This paper teaches AI to pay attention better by training its focus, not just its words.
Parallel-Probe is a simple add-on that lets many AI “thought paths” think at once but stop early when they already agree.
SWE-World lets code-fixing AI agents practice and learn without heavy Docker containers by using smart models that pretend to be the computer and tests.
Re-TRAC is a new way for AI search agents to learn from each try, write a clean summary of what happened, and then use that summary to do better on the next try.
CoDiQ is a recipe for making hard-but-solvable math and coding questions on purpose, and it controls how hard they get while you generate them.
FS-Researcher is a two-agent system that lets AI do very long research by saving everything in a computer folder so it never runs out of memory.
This paper shows that making short videos can help AI plan and reason in pictures better than writing out steps in text.
DeepVerifier is a plug-in checker that helps Deep Research Agents catch and fix their own mistakes while they are working, without retraining.
This paper teaches video-making AIs to follow real-world physics better without retraining them.
The paper fixes a big problem in training web-searching AI: rewarding only the final answer makes agents cut corners and sometimes hallucinate.
DiffProxy turns tricky multi-camera photos of a person into a clean 3D body and hands by first painting a precise 'map' on each pixel and then fitting a standard body model to that map.
Coding agents used to fix software rely on feedback; unit tests give only pass/fail signals that are often noisy or missing.