Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success

arXiv:2610.40444 · cs.AI, cs.CL · Submitted 2026-10-29 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-10-29

Updated: 2026-10-29

Comments: 21 pages, 2 figures. Accepted to NeurIPS 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Related papers