dense-reward

Introduces Long-Horizon-Terminal-Bench, a benchmark of 46 long-horizon terminal tasks with dense reward-based grading, evaluating AI agents on planning, long-context, and debugging. Even the strongest model achieves only 15.2% pass@1, showing significant room for improvement.

DR-MV3D presents a map-grounded learning framework with dense rewards to improve multi-view 3D visual question answering through global map construction, view-trajectory planning, and egocentric grounding.