← Thursday, October 1, 2026AgentsPaper

Verified action sampling raises terminal-agent Pass@1 from 50.00% to 68.03%

huggingface.co by Minki Kang et al. Editor score 8/10

Mid-Harness samples candidate commands and verifies them before execution; with a GPT-5.6 Sol verifier, eight samples raise TerminalBench-Lite Pass@1 from 50.00% to 68.03%. The result shows that stronger verification can make test-time compute useful without changing the model or harness.

What: Mid-Harness samples and verifies candidate actions at the model-harness boundary before forwarding one for execution.
Method: A capable verifier can select useful alternatives from the same generator; with GPT-5.6 Sol verification, 8 sampled actions raise Pass@1 from 50.00% to 68.03%.
Why it matters: The approach improves terminal-agent action reliability without changing the generator or harness.

Candidate actions pass through a verifier before the harness executes a selected action. Sketched from the article's own text.

Read on huggingface.co →

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.