The Last Mile of Coding Agents for Long-Document Tasks: An Empirical Study on Clinical Trial Protocol Digitization
TrialScribe is developed, a domain-specific harness that equips coding agents with task skills and a verification loop that improves a locally served open-weight model by 6.2-59.4 points across eight metrics, enabling it to match or surpass proprietary models such as GPT-5.6-Sol.
Jia-Cheng Lin, Geoffrey Low, Nishit Agarwal et al.
· 0 citations