Pinned Loading
-
PrimerSearcher
PrimerSearcher PublicWe construct an autonomous deep retrieval Agent for multi-hop complex questions and post-train the Qwen3-30B-A3B-Thinking-2507 model on high-quality long-trajectory data, internalizing behaviors su…
Python
-
PrimerResearcher
PrimerResearcher PublicWe construct an autonomous report generation Agent for open-domain research tasks and post-train the Qwen3-8B model with cold-start SFT followed by ArenaRL post-training based on relative ranking r…
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.