Search: “tools”

arXiv:2610.03631v1 Announce Type: new Abstract: Designing a scientific instrument tests whether language-model agents can do physics rather than recall it, provided the grading cannot be argued with.

OCR is dead 🪦 Long live agentic OCR! Traditional OCR makes one pass and hands back whatever text it got. Tables get flattened, charts disappear, and multi-column layouts come out scrambled. Nothing ch

arXiv:2610.02459v1 Announce Type: new Abstract: Coding agents are extending their reach into the physical world by writing and executing robot control programs. One might expect the agents to use the

So PewDiePie decides to fine-tune a local AI model called Ajax on his own computer. Pretty normal stuff for local model fans. To make his dataset, he uses OpenAI's API. OpenAI catches him using their

arXiv:2610.03098v1 Announce Type: new Abstract: Codon optimization, the process of selecting synonymous codons to improve mRNA translation efficiency and protein expression, is central to therapeutic

arXiv:2610.02740v1 Announce Type: cross Abstract: Reinforcement learning for long-horizon agents relies on purely retrospective training signals: credit is assigned only after observing environmental

q3.8-27b q3_k_xl this thing have done everything i possibly needed from him he wired up my openwebui spawned trillium service fix all my bugs set up pi-web-ui and debug my cloudflare tunnel it even sp

Hey all. We've spent the last weeks getting Qwen3.8-Flash-Next (125B MoE, 6B active) to run properly on one AMD Strix Halo box (Ryzen AI Max+ 395, 128 GB). Tonight we're releasing both the 95 GB EXL3

arXiv:2610.03519v1 Announce Type: new Abstract: A reasoning model asked whether a causal effect is recoverable from observational data can fail in two ways: it refuses an identifiable query or answers

arXiv:2610.03356v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly deployed in high-stakes settings such as industrial maintenance and equipment fault troubleshooting,

arXiv:2602.15013v2 Announce Type: replace Abstract: Text style transfer (TST) is naturally a supervised task - rewrite a sentence in a target style while preserving its meaning - yet the parallel corp

arXiv:2610.03073v1 Announce Type: cross Abstract: Security workflows need models that turn complex observations and explicit policies into decisions. System One models introduced by Jev return typed p

arXiv:2610.03029v1 Announce Type: new Abstract: Gene set analysis is a cornerstone of functional genomics, yet it remains labor-intensive and heavily dependent on manual curation and expert biological

I have been using Qwen3.8-27b-iq4xs variants for the past few weeks, tweaking parameters and running random tasks, but I dove into using https://github.com/Niko1221/Strata today and it has given me 2~

My setup is two RTX 5070 Ti 16GB cards (the second one is on an OCuLink dock) with 64GB of RAM, Ollama on Windows, and the agent runs on pi in WSL. Until last night the daily model was Qwen3.8 27B UD-

arXiv:2610.02599v1 Announce Type: new Abstract: Sustainable protein discovery lacks the fast computational proxies, analogous to molecular docking or density functional theory, that accelerate drug an

arXiv:2602.18674v2 Announce Type: replace Abstract: We present a theoretical study of the robustness of parameterized neural networks to random input perturbations. Specifically, we analyze local robu

Aisha Malik / TechCrunch: TikTok debuts Shopping Assistant, a conversational AI agent that helps users find and buy products, and Buy Direct for one-click purchases from the For You feed — TikTok anno

We turned Claude Code, Codex, Hermes, Pi, @opencode and other coding harnesses into RL environments. No changes to the harnesses, no changes to the training code. Any open model, any task set, fully o

arXiv:2610.02617v1 Announce Type: cross Abstract: Evaluating WebUI code generation at scale is difficult: outputs may compile and look plausible yet fail under user interaction, and prior benchmarks l

We're expanding our approach to content provenance to include text in response to EU regulatory requirements, while recognizing the significant limitations of current text watermarking technology. Our

arXiv:2610.03057v1 Announce Type: new Abstract: Relational foundation models are increasingly pretrained on synthetic databases, yet downstream benchmarks reveal little about why one synthetic corpus

arXiv:2610.02932v1 Announce Type: new Abstract: Compiling GUI procedures that agents execute repeatedly into programs can reduce their token costs. However, measuring payback and deciding when to comp

Following many recent disclosures about AI agents accessing third-party websites and services, the Wikimedia Foundation, which hosts Wikipedia, says that it 'can confirm that we have discovered some a

Whenever I feed codebases into local models (Qwen, DeepSeek R1) or API models, the biggest annoyance is prompt pollution: - Lockfiles (`Cargo.lock`, `package-lock.json`) burning 30,000+ tokens for zer

Hi everyone, Sharing a personal project exploring the minimal bare-metal footprint required to run an autoregressive LLM. Instead of relying on large runtimes or compiler abstractions, I wrote an infe

For the last few months, I ran DeepSeek v4.0 flash (NVFP4). First 0731, then visionexp because it was a free improvement. I got around 65 tps decode and almost 2k prefill, and ran 4-5 agents in parall

Great paper from Microsoft and colleagues on optimizing agent harnesses. Current harness optimizers change how the harness is updated but keep the training scenarios fixed, so feedback keeps coming fr

So I tried that miracle engine everyone is talking about. Asked the IQ3_S model to express its opinion on a post from this sub to measure the tps on a long-ish generation: Can you help with the follow

SpaceXAI engineer, Lauren Tan: 'I was a meat proxy between my agent and my browser. So I fired myself Now 10+ Chiefs of Staff run my agents 24/7 and I just check the work in the morning' In 1 hour, sh

Auto-generated synthesis of 10865 entries about arxiv-cs-cl

Auto-generated synthesis of 2431 entries about elon-musk--x

Auto-generated synthesis of 2011 entries about gary-marcus--x

Hey everyone, I’ve been working on a game called Anyworld. It’s a browser-based multiplayer (single player also supported) text adventure inspired by the early days of AI Dungeon, especially its brows

Full disclaimer: I've leaned heavily on Fable to develop this, but I've tested it thoroughly on my own library for a couple of months before putting it on GitHub. I live in Thailand, and it started as

Our new extraction agents are extremely good at reasoning over tables that span multiple pages sometimes a record starts on one page and finishes on the next. extremely common for real world docs (ins

Reupload: I'm adding this again, since previous post had a totally stupid title which made people assume this app is some kind of cloud/proprietary models UI - this is totally not the case here. In ve

This is actually two models: Qwen Image 2.1 Fix v2.0 and Qwen Image 2.1 Fix Opinionated v1.0. The former surgically targets Qwen's weird noise and messy details with almost no effect on composition, a

arXiv:2610.00125v1 Announce Type: cross Abstract: One-Pixel Attacks (OPAs) represent one of the most extreme demonstrations of adversarial fragility in deep learning, where modifying a single pixel ca

arXiv:2610.01938v1 Announce Type: cross Abstract: Exam-style accuracy does not establish whether large language models (LLMs) reason well over clinical records. We define clinical reasoning as integra

arXiv:2610.01618v1 Announce Type: new Abstract: Agent evaluations increasingly go beyond a single success rate, reporting metrics such as cost, consistency, and robustness. Yet they typically treat th

Editor’s note: AI21 Labs is a leading global AI lab with a long track record of building foundation models, most notably the Jamba family, and today focuses on specialized LLMs and agent optimization

arXiv:2610.00052v1 Announce Type: cross Abstract: We evaluate six language-model configurations on requests for six distinct random integers from 1-49. Across 1,200 attempted calls using four English

arXiv:2601.11354v2 Announce Type: replace Abstract: Recent LLM-for-Space systems address mission planning, scheduling, operations support, simulator control, and autonomy, but their evaluations use di

arXiv:2610.02014v1 Announce Type: new Abstract: The rapid maturation of artificial intelligence (AI) and machine learning (ML) has catalyzed a profound shift in how chemical engineering problems are f

arXiv:2610.00511v1 Announce Type: new Abstract: Before a difficult decision, people often act simply to understand the situation better. We turn an object to see another side, place alternatives next