A-RAG lets the AI choose how to search, what to read, and when to stop, instead of following a fixed recipe.
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.
The paper asks AI to hunt for insights in big databases without being told exact questions, like a curious scientist instead of a test-taker.
This paper builds an AI agent that learns new skills while working, like a kid who learns new tricks during recess without a teacher telling them what to do.
This paper shows that giving an AI a safe, tiny virtual computer (a sandbox) lets it solve many kinds of problems better, not just coding ones.
AgentEHR is a new, realistic test that asks AI agents to read messy hospital records and make full clinical decisions, not just look up facts.
DocDancer is a smart document helper that answers questions by exploring and reading long, mixed-media PDFs using just two tools: Search and Read.