{"ID":6538278,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10990","arxiv_id":"2607.10990","title":"TreeSoc: Tree-Structured Dynamic Reasoning and Tool Synergy for Soccer Video Understanding","abstract":"Automated understanding of complex soccer scenarios from video remains a significant challenge for contemporary vision-language models (VLMs), which suffer from shallow cross-modal alignment and exhibit fundamental limitations in multi-step reasoning and coordinated tool integration. We present TreeSoc, a structured reasoning framework that reformulates soccer video question answering as a hierarchical search problem rather than a single-pass prediction. Specifically, TreeSoc employs a dynamic depth-first search (DFS) mechanism that decomposes complex queries into sequentially ordered sub-tasks, enabling iterative reasoning refinement through explicit intermediate states. This tree-structured decomposition naturally supports adaptive tool routing, wherein domain-specific modules are selectively activated and their outputs incorporated at each reasoning node to produce contextually grounded predictions. On SoccerBench, TreeSoc achieves state-of-the-art performance, with accuracies of 85.2%, 87.4%, and 82.2% on TextQA, ImageQA, and VideoQA, respectively. Additionally, TreeSoc further demonstrates strong cross-domain generalization, attaining 74.16% accuracy on NExT-QA. These results establish structured, tool-augmented tree reasoning as an effective paradigm for robust video understanding. Code is available at: https://github.com/thanhnhan29/TreeSoc.","short_abstract":"Automated understanding of complex soccer scenarios from video remains a significant challenge for contemporary vision-language models (VLMs), which suffer from shallow cross-modal alignment and exhibit fundamental limitations in multi-step reasoning and coordinated tool integration. We present TreeSoc, a structured re...","url_abs":"https://arxiv.org/abs/2607.10990","url_pdf":"https://arxiv.org/pdf/2607.10990v1","authors":"[\"Thanh-Nhan Vo\",\"Thanh-Khoi Nguyen\",\"Trong-Thuan Nguyen\",\"Trung-Hoang Le\",\"Minh-Triet Tran\"]","published":"2026-07-13T01:27:20Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":614231,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-14T02:54:43.516908796Z","DeletedAt":null,"paper_id":6538278,"paper_url":"https://arxiv.org/abs/2607.10990","paper_title":"TreeSoc: Tree-Structured Dynamic Reasoning and Tool Synergy for Soccer Video Understanding","repo_url":"https://github.com/thanhnhan29/TreeSoc","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}