This paper presents BEDA, a simple way to make chatty AI act strategically by turning what it believes into gentle rules (probabilistic constraints) that guide what it can say.
Youtu-Agent is a build-and-grow factory for AI agents that cuts manual setup and keeps agents improving over time.
GenEnv is a training system where a student AI and a teacher simulator grow together by exchanging tasks and feedback.
MemEvolve teaches AI agents not only to remember past experiences but also to improve the way they remember, like a student who upgrades their study habits over time.
SCOPE lets AI agents rewrite their own instructions while they are working, so they can fix mistakes and get smarter on the next step, not just the next task.
This paper builds InternGeometry, a large language model agent that solves Olympiad-level geometry by talking to a math engine, remembering what worked, and trying smart new ideas.