Banger paper from Meta Superintelligence Labs. They find something super interesting and unexpected. (bookmark it) Base models with a light …

Banger paper from Meta Superintelligence Labs. They find something super interesting and unexpected. (bookmark it) Base models with a light harness often solve more agentic tasks than their RL post-trained versions when both get enough samples. Post-trained models win on pass@1. At large K, base models frequently solve tasks the post-trained ones never solve on BFCL v4 multi-turn, ACEBench, and WebShop. This is because post-training pushes each task toward always solved or never solved. Consistency goes up, and coverage goes down. The authors call the lost test-time scalability the Sharpening Tax. Across 42 base and post-trained pairs, it shows up in most settings, grows with model size, and can be estimated from a few rollouts. Their fix, PTGS, sets the sampling temperature per prompt from its estimated difficulty during RL. It pays a smaller tax and also raises pass@1. Paper: https://academy.dair.ai/papers/sharpening-tax-in-post-training-2610.01509

Source: DAIR.AI (X) | 2026-10-03

Related