Distills reusable reasoning strategies from successful and failed agent runs. Retrieved lessons guide later tasks, while memory-aware test-time scaling turns extra exploration into better memories.

Trains long-horizon web researchers by combining agentic mid-training, synthetic trajectories, and reinforcement learning. A 30.5B-parameter model activates 3.3B parameters per token and learns to plan, search, and synthesize evidence.

Trains an 8B model to search, synthesize evidence, and write cited research reports. Its reinforcement-learning rewards use evolving rubrics grounded in retrieved evidence and contrasting model responses.

Measures whether reusable skills improve agent task completion through paired tests. Across 87 tasks and 18 model–harness configurations, curated skills raise average pass rate by 16.6 percentage points; compact skill bundles work best.

Helps agents decide when to retrieve, test, or commit by supplying calibrated uncertainty estimates alongside action costs. Experiments show more adaptive exploration and better cost-adjusted rewards than prompting or RL alone.

Embeds an agent's reasoning together with its search query to improve retrieval. Trains a 4B embedding model on synthesized deep-research trajectories, helping preserve intent across multi-step searches.

Trains one model to delegate work recursively to copies of itself. Joint reinforcement learning teaches task splitting and communication, improving harder-task generalization while trading extra computation for parallel execution.

Generates computer-use tasks with executable setups and verifiable rewards. A generator and independent reward writer produce 32,112 verified examples across 110 desktop and mock-web environments for reinforcement learning.