Knowledge catalogue
arXiv:2608.26172v1 Announce Type: cross Abstract: Deploying natural-language interfaces over enterprise OLTP catalogs fails at scale because semantic parsers collapse under schema-graph scaling, infla
arXiv:2608.27021v1 Announce Type: cross Abstract: LLM-based agents are increasingly proposed for network fault diagnosis, but existing benchmarks evaluate them only on accurate tickets and always assu
arXiv:2608.26317v1 Announce Type: cross Abstract: Frontier language models are increasingly marketed as omni systems that can perceive and respond across modalities. Existing evaluation frameworks, ho
What's Changed Ollama's app now follows the system appearance again, restoring dark mode support Fixed the macOS app to properly hand off to an already-running instance instead of starting a second on
arXiv:2608.26123v1 Announce Type: new Abstract: Large language models (LLMs) are trained predominantly on English-language internet text that over-represents certain cultural narratives, raising conce
You can now fine-tune GLM-5.3 with @tinkerapi. It’s the first GLM model on the platform and quite possibly the strongest model available there today. https://tinker-docs.thinkingmachines.ai/tinker/mod
100% Agree @GavinSBaker. Now, I'm going to debunk every single piece of mis-information about data centers that I've ever seen online: > DISINFORMATION: Data centers use a lot of water. FACT: Most AI
Jack Queen / Reuters: A US judge blocks the Pentagon from blacklisting Anthropic, ruling that its designation as a supply-chain risk was “illegal and baseless” — A U.S. judge on Thursday blocked the P
arXiv:2608.24979v1 Announce Type: cross Abstract: Scientific agents increasingly analyze data, execute code, and produce research artifacts, yet most benchmarks emphasize final answers, isolated progr
Google DeepMind: Google launches a pilot of double-blind AI evaluations, keeping external evaluations in a cryptographic “box” to stop benchmark contamination and protect IP — Building trust in propri
If you maintain a skill library for long-horizon agents, this one is worth your time. (bookmark it) It discusses one of most common topics I get asked about these days. It shares some good ideas on ho
arXiv:2608.25593v1 Announce Type: new Abstract: Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/s
arXiv:2608.25866v1 Announce Type: new Abstract: Quantifying wound tissue composition is essential for monitoring chronic ulcer progression and guiding treatment decisions. However, pixel-level annotat
Neat paper suggesting that human augmentation and task automation are not necessarily related. Models that are really good at doing work are not always good at helping humans do work better. Given the
arXiv:2608.25832v1 Announce Type: new Abstract: Large language models access knowledge inconsistently across languages, but to what extent do they differ in their skill sets when interacting with diff
arXiv:2603.10068v2 Announce Type: replace-cross Abstract: Most adversarial evaluations of large language model (LLM) safety assess single prompts and report binary pass/fail outcomes, which fails to c
arXiv:2608.23898v1 Announce Type: new Abstract: We introduce BenchBench-Protocol, a benchmark for large language models of 149 protocol-modification tasks recovered from modifications that scientists
BREAKING: GLM-5.3 Flash by @Zai_org debuts at 6th overall on Design Arena with a preliminary Elo of 1343. This places the MIT-licensed, natively multimodal model in the same performance band as GLM-5.
arXiv:2507.21790v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are becoming widely used to support various workflows across different disciplines, yet their potential in discre
arXiv:2608.23569v1 Announce Type: new Abstract: State-of-the-art Natural Language to SQL (NL2SQL) models report execution accuracy exceeding 89 percent on established benchmarks such as Spider and BIR
Amazon Bedrock AgentCore Evaluations decouples agent evaluation from the framework you build on. As long as your agent emits OpenTelemetry telemetry, the service can score it, whether you use LangGrap
arXiv:2608.23961v1 Announce Type: cross Abstract: Background: Large Language Models (LLMs) have demonstrated strong performance across a variety of code-understanding tasks, leading many to believe th
arXiv:2608.24191v1 Announce Type: cross Abstract: Urdu, the world's tenth most spoken language with 246 million speakers, remains almost entirely absent from mainstream LLM safety evaluation and nine
GLM-5.3-Flash scores 57 on the Artificial Analysis Intelligence Index. At 0.09 Cost per Task, it sits comfortably on the Intelligence vs. Cost per Task Pareto frontier @Zai_org has released GLM-5.3-Fl
Great new paper from AWS on agent handoff tax. If you build agents today, you need to understand the so-called handoff tax. (bookmark it) Escalating to a stronger model mid-run is usually the resort w
Great paper on why agent leaderboard comparisons are hard to trust. It's on the hot topic of how much of an agent benchmark score actually belongs to the harness. The harness is the layer between the
Hosting the 2nd founder dinner in sf on August 31 with @GuangyuRobert at @Fundamental - the team behind @tryshortcutai Agents are increasingly capable of solving tasks for longer task horizons without
Megathread for discussing the release of GLM-5.3-Flash. Quants Fine-Tunes & Abliterations Chat Templates Inference Server Support & Configuration Experiences, Benchmarks & Model Comparisons We'll try
On August 26, 2026 Z.ai reported that its Code‑Bench metric—which assesses real‑world coding performance—shows GLM‑5.3‑Flash outperforming GLM‑5.2 at every effort level. The new model’s results are on
arXiv:2608.24876v1 Announce Type: new Abstract: Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We in
arXiv:2608.23611v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer new opportunities for automated code refactoring. However, generated changes must reduce targeted quality problems
arXiv:2608.24291v1 Announce Type: new Abstract: Paper-to-code reproduction asks scientific AI agents to turn research papers into executable repositories that preserve the paper's method, protocol and
arXiv:2608.24252v1 Announce Type: new Abstract: LLM agents can generate paper reproduction code, yet often produce scientifically unfaithful implementations. We define this failure mode as semantic dr
arXiv:2608.24358v1 Announce Type: new Abstract: Coding agents perform long-running tasks spanning dozens of model calls, tool uses, and code edits. As these runs unfold, users face a practical cost-qu
Benchmarked qwen3.8 xhigh, medium and muse glimmer. Xhigh effort mode with qwen3.8 took almost 30hrs. (And still failed on 16 cases because of the 32K output token limit) Medium effort mode and muse g
arXiv:2608.22713v1 Announce Type: new Abstract: Clinical diagnosis requires progressive integration of patient history, physical examination, laboratory findings, medical images, and diagnostic-inform
arXiv:2608.21747v1 Announce Type: cross Abstract: LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture spec
arXiv:2608.21880v1 Announce Type: new Abstract: Bangla large language model (LLM) safety is difficult to evaluate with English-centric or standard-script benchmarks because Bangla users routinely writ
arXiv:2608.22808v1 Announce Type: new Abstract: When can an agent failure be caught? An audit is usually limited by the record rather than by the method. CatchBench therefore puts one auditor's questi
arXiv:2608.22533v1 Announce Type: new Abstract: Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and ve
arXiv:2608.22068v1 Announce Type: new Abstract: Geothermal well arrays, which organize multiple geothermal wells into carefully planned geometric configurations, provide opportunities to enhance energ
arXiv:2608.21460v1 Announce Type: cross Abstract: Vision Language Models have recently shown improvements in several objective and verifiable domains such as object detection but continue to underperf
arXiv:2608.21668v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to simulate students at different mastery levels. These simulations can generate synthetic training d
i’m seeing SO many US companies shift away from frontier models to open source in the last 4 weeks. cost and privacy are big factors but more so people are realising fine-tuning and training their own
arXiv:2608.23061v1 Announce Type: new Abstract: Background: Automating clinical guideline-based decision-making with large language models (LLMs) remains challenging because of reliability, hallucinat
arXiv:2606.17443v2 Announce Type: replace Abstract: Large language models (LLMs) are becoming a major way for consumers to find products, but we do not yet understand how brands compete in this new ch
arXiv:2608.21601v1 Announce Type: new Abstract: Benchmarks for scientific artificial intelligence are mostly written to be scored: multiple-choice questions, curated agent tasks with reference solutio
arXiv:2608.23200v1 Announce Type: new Abstract: Large language models are increasingly expected to execute complex workflows whose success depends on maintaining interdependent constraints and produci
arXiv:2608.22237v1 Announce Type: new Abstract: Long-horizon agents increasingly rely on repeated access to external artifacts, yet current reading interfaces often expose entire objects even when onl
arXiv:2608.21985v1 Announce Type: new Abstract: As the adoption of large language models (LLMs) grows in Arabic-speaking regions, ensuring their safety and cultural alignment is increasingly critical.
arXiv:2608.23564v1 Announce Type: cross Abstract: Modern software systems accumulate technical debt over decades of development, which makes migration expensive and largely manual. As coding agents be
arXiv:2608.22752v1 Announce Type: new Abstract: A safety rule and an episodic log compete for the same tokens in an AI agent's context. When the budget overflows, both are summarized at the same rate;
arXiv:2608.23370v1 Announce Type: new Abstract: Large Language Models (LLMs) recognise patterns but do not natively track the path of exclusions that a coherent discourse demands. When an input rests
Source of Claims: https://x.com/Andy_ShuoYang/status/2090856976880472439 Your gaming PC can now serve frontier models at interactive speed using official checkpoints without extreme quantization! Qwen
AgentX 1.0 is the first fully open‑source multi‑turn agentic coding inference benchmark (Apache 2.0), released August 2026 with a 1 million‑token context and over 1 million tokens of dataset built at
arXiv:2608.20637v1 Announce Type: cross Abstract: Static analyzers have been widely adopted for vulnerability detection in C/C++ programs. Query-based static analyzers (e.g., CodeQL) encode vulnerable
arXiv:2608.21101v1 Announce Type: cross Abstract: As large language model (LLM) agents move from conversation to executing code, reading local files, and orchestrating external tools, a single agent h
arXiv:2608.21057v1 Announce Type: new Abstract: Agentic large language model (LLM) systems are reshaping scientific workflows in chemistry and drug discovery, but evaluating their open-ended, tool-aug
arXiv:2608.21021v1 Announce Type: cross Abstract: Real-world fault analysis in 5G and emerging 6G networks demands domain expertise to analyze free-text diagnostics, including root-cause explanations
arXiv:2608.20391v1 Announce Type: new Abstract: Most legal NLP resources draw from federal case law and focus on coarse classification, leaving administrative adjudication, where the vast majority of