Google Cloud's PaperOrchestra Turns Experiment Logs Into Conference-Ready Papers Google Cloud AI Research released PaperOrchestra, an Apache 2.0 multi-agent system that converts idea summaries and experiment logs into compilable LaTeX manuscripts targeting CVPR and ICLR templates, with Semantic Scholar API grounding citations to reduce hallucinated references. The system splits the work across five specialized agents — outline, plotting, literature review, section writing, and content refinement — and in human evaluation showed a 14 to 38 percent overall win margin against autonomous baselines while still trailing human writers. Google also published PaperWritingBench, a benchmark of 200 reverse-engineered CVPR and ICLR 2025 papers, and users run the software themselves, covering their own model API and compute costs since Google offers no hosted service. Google Cloud's PaperOrchestra Turns Experiment Logs Into Conference-Ready Papers Google Cloud AI Research has open-sourced a multi-agent system that turns experiment logs and raw ideas into submission-ready LaTeX manuscripts with real citations. - Google Cloud AI Research released PaperOrchestra https://github.com/google-research/paper-orchestra?utm source=alphasignal , an Apache 2.0 multi-agent paper writer. - Specialized agents handle outline, literature review, section writing, refinement, and plotting in parallel. - Semantic Scholar API grounds citations to reduce hallucinated references in the generated lit review. - Outputs compilable LaTeX targeting CVPR or ICLR templates from idea summaries and experiment logs. - Human evaluation shows 14 to 38 percent overall win margin against autonomous baselines, still trailing humans. - Companion PaperWritingBench https://huggingface.co/datasets/yiwen-song/PaperWritingBench?utm source=alphasignal benchmarks 200 reverse-engineered CVPR and ICLR 2025 papers. Google Cloud AI Research has released PaperOrchestra https://github.com/google-research/paper-orchestra?utm source=alphasignal , an Apache 2.0 project that converts research notes, experimental results, and venue templates into structured LaTeX manuscripts. The system targets a difficult stage of research: assembling scattered source material into a coherent first draft with citations, figures, and conference formatting. The repository includes a command-line pipeline, a Streamlit interface, and templates for venues such as CVPR and ICLR. It supports Gemini, OpenAI, and Vertex AI models, while Semantic Scholar supplies publication metadata for citation checks. Users run the software themselves and cover their own model API and compute costs; Google does not provide a hosted service. Five agents, one manuscript PaperOrchestra divides the writing process among specialized agents that can work in parallel, exchange outputs, and critique the evolving draft. | Agent | Responsibility | |---|---| | Outline | Organizes the research question, method, evidence, and planned sections. | | Plotting | Creates statistical plots and conceptual diagrams from supplied data. | | Literature Review | Searches for relevant work and checks candidate papers through Semantic Scholar. | | Section Writing | Drafts the manuscript in the selected LaTeX template. | | Content Refinement | Revises the draft using simulated peer-review feedback. | A run begins with three main inputs: - Idea Summary: the research problem, proposed method, and theoretical basis. This story is for Pro members You've reached the end of the free preview. Upgrade to AlphaSignal Pro to read the full article - and everything else behind the paywall.