{"ID":2825932,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20586","arxiv_id":"2512.20586","title":"Automated stereotactic radiosurgery planning using a human-in-the-loop reasoning large language model agent","abstract":"Stereotactic radiosurgery (SRS) demands precise dose shaping around critical structures, yet black-box AI systems have limited clinical adoption due to opacity concerns. We tested whether chain-of-thought reasoning improves agentic planning in a retrospective cohort of 41 patients with brain metastases treated with 18 Gy single-fraction SRS. We developed SAGE (Secure Agent for Generative Dose Expertise), an LLM-based planning agent for automated SRS treatment planning. Two variants generated plans for each case: one using a non-reasoning model, one using a reasoning model. The reasoning variant showed comparable plan dosimetry relative to human planners on primary endpoints (PTV coverage, maximum dose, conformity index, gradient index; all p \u003e 0.21) while reducing cochlear dose below human baselines (p = 0.022). When prompted to improve conformity, the reasoning model demonstrated systematic planning behaviors including prospective constraint verification (457 instances) and trade-off deliberation (609 instances), while the standard model exhibited none of these deliberative processes (0 and 7 instances, respectively). Content analysis revealed that constraint verification and causal explanation concentrated in the reasoning agent. The optimization traces serve as auditable logs, offering a path toward transparent automated planning.","short_abstract":"Stereotactic radiosurgery (SRS) demands precise dose shaping around critical structures, yet black-box AI systems have limited clinical adoption due to opacity concerns. We tested whether chain-of-thought reasoning improves agentic planning in a retrospective cohort of 41 patients with brain metastases treated with 18...","url_abs":"https://arxiv.org/abs/2512.20586","url_pdf":"https://arxiv.org/pdf/2512.20586v1","authors":"[\"Humza Nusrat\",\"Luke Francisco\",\"Bing Luo\",\"Hassan Bagher-Ebadian\",\"Joshua Kim\",\"Karen Chin-Snyder\",\"Salim Siddiqui\",\"Mira Shah\",\"Eric Mellon\",\"Mohammad Ghassemi\",\"Anthony Doemer\",\"Benjamin Movsas\",\"Kundan Thind\"]","published":"2025-12-23T18:32:17Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.HC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}