and code-based image manipulation, h
arXiv:2607.26656v1 Announce Type: cross Abstract: Real-world vulnerabilities often span multiple functions, yet most learning-based detectors classify each function in isolation: on a sample of real C
arXiv:2607.27083v1 Announce Type: new Abstract: As LLM agents increasingly depend on diverse external services such as search engines, databases, and connectors, agent harnesses face a fundamental too
arXiv:2607.25415v1 Announce Type: new Abstract: Production LLM agents are increasingly assembled from a frozen model wrapped in a harness: a prompt template, a tool set, a memory/retrieval layer, a pl
Welcome to our latest Gemini Enterprise Agent Platform deep dive, a practical walkthrough where we’ll teach you how to build real-world, production-ready agents starting from step 1. If you haven’t al
arXiv:2607.24878v1 Announce Type: cross Abstract: Phenotype-driven diagnostic benchmarks usually report the rank of the reference disease, but they rarely reveal which plausible alternatives are ranke
arXiv:2607.25398v1 Announce Type: new Abstract: Language-model agents are increasingly deployed under standing instructions: a system prompt, a policy file, or a skills document is placed in context,
On benchmarking long-context agentic instruction following. Agent benchmarks mostly reward reaching the answer. This new benchmark measures whether the agent reached it the permitted way, which is the
arXiv:2607.25485v1 Announce Type: new Abstract: Health AI is evolving from answering questions to agentic systems that converse with patients, reason about health records, and act on their behalf. Pri
arXiv:2607.24850v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled search agents to autonomously tackle complex tasks across extended search and reasoning h
arXiv:2607.25816v1 Announce Type: new Abstract: Large language model agents often spend substantial wall-clock time waiting for tool call results. Tool-call speculation can hide this latency by predic
arXiv:2607.22711v1 Announce Type: cross Abstract: LLM coding agents operate by constructing trajectories that accumulate reasoning, tool calls, and results to enable multi-step decision-making. Howeve
arXiv:2607.23524v1 Announce Type: new Abstract: Deep search is becoming a core capability of modern agent systems, yet it is typically evaluated solely based on end-to-end answer accuracy. This couple
arXiv:2607.24419v1 Announce Type: new Abstract: Deep models have substantially advanced 12-lead ECG classification, yet their refinement still relies heavily on human experts to inspect failures and i
arXiv:2607.24280v1 Announce Type: new Abstract: Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this
arXiv:2607.23491v1 Announce Type: cross Abstract: Two structural insights have been overlooked in automated residential floor plan generation. First, design is inherently progressive. Architects begin
arXiv:2607.22926v1 Announce Type: new Abstract: High-impact generative AI makes catastrophic misuse a lifecycle-control problem, not merely a prompt-filtering problem. SAGE is a safety-first, authoriz
arXiv:2607.22732v1 Announce Type: new Abstract: LLM-based game agents often perform poorly on more complex tasks. This work examines whether these failures are linked to limited spatial reasoning and
arXiv:2607.23123v1 Announce Type: new Abstract: Existing evaluations of large language models cover knowledge, reasoning, coding, and tool use, but they rarely treat a verifiable deliverable produced
arXiv:2607.24054v1 Announce Type: new Abstract: A correct answer can conceal why an agent succeeded. Once agents change their information state during evaluation, correctness no longer distinguishes i
arXiv:2509.06278v4 Announce Type: replace Abstract: Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations. Although recent large lang
arXiv:2607.21799v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly perform commercial tasks that involve retrieving external content such as images and, where appropriate,
arXiv:2607.22165v1 Announce Type: cross Abstract: LLM-based database agents show promise, but differing task scopes, testbeds, and metrics hinder comparison. We identify four gaps between evaluation a
arXiv:2607.22083v1 Announce Type: cross Abstract: We present Nanbeige4.2-3B, a compact general agentic model with 3B non-embedding parameters. It delivers strong performance across code-agent, office-
arXiv:2607.22529v1 Announce Type: new Abstract: LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fund
GigaChat Audio 10B is an audio-native LLM built on top of the GigaChat 3.1 Lightning text model. A Conformer speech encoder and a modality adapter feed audio embeddings directly into a Mixture-of-Expe
arXiv:2607.20498v1 Announce Type: new Abstract: Large language models (LLMs) augmented with tools are emerging as autonomous agents capable of using Web engine, APIs, and code to solve complex, long-h
arXiv:2607.21461v1 Announce Type: new Abstract: Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candida
arXiv:2607.21125v1 Announce Type: new Abstract: Image restoration agents have recently emerged as a flexible paradigm for handling diverse and unpredictable degradations in real-world scenarios. Exist
arXiv:2607.20531v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed over Model Context Protocol (MCP) servers, yet the benchmarks used to evaluate them score th
arXiv:2607.20759v1 Announce Type: cross Abstract: AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with au
https://huggingface.co/swiss-ai/Apertus-v1.5-70B https://huggingface.co/swiss-ai/Apertus-v1.5-8B Apertus 1.5 is a family of 8B and 70B parameter language models designed to advance the state of multil
arXiv:2512.16300v3 Announce Type: replace Abstract: Existing image forgery detection (IFD) methods either exploit low-level, semantics-agnostic artifacts or rely on multimodal large language models (M
LLaDA2.2-flash is an agent-oriented diffusion language model in the LLaDA2 series. By introducing Levenshtein Editing (with DELETE and INSERT control tokens) to diffusion language modeling, it represe
The math behind reinforcement learning (RL) post-training for large language models (LLMs) is notoriously unforgiving. As frontier AI labs push the boundaries of reasoning and coding models using RL p