Skip to main content ->
Ai2

Latest research

November 13, 2026

XYBench: Helping with the problem behind the question

XYBench is an 8,115-question benchmark testing whether LLMs spot misconceptions in user requests and redirect toward the user’s underlying goal.
Read post
November 6, 2026

ToyBlocks: A controlled world for robot learning and evaluation

ToyBlocks is an open simulation framework for studying robot learning through automated task generation, training demonstrations, and evaluation in a controlled tabletop world.
Read post
November 3, 2026

StateBench: Testing how language models track state changes over long documents

StateBench tests how language models track changing information across long documents at four difficulty levels, revealing where models struggle and how targeted training helps recurrent and hybrid architectures handle longer sequences.
Read post
October 27, 2026

Can we trust LLMs to judge whether a research idea is novel?

Old Ideas, Novel Problems tests how reliably LLMs judge the novelty of research ideas, finding that small changes to the evaluation setup can produce very different verdicts.
Read post
October 23, 2026

LitPivot: Developing research ideas through dynamic contextualization within the literature landscape

LitPivot helps researchers refine early research ideas through literature-supported critiques and revisions as their proposals evolve.
Read post
October 22, 2026

OlmoEarth v1.3: State-of-the-art embeddings for the whole planet

OlmoEarth v1.3 brings state-of-the-art satellite embeddings, precomputed global data, and a browser-based Embeddings Explorer for mapping and analyzing the planet.
Read post
October 22, 2026

A crop-mapping benchmark for the tropics

PLANTEUR extends the PASTIS crop-mapping benchmark to six tropical regions to help evaluate geospatial models across more diverse agricultural systems.
Read post
October 20, 2026

FairStress: A deeper evaluation of fairness in LLM decision-making

FairStress is a new benchmark that reveals demographic differences in how LLMs defend and explain their decisions, even when their final choices appear fair.
Read post
October 14, 2026

HiRO-ACEv2: Simulating extreme weather at 3 km resolution for a fraction of the cost

HiRO-ACEv2 captures extreme rain, wind, and pressure events at 3 km resolution for about 1/300th the cost of X-SHiELD, making detailed global climate simulations more accessible to researchers.
Read post
1-9Next