A constrained verifiable agent framework for open-web data collection achieves zero execution-stage LLM tokens and lowest wall-clock time on 80 verified tasks by shifting from free-form code to typed JSON configs with taxonomy and static DAG execution.
arXiv preprint arXiv:2603.29161 (2026)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data Collection
A constrained verifiable agent framework for open-web data collection achieves zero execution-stage LLM tokens and lowest wall-clock time on 80 verified tasks by shifting from free-form code to typed JSON configs with taxonomy and static DAG execution.