Model Releases
Banger paper from NVIDIA on test-time compute for terminal agents. The finding is that you should sample several candidate shell commands, v…
Banger paper from NVIDIA on test-time compute for terminal agents. The finding is that you should sample several candidate shell commands, verify them before running one, and spend more on the verifie
Banger paper from NVIDIA on test-time compute for terminal agents. The finding is that you should sample several candidate shell commands, verify them before running one, and spend more on the verifier than on extra samples. With a GPT-5.6 Sol verifier choosing among 8 sampled actions, TerminalBench-Lite Pass@1 rises from 50.0% to 68.0%. With a weak verifier, extra samples add almost nothing. Mid-Harness leaves the generator and harness unchanged and works between them. When a small TMAX-9B model verifies its own candidates, pairwise comparison works best, and distilling the strong verifier into it helps further. Combining action sampling with trajectory sampling reaches higher success at lower estimated token cost than sampling full trajectories alone. Paper: https://academy.dair.ai/papers/mid-harness-scaling-actions-between-model-and-harness-for-terminal-agents-2609.39982
Related
- Dynamic workflows (generating harnesses on the fly) are a new form of test-time compute. But LLMs aren't great at building them. I often hav…
- Banger paper from Google. It's standard practice to sample several agent rollouts and trust the answers they agree on. This Google paper sho…
- Build your own harness, folks. This is absolute banger paper from NVIDIA on self-evolving agent harnesses. (bookmark it) They introduce SoL-…
Source: DAIR.AI (X) | 2026-10-04