{"type":"ScholarlyArticle","title":"DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance","authors":[{"name":"Yansi Li","slug":"yansi-li","given":"Yansi","family":"Li","affiliation":""},{"name":"Zhuosheng Zhang","slug":"zhuosheng-zhang","given":"Zhuosheng","family":"Zhang","affiliation":""}],"abstract":"Generating executable tool plans requires selecting appropriate subsets from tool libraries, a combinatorial search problem with an exponentially large solution space. However, we identify a critical misalignment in predominant approaches: standard autoregressive (AR) decoding suffers from early commitment, where initial token choices rigidly constrain the search trajectory. A controlled study shows that masked denoising raises Pass@10 solution coverage from 0.320 to 0.943 over AR sampling under matched compute. Motivated by this, we propose DiG-Plan, a framework that decouples combinatorial exploration from structural refinement. DiG-Plan employs a diffusion-based proposer to generate diverse tool sets via iterative refinement, followed by an AR refiner for dependency prediction. On TaskBench, DiG-Plan improves over AR baselines by a 10% relative margin, with the largest gains on complex compositional tasks; API-Bank results show that the propose-refine-select design remains effective across domains. Code is available at https://github.com/puddingyeah/DiG-Plan.","doi":"10.24963/ijcai.2026/649","url":"https://ijcai.org/proceedings/2026/649","pdf":"https://ijcai.org/proceedings/2026/0649.pdf","markdown":"https://ijcai.org/proceedings/2026/649.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/649","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":"Natural Language Processing","track":"Main Track","number":649,"pages":{"first":5828,"last":5836},"keywords":["Planning and Scheduling: Search in planning and scheduling","Planning and Scheduling: Planning algorithms","Natural Language Processing: Applications","Natural Language Processing: Tools","Natural Language Processing: Language models"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}