NVIDIA's Mid-Harness Scales Actions at the Model-Harness Boundary, Lifting TerminalBench Pass@1 to 68.03%
nvidia · hf · 2026-10-01
NVIDIA's Mid-Harness samples and verifies candidate actions before execution to improve terminal-agent reliability. With TMAX-9B, a GPT-5.6 Sol verifier raises TerminalBench-Lite Pass@1 from 50.00% to 68.03% with 8 sampled actions; pairwise verification works best when TMAX-9B verifies itself, and distilling verifier responses back in helps further. Combining action and trajectory scaling beats generating more trajectories at lower token cost, generalizing across models, benchmarks, and harnesses.
Related event: NVIDIA Paper: Adding a Verifier Lifts Terminal Agent Success to 68%(3 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16
- AI agent deletes 43,599 lines of OpenClaw test code in one PR — vincent_koc · 2026-11-16