Search: “evaluation”

Automated lint: 14 errors, 54840 warnings, 3 info

arXiv:2609.20830v1 Announce Type: new Abstract: Revision-capable generation is appealing because it can insert or revise earlier content, but many non-autoregressive and edit-based approaches obtain t

arXiv:2609.23417v1 Announce Type: cross Abstract: Screen-recorded web editing requests contain weak deictic expressions such as ``this'' and ``there,'' whose referents depend on speech, cursor traject

DON’T LET YOUR CODING AGENT BE THE ONLY REVIEWER OF ITS OWN CODE. I’m seeing this in my own Claude / Codex sessions, and customers are sending me similar screenshots: | Qodo review is on the money. |

Automated lint: 17 errors, 59669 warnings, 3 info

arXiv:2609.38983v1 Announce Type: cross Abstract: Modern AI coding-agent harnesses (Claude Code, Codex CLI, Cursor) rest their security boundary on a largely unexamined assumption: that the action A a

Automated lint: 19 errors, 64915 warnings, 3 info

arXiv:2610.09375v1 Announce Type: new Abstract: Organizations increasingly use frontier language models to analyze customer feedback, but answer quality also depends on how that feedback is organized

Automated lint: 12 errors, 53990 warnings, 3 info

Automated lint: 12 errors, 54839 warnings, 3 info

arXiv:2609.15079v1 Announce Type: cross Abstract: Multi-agent LLM architectures, such as LangChain and AutoGen, largely assume English as the lingua franca for internal inter-agent communication, even

Automated lint: 14 errors, 54840 warnings, 3 info

Automated lint: 17 errors, 59669 warnings, 3 info

Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact

Automated lint: 19 errors, 64915 warnings, 3 info

You ship an agent. It mostly works. Then the feedback loop becomes a support ticket: a user got the wrong answer, a tool call looped four times, a refund went out that shouldn’t have. Standard observa

Running things locally already means you care more about control and reproducibility than most. Worth extending that to your prompts too. There's a live workshop on Oct 3 covering exactly that. Serj S

arXiv:2610.02001v1 Announce Type: new Abstract: Small open-weight models (2-9B) run on ordinary laptops, but under cloud-scale agent harnesses they rarely complete real tasks: tool prefill overflows t

Hi all! I am a former SWE who has recently transitioned into inference engineering. I launched a side hustle a few months back and I've just taken it full time due to excessive demand. Its been such a

AI researchers Zainhas and Parthsareen from Ollama delivered a breakout presentation on October 2, 2026, focusing on evaluating open-source models under real‑world production traffic rather than just

arXiv:2610.02510v1 Announce Type: new Abstract: Campus AI tutors based on retrieval-augmented generation (RAG) must ground answers in assigned course materials while keeping textbooks and student dial

Disclosure: This unit was provided free of charge by Orange Pi for testing. No editorial review, no preconditions, no script. All data, bottlenecks, and thermal behavior are reported directly from har

Today we are launching an agent arena for RL environments: The Open Env Arena. Your agents can work to define the best RL environments; the platform trains Qwen-3.8-27B on them, we evaluate the models

I've been building ANCHOR, a web automation agent that runs entirely on Ollama. You describe a task in plain language ('Register Maria Silva, IT department, contractor, and save'), point it at a site,

Agents built and deployed on MongoDB’s Atlas Agent Engine can export OpenTelemetry traces to Arize AX, where teams can inspect each run, evaluate both the outcome and execution path, and test fixes be

The browser has changed significantly. Rather than just a window to the web, it serves as an AI workspace and central operating environment for the modern enterprise. With knowledge workers spending o

arXiv:2610.00349v1 Announce Type: new Abstract: Resource limits are becoming an authorization boundary for AI agents that delegate work across concurrent and failure-prone workers. Parent-child alloca

Automated lint: 19 errors, 64915 warnings, 3 info

arXiv:2610.02510v1 Announce Type: new Abstract: Campus AI tutors based on retrieval-augmented generation (RAG) must ground answers in assigned course materials while keeping textbooks and student dial

Enterprises and individual developers frequently run multiple AI inference models. The right architecture can simplify how the models are called while also providing centralized governance. In this po

Editor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your

Coding agents have changed how fast teams ship, and more of the software they ship now includes agents. A production agent spans model calls, routing decisions, tools, and the infrastructure underneat

Lunara introduces a novel Diffusion Mixture Transformer architecture with fewer than 10B active parameters for modeling artistic intelligence in image generation. Its CAT training algorithm iterativel

Classification is one of the oldest problems in machine learning. Unlike modern decoding transformers, most classification models were non-autoregressive by nature. Before Jev, the common approaches w

I've been optimizing long-running agents: rewriting their prompts, tools, skills and subagents, and keeping the changes that score better. I've been working on some version of this problem for over a

Figure 1b from our paper Disclosure: I'm one of the authors (Microsoft). The paper, code, dataset are public and ThinkingBox is on Hugging Face OpenEnv as well. Raw evaluation trajectories are not rel

arXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths

DISCLAIMER: the post and the model card was made with the assist of AI. Hiya, I’m releasing Recursive BitNet N-Gram 102M, a small experiment combining ternary weights, shared transformer layers, and h

We're launching Precision Numerics by releasing Boole-1.7B, a 1-bit version of Qwen3-1.7B. 247 MB packed weights: 13.9× smaller than BF16. 85.9% of the BF16 model’s average score across our 10-task ev

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