{"ID":2840127,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.14631","arxiv_id":"2511.14631","title":"Enhancing Agentic Autonomous Scientific Discovery with Vision-Language Model Capabilities","abstract":"We show that multi-agent systems guided by vision-language models (VLMs) improve end-to-end autonomous scientific discovery. By treating plots as verifiable checkpoints, a VLM-as-a-judge evaluates figures against dynamically generated domain-specific rubrics, enabling agents to correct their own errors and steer exploratory data analysis in real-time. Case studies in cosmology and astrochemistry demonstrate recovery from faulty reasoning paths and adaptation to new datasets without human intervention. On a 10-task benchmark for data-driven discovery, VLM-augmented systems achieve pass at 1 scores of 0.7-0.8, compared to 0.2-0.3 for code-only and 0.4-0.5 for code-and-text baselines, while also providing auditable reasoning traces that improve interpretability. Code available here: https://github.com/CMBAgents/cmbagent","short_abstract":"We show that multi-agent systems guided by vision-language models (VLMs) improve end-to-end autonomous scientific discovery. By treating plots as verifiable checkpoints, a VLM-as-a-judge evaluates figures against dynamically generated domain-specific rubrics, enabling agents to correct their own errors and steer explor...","url_abs":"https://arxiv.org/abs/2511.14631","url_pdf":"https://arxiv.org/pdf/2511.14631v1","authors":"[\"Kahaan Gandhi\",\"Boris Bolliet\",\"Inigo Zubeldia\"]","published":"2025-11-18T16:23:02Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.CV\",\"cs.MA\"]","methods":"[\"Language Model\",\"LoRA\"]","has_code":false,"code_links":[{"ID":606943,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2840127,"paper_url":"https://arxiv.org/abs/2511.14631","paper_title":"Enhancing Agentic Autonomous Scientific Discovery with Vision-Language Model Capabilities","repo_url":"https://github.com/CMBAgents/cmbagent","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}