{"ID":3084865,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T05:00:38.846751169Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05728","arxiv_id":"2606.05728","title":"DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance","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.","short_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 initi...","url_abs":"https://arxiv.org/abs/2606.05728","url_pdf":"https://arxiv.org/pdf/2606.05728v1","authors":"[\"Yansi Li\",\"Zhuosheng Zhang\"]","published":"2026-06-04T05:37:31Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\"]","methods":"[\"Diffusion Model\",\"LoRA\"]","has_code":false,"code_links":[{"ID":612866,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-05T06:46:15.197025399Z","DeletedAt":null,"paper_id":3084865,"paper_url":"https://arxiv.org/abs/2606.05728","paper_title":"DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance","repo_url":"https://github.com/puddingyeah/DiG-Plan","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}