Search

OmniGAIA is a new test that checks if AI can watch videos, look at images, listen to audio, and use web and code tools in several steps to find a verified answer.

ATLAS is a system that picks the best mix of AI models and helper tools for each question, instead of using just one model or a fixed tool plan.

AI agents are computer helpers that can use tools and act on their own a little or a lot, and this paper measures how that happens in real life.

ResearchGym is a new "gym" where AI agents are tested on real research projects end to end, not just on toy problems.

AI helpers often don’t know new users’ tastes and can’t keep up when those tastes change.

AI agents often act very sure of themselves even when they are wrong, especially on long, multi-step tasks.

Long AI tasks can go wrong early and keep getting worse, like a snowball of mistakes called the Spiral of Hallucination.

Before SkillNet, AI agents kept solving the same kinds of problems over and over without saving what they learned in a clean, reusable way.

This paper builds a tough new test called O3-BENCH to check if AI can truly think with images, not just spot objects.

FINCH is a new test that checks whether AI can handle real finance and accounting work using messy, real spreadsheets, emails, PDFs, charts, and more.

QuantiPhy is a new test that checks if AI models can measure real-world physics from videos using numbers, not guesses.

Monadic Context Engineering (MCE) is a way to build AI agents using math-inspired Lego blocks called Functors, Applicatives, and Monads so state, errors, and side effects are handled automatically.

OpenAI and Amazon announced a multi-year partnership to make building and running AI apps easier, safer, and faster for businesses of all sizes.

This paper builds a new test called AgentIF-OneDay that checks if AI helpers can follow everyday instructions the way people actually give them.

Terminal-Bench 2.0 is a tough test that checks how well AI agents can solve real, professional tasks by typing commands in a computer terminal.

AgentDoG is a new ‘diagnostic guardrail’ that watches AI agents step-by-step and explains exactly why a risky action happened.

The paper shows that simply adding a new AI model to the menu—without anyone actually using it—can push a fairness-focused regulator to change the market rules, shifting money from one side to the other.

This survey explains how AI agents remember things and organizes the whole topic into three clear parts: forms, functions, and dynamics.

Accuracy alone can make AI agents look good on paper while still failing in real life; this paper shows how to measure reliability properly.