{"type":"ScholarlyArticle","title":"Lookahead Branching for Neural Network Verification","authors":[{"name":"Liam Davis","slug":"liam-davis","given":"Liam","family":"Davis","affiliation":""},{"name":"Duo Zhou","slug":"duo-zhou","given":"Duo","family":"Zhou","affiliation":""},{"name":"Huan Zhang","slug":"huan-zhang","given":"Huan","family":"Zhang","affiliation":""},{"name":"Guy Katz","slug":"guy-katz","given":"Guy","family":"Katz","affiliation":""},{"name":"Clark Barrett","slug":"clark-barrett","given":"Clark","family":"Barrett","affiliation":""},{"name":"Haoze Wu","slug":"haoze-wu","given":"Haoze","family":"Wu","affiliation":""}],"abstract":"In this work, we investigate the effect of lookahead branching strategies in neural network verification. We present a general recipe to integrate lookahead into any branch-and-bound verifier and demonstrate how one of the current state-of-the-art branching heuristics, FSB, can be viewed as a special instantiation of the lookahead branching strategy. We also describe how, in addition to improving the quality of branching decisions, lookahead can generate additional lemmas that accelerate verification. We instantiate the method in two representative branch-and-bound-based verifiers (Marabou and α-β-CROWN), and demonstrate that lookahead leads to consistent speedups in verification time and up to 57% more solved instances. Code is available at https://github.com/ai-ar-research/lookahead-branching.","doi":"10.24963/ijcai.2026/59","url":"https://ijcai.org/proceedings/2026/59","pdf":"https://ijcai.org/proceedings/2026/0059.pdf","markdown":"https://ijcai.org/proceedings/2026/59.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/59","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI Ethics, Trust, Fairnes","track":"Main Track","number":59,"pages":{"first":518,"last":526},"keywords":["AI Ethics, Trust, Fairnes: Safety and robustness","AI Ethics, Trust, Fairnes: Trustworthy AI"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}