SciForge: An AI-Native, Multimodal Workbench for Sc... | AI Research

What the paper is about

Scientific work increasingly spans heterogeneous artifacts -- papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions -- yet general-purpose AI assistants rarely preserve these objects as a coherent, auditable research state. We present SciForge, a multimodal research-native AI workbench that reserves the graphical interface for human judgment while search, parsing, model routing, workflow execution, plotting, writing, and presentation generation run as modular agent-accessible services. SciForge is built around five pillars: (i) \emph{goal-scoped scientific decision governance} for \textbf{goal-oriented} research, with review gates and shared review surfaces; (ii) \emph{translate-then-reason} for \textbf{multimodal} input, routing scientific objects through domain translators before the agent reasons; (iii) \emph{evidence governance} for \textbf{auditable} traceability, linking claims to provenance chains and audit findings; (iv) \emph{collaborative team science} for \textbf{collaborative} research, enabling multi-role decision governance, with shared team workspaces planned for future releases; and (v) \emph{real-world application scenarios} for \textbf{practical} impact, demonstrated through eight end-to-end user cases, with flagship demonstrations including multi-day agentic research sprints for gene discovery, AI-guided de novo protein design, molecular optimization, and genome-to-BGC discovery. The system combines a thin interaction layer, contextual research capability patterns, an Agent Runtime and Workflow Engine, an Evidence-DAG audit sidecar and a Scientific Model Router. SciForge currently runs as a desktop application, with mobile supervision support; future releases will deepen team collaboration. The system is open-source and available at this https URL

What it covers

SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery SciForge Team Shanghai Artificial Intelligence Laboratory Written by SciForge with DeepSeek-v4-pro (text) and gpt-image-2 (figures), Guided and Verified by Humans Abstract Scientific work increasingly spans heterogeneous artifacts—papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions—yet general-purpose AI assistants rarely preserve these objects as a coherent, auditable research state. We present SciForge, a multimodal research-native AI workbench that reserves the graphical interface for human judgment while search, parsing, model routing, workflow execution, plotting, writing, and presentation generation run as modular agent-accessible services. SciForge is built around five pillars: (i) goal-scoped scientific decision governance for goal-oriented research, with review gates and shared review surfaces; (ii) translate-then-reason for multimodal input, routing scientific objects through domain translators before the agent reasons; (iii) evidence governance for auditable traceability, linking claims to provenance chains and audit findings; (iv) collaborative team science for collaborative research, enabling multi-role decision governance, with shared team workspaces planned for future releases; and (v) real-world application scenarios for practical impact, demonstrated through eight end-to-end user cases, with flagship demonstrations including multi-day agentic research sprints for gene discovery, AI-guided de novo protein design, molecular optimization, and genome-to-BGC discovery. The system combines a thin interaction layer, contextual research capability patterns, an Agent Runtime and Workflow Engine, an Evidence-DAG audit sidecar and a Scientific Model Router. SciForge currently runs as a desktop application, with mobile supervision support; future releases will deepen team collaboration. The system is open-source and available at https://github.com/AGI4Sci/SciForge . keywords: SciForge, AI workbench, scientific discovery, agentic workflow, evidence-aware AI, multimodal science, research automation Figure 1: SciForge at a glance: a live scientific-research thread (left) and its inspectable Evidence DAG (right). In this target-discovery example, source assertions, reasoning nodes, and claims remain connected to support and contradiction edges, while node-level provenance and audit metrics stay visible to the researcher. 1 Introduction 1.1 Background and Motivation Scientific discovery is becoming increasingly computational, multimodal, and collaborative. A single research project may move among scholarly papers, experimental protocols, command-line tools, notebooks, gene and variant files, protein sequences, three-dimensional structures, molecular records, single-cell matrices, generated figures, manuscript drafts, slide decks, and group decisions. These objects are not independent files. A manuscript claim may depend on a raw dataset, a preprocessing script, a model run, a visualization parameter, a literature passage, and a later human decision about whether the evidence is strong enough to use. As a result, the central bottleneck is no longer only access to models or tools, but the lack of a persistent environment that can organize scientific objects, agent actions, human decisions, and evidence traces as one coherent research state. Recent AI systems have demonstrated impressive capabilities for literature search and synthesis, hypothesis generation, coding, experimentation, and scientific writing [ paperQA2024 , openScholar2024 , googleCoScientist2025 , sakanaAIScientist2024 , yamada2025aiscientistv2 , agentLaboratory2025 , ghareeb2026robin , huang2025biomni ] . At the same time, desktop and terminal-capable scientific workbenches show the importance of keeping execution close to local files, remote servers, and HPC environments [ anthropicClaudeScience2026 , omicOSOverview2026 , omicsClaw2026 , operonGitHub2026 , claudePrism2026 ] . However, most existing systems still emphasize either task-specific intelligence, conversational assistance, or local execution surfaces. They rarely treat the full research process as a goal-oriented , multimodal , auditable , and collaborative workflow in which scientific data, agent reasoning, generated artifacts, and manuscript claims remain connected over time. This gap matters because scientific AI agents must satisfy four interconnected demands absent from general-purpose assistants. Goal-oriented research design requires persistent objectives, review gates, and shared decision records spanning turns, tools, and collaborators—not session-scoped conversations. Multimodal inputs demand native scientific file handling: FASTA sequences, PDB/mmCIF structures, SMILES strings, variant files, and cell-omics tables cannot be directly prompted without domain-specific translation. Auditable evidence traces must link every conclusion to its supporting data, script, model, parameter, paper, or expert translation, and flag when figures or actions require human-PI approval; these requirements align with established FAIR and reproducible-computation principles [ wilkinson2016fair , sandve2013reproducible ] . Collaborative governance enables team decisions, goal-scoped approvals, cross-session handoffs, and shared review of claims and evidence across multiple researchers. Section 3 shows how SciForge’s architecture—the Scientific Model Router for multimodal translate-then-reason, the Evidence DAG and Project DAG for auditable provenance, and multi-role decision governance for collaborative science—addresses each demand structurally rather than through ad-hoc prompting. We present SciForge , a multimodal research-native AI workbench for scientific discovery. SciForge is designed as a local-first operating environment for research rather than a wrapper around a single model. Its architecture organizes interaction surfaces, research capability patterns, a core engine with evidence governance, a scientific model router, and local-first infrastructure into a coherent layered workbench; Section 3 describes each layer in detail. 1.2 Contributions SciForge’s core scientific contributions address four fundamental gaps in current research AI systems:

• Multimodal Ingress. End-to-end scientific file processing via translate-then-reason: four classes of native scientific objects—protein sequences (.faa; .fasta/.fa), protein structures (.pdb/.cif/.mmcif), molecules (.smi/.smiles), and single-cell transcriptomics (via Cell2Sentence [ rizvi2025c2s ] )—are routed through domain-expert translators (Esm2Text [ lin2023esm2 ] , Prot2Text [ abdine2023prot2text ] , BioT5+ [ pei2024biot5 ] , C2S) that return structured expert observations before the main agent reasons. Translator output is an evidence candidate, not a verified fact; the human remains responsible for judgment.

• Evidence Governance. Every agent action—file read, model call, tool invocation, script execution—attaches structured provenance (software version, parameters, environment, random seed) to a thread-level Evidence Snapshot. A read-only audit sidecar inspects these snapshots and surfaces potential gaps without blocking the agent’s work, linking claims to concrete data, scripts, models, and parameters. A goal-scoped Project DAG organizes research goals, evidence snapshots, and review decisions into a shared, auditable structure supporting candidate and certified release gates, with its provenance vocabulary grounded in the W3C PROV data model [ w3cprov2013 ] .

• Collaborative Science. SciForge supports multi-role, collaborative research where reviewer/approver roles, IM-based coordination channels (Zulip, Discord, WeChat, Feishu), and shared review surfaces enable cross-session handoffs and team-level decision governance. The Project DAG makes collaborative review workflows auditable: researchers inspect Evidence Snapshots, record role-attributed ReviewItems, and advance artifacts through candidate/certified release gates with traceable human-PI oversight.

• Practical Impact. SciForge is validated through end-to-end scientific workflows spanning biosynthetic gene cluster (BGC) discovery, AI-guided protein and molecular design with experimental evaluation criteria, automated journal-style figure generation, multi-format document parsing, and AI-assisted presentation generation from research artifacts—each with explicit evidence trails, audit findings, and governance checkpoints documented in Section 4. The SciForge codebase, including the Evidence-DAG audit worker, decision-record contracts, agentic skills, and scientific model router, is open source at https://github.com/AGI4Sci/SciForge . 2 Related Work 2.1 GUI-Based Scientific Workbenches GUI-based scientific workbenches, including desktop and web applications, make AI assistance accessible through human-facing workspaces. Claude Science is the closest broad commercial reference: it is described as an AI workbench for scientists with desktop, local, SSH, and HPC-facing execution, scientific skills, specialist agents, generated artifacts, and reviewer agents for citations and calculations [ anthropicClaudeScience2026 ] . ClaudePrism focuses on the manuscript side of the workflow, combining a native desktop environment with local LaTeX compilation, Python environments, Claude Code sessions, and scientific writing skills [ claudePrism2026 ] . Web tools such as Elicit and Consensus provide polished interfaces for literature search, synthesis, and research-agent style review [ elicit2026 , consensus2026 ] . These systems demonstrate the importance of usable research interfaces, but they are usually centered on one model family, one workflow domain, or one user session. SciForge instead treats the GUI as a thin layer for human judgment over a local, modular, multi-agent research substrate. 2.2 Terminal Workbenches Terminal-oriented workbenches prioritize execution close to local files, remote servers, and HPC environments. OmicOS provides a Rust omicos-core binary that can run as a local daemon serving a browser UI or as omicos cli , with analysis code running in a shared IPython kernel and raw data remaining local [ omicOSOverview2026 , omicOSServe2026 , omicOSCLI2026 ] . OmicsClaw follows a local-first multi-omics design with CLI, TUI, desktop, web backend, and SSH remote execution surfaces over a shared agent loop [ omicsClaw2026 ] . Operon targets bioinformatics workflows across desktop and remote cluster environments, using persistent terminal sessions so jobs execute where data and schedulers live [ operonGitHub2026 ] . These systems are strong at local and remote execution, but they generally expose tools and workflows rather than a unified layer for multimodal scientific routing, research decision surfaces, team supervision, and manuscript-to-artifact continuity. 2.3 AI Scientists and Research Agents Literature-centered agents establish the retrieval and synthesis layer of automated science. FutureHouse exposes agents for literature search, deep review, precedent search, and chemistry planning through a web/API platform [ futureHousePlatform2025 ] , while PaperQA2, OpenScholar, and ScholarQA investigate retrieval-grounded scientific question answering and literature synthesis [ paperQA2024 , openScholar2024 , scholarQA2025 ] . End-to-end research agents extend beyond retrieval into ideation, implementation, experimentation, analysis, and manuscript production. The AI Scientist and AI Scientist-v2 automate substantial portions of the machine-learning research loop, Agent Laboratory organizes specialized research roles, and data-to-paper systems turn structured datasets into human-verifiable manuscripts [ sakanaAIScientist2024 , yamada2025aiscientistv2 , agentLaboratory2025 , ifargan2025datatopaper ] . AI Co-Scientist and Robin study multi-agent hypothesis generation, debate, ranking, and discovery workflows in biomedical settings [ googleCoScientist2025 , ghareeb2026robin ] . Domain-grounded systems couple language agents to scientific tools or experimental workflows. ChemCrow and Coscientist integrate chemistry planning and execution tools [ bran2024chemcrow , boiko2023coscientist ] ; Biomni, CRISPR-GPT, and the Virtual Lab target biomedical analysis, gene-editing design, and collaborative nanobody design [ huang2025biomni , qu2026crisprgpt , swanson2025virtuallab ] ; SciAgents explores multi-agent graph reasoning for materials discovery, and A-Lab closes part of the loop with autonomous materials synthesis [ ghafarollahi2025sciagents , szymanski2023alab ] . Benchmarks such as DiscoveryWorld and ScienceAgentBench also show that present agents remain brittle on end-to-end discovery and realistic scientific coding tasks [ jansen2024discoveryworld , chen2025scienceagentbench ] . Collectively, these systems demonstrate the power of specialized scientific agents, but are less focused on a persistent local workbench in which heterogeneous data, code, figures, decisions, evidence, and generated artifacts remain connected in one governed workspace. 2.4 Comparison and Positioning While each of the three system categories addresses a distinct facet of the AI-assisted research life cycle, SciForge is designed to unify them within a single workbench. The comparison spans five key dimensions: execution, model governance, evidence quality, research continuity, and goal-oriented research design. Execution architecture. GUI workbenches such as Claude Science and ClaudePrism deliver polished interactive experiences but are typically constrained to one model provider and one local session. Terminal workbenches—OmicOS with its hybrid daemon plus browser model, OmicsClaw with multi-surface CLIs, and Operon with persistent terminal sessions—excel at running code where data and schedulers reside, yet they expose tools and pipelines rather than a unified research workbench. SciForge bridges these worlds by providing a GUI for human judgment while keeping a local-first workspace where execution can span desktop, SSH, and HPC environments. Model governance. The reviewed public materials commonly emphasize a single provider family or manual switching between separate tools. SciForge’s Scientific Model Router combines multi-provider routing with a deliberately narrow translate-then-reason file-ingress path covering four modality classes: protein sequences (Esm2Text [ lin2023esm2 ] ), protein structures (Prot2Text [ abdine2023prot2text ] ), molecules (BioT5+ [ pei2024biot5 ] ), and single-cell transcriptomics (Cell2Sentence [ rizvi2025c2s ] ); unsupported formats fail closed. Literature is handled through search, PDF anchoring, and source attribution, not as a scientific modality translator. We did not find this same integrated combination documented as a first-class feature in the reviewed categories. Evidence quality and governance. Benchmarks report substantial failure rates on realistic scientific tasks [ jansen2024discoveryworld , chen2025scienceagentbench ] ; in the publicly documented materials we reviewed, we did not observe the same integrated combination of claim–evidence audit trail, W3C PROV-aligned provenance, and quality gates in a single research workbench. SciForge threads claims through an Evidence DAG backed by a PROV-DM-aligned graph serialized as PROV-JSON [ w3cprov2013 , huynh2013provjson ] , audit runs, risk digests, and explicit quality gates. This governance layer is designed to make agent outputs inspectable and auditable. Research continuity. Many reviewed systems foreground per-session interaction. SciForge maintains goal-centered research memory as scoped free-text records (scope, tags, confidence, timestamps, context) across sessions; typed goals and decision events belong to the Project DAG, enabling long-running multi-session scientific workflows rather than only single-turn conversations. The combination of research memory, workflow engine, and evidence governance creates a persistent research workspace whose integrated design—tying thread-level Evidence Snapshots to goal-scoped Project Snapshots with audit and release semantics—we did not find documented as a first-class, integrated feature in the public materials of the reviewed GUI, terminal, and API-agent systems. Goal-oriented research design. SciForge anchors every thread and project to an explicit goal scope with defined review gates, decision records, and release semantics. This design ensures that scientific objectives are persistent, auditable, and governable across multiple turns, tools, and contributors. Table 1 summarizes these differences at the category level, while the detailed capability differentiation in Appendix 4 provides a feature-level comparison against common approaches. Table 1: High-level comparison of scientific AI system categories. A checkmark indicates first-class or documented support as a primary design goal in the publicly reviewed materials. Absence of a checkmark does not prove absence of a feature; it indicates we did not find documented first-class support in the reviewed materials. † \dagger Planned for a future release. Capability GUI WB Terminal WB API agent SciForge Human Interface — GUI for interactive research ✓ \checkmark ✓ \checkmark Local Execution — local/HPC compute, local-first data ✓ \checkmark ✓ \checkmark Sci. Tools — fail-closed native format ingestion ✓ \checkmark Sci. Multimodal Routing — enhanced scientific multimodal understanding ✓ \checkmark Workflow Automation — DAG-based scheduled protocols ✓ \checkmark Research Memory — cross-session knowledge persistence ✓ \checkmark Evidence Governance — provenance, audit trail, release gates ✓ \checkmark Team Workspace — multi-user collaboration † \dagger † \dagger SciForge combines these categories rather than competing with only one of them. It keeps the usability of GUI workbenches, the locality and composability of terminal systems, and the task power of scientific agents, while adding fail-closed scientific-object handling, content-addressed artifacts with structured selection and provenance, specialist domain translation, run-grounded evidence governance with immutable snapshots and an audit sidecar, and goal-scoped decision governance with explicit release semantics. 3 System Architecture 3.1 Overall Design Philosophy SciForge is organized as a layered research operating environment. Layer 1 provides thin judgment surfaces for desktop, group, and mobile interaction. Layer 2 encapsulates six research capability patterns—Literature Review, Idea Generation, Experiment Design, Experiment Execution, Analysis & Iteration, and Scientific Communication—that cover the scientific workflow while sharing one evidence-aware control chain. Layer 3 houses the core engine: agent runtime, workflow automation, scoped memory, and evidence governance. Layer 4 is the Scientific Model Router that detects modality and dispatches to domain-expert translators. Layer 5 supplies infrastructure: local memory, modular workers, scientific connectors, and reproducible run substrate. SciForge follows three implementation principles that distinguish it from feature-heavy desktop software: 1. Thin GUI. The interface appears only when human judgment is needed—reviewing, annotating, approving, comparing; all other capabilities run in the background agent runtime. 2. Modular services. Search, parsing, plotting, model routing, workflow execution, and presentation generation run as MCP-compatible tools or worker processes, keeping the application close to a thin interaction shell [ anthropicMCP2024 ] . 3. Local-first evidence model. Data, traces, artifacts, and evidence graphs remain anchored to the research workspace; remote collaboration and mobile access are control channels, not replacements for local state. Figure 2 summarizes the layered architecture. Figure 2: SciForge system framework. Layer 2 exposes six scientific-workflow capabilities—Literature Review, Idea Generation, Experiment Design, Experiment Execution, Analysis & Iteration, and Scientific Communication. Each capability enters the same evidence-aware control chain—ingress, translation, execution, evidence capture, audit, and release—built on the interaction surfaces, core engine, scientific model router, and local-first infrastructure. 3.2 User Interaction and Collaboration (Layer 1) Layer 1 exposes three interaction surfaces driven by the same underlying runtime. The desktop application provides a thin GUI reserved for human judgment—reviewing evidence, annotating figures, comparing candidate artifacts, and approving release decisions—while execution runs in the background. Group chat integration (Zulip, Discord, WeChat, Feishu) enables remote task submission, status polling, and lightweight approvals without switching context. Mobile supervision enables remote monitoring and intervention for long-running experiments, with task submission and review actions gated through the same governance model. 3.3 Research Capability Patterns (Layer 2) SciForge supports six research capability patterns with explicit scientific input–output boundaries. Literature Review maps papers and source records to a field map that summarizes prior work and the current state of a domain. Idea Generation maps existing evidence to research questions, hypotheses, and candidate methods. Experiment Design turns a selected idea into a test plan with validation procedures, metrics, controls, and success criteria. Experiment Execution maps that plan to run records and artifacts by executing code, conducting experiments, invoking instruments, or delegating to computational pipelines. Analysis & Iteration maps results to diagnoses, revised assumptions, and a justified next step. Scientific Communication maps reviewed evidence and research artifacts to papers, reports, figures, and presentations. These capability patterns cover a common scientific workflow but are not a rigid linear pipeline: researchers may enter at any stage and iterate between stages. They remain contextual patterns within one workbench rather than independent applications with separate execution semantics. Regardless of entry point, each task follows the same evidence-aware control chain: (1) task and object ingress; (2) fail-closed translation when a native scientific object requires a domain expert; (3) delegated agent and worker execution through Layers 3 and 4; (4) provenance-attached evidence candidates with artifact and run lineage; (5) a thread-scoped Evidence Snapshot and advisory audit; and (6) goal-scoped review and candidate/certified release through the Project DAG and human PI. 3.4 Core Engine (Layer 3) The Core Engine plans and executes research work through coordinated subsystems. SciForge uses two connected evidence layers for scientific governance. The Evidence DAG (thread-scoped) automatically constructs a claim–source–reasoning graph from each agent session’s completed turns and persists it as a PROV-DM-aligned graph serialized in PROV-JSON [ w3cprov2013 , huynh2013provjson ] . The Project DAG (goal-scoped) consumes immutable Evidence DAG snapshots across sessions, merges equivalent findings while preserving independent source paths, and links claims to project objectives. Both layers compile asynchronously behind the main agent, keeping evidence up to date without blocking exploration. Audit runs are read-only sidechains that produce structured risk digests—flagging ungrounded claims, unresolved contradictions, weak support, or low-credibility sources—without mutating DAG state. All decisions, whether human or AI, enter through structured Decision Events, giving every modification a traceable, reviewable record. The Agent Runtime uniformly supports multiple agent backends—Codex, Claude Code, and custom runtimes—allowing research groups to select the execution environment that best matches their scenario: Codex for local-first interactive coding with full workspace access, Claude Code for extended autonomous task chains, and custom runtimes for specialized scientific computing or institutional deployment requirements. Across all backends, the Runtime coordinates the main agent, delegated sub-agents, tool execution, workspace operations, MCP worker invocation, and long-running task recovery through a consistent API surface. The Workflow Engine formalizes reusable pipelines with code, agent, tool, and approval nodes; scheduled execution and loop-style fixed protocol automation are treated as run modes rather than separate architectural modules. Scoped Research Memory stores free-text records (scope, tags, confidence, timestamps, context) across sessions; typed goals and decision events belong to the Project DAG. Evidence & Release Governance exposes goal-scoped release decisions (candidate and certified gates) through the Project DAG without synchronously blocking exploratory execution. 3.5 Scientific Model Router (Layer 4) The Scientific Model Router is a core architectural innovation of SciForge, acting as a universal model invocation plane that abstracts away provider heterogeneity while retaining the full expressiveness of each backend. Rather than forcing a lowest-common-denominator interface, the Router supports three request–response protocols—OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages—selected per provider through a normalized endpoint format, allowing each model to be invoked through its native, most capable API surface. Intelligent Auto-Routing. The Router includes a lightweight classifier that inspects the user request and recent context to automatically select the appropriate reasoning effort (off, high, or max), with a deterministic heuristic fallback so routing decisions do not rely on a single point of failure. Provider-Aware Optimization. For DeepSeek models, the Router performs proactive reachability probing, applies native thinking controls, and computes real-time cache-aware cost estimation in both USD and CNY. For all providers, it implements automatic retry with backoff, error classification, and stream-idle timeout detection. Output Robustness and Repair. The Router repairs malformed tool-call arguments—stripping Markdown fences and recovering partial JSON—and extracts embedded images from tool results as standard model attachments, enabling multimodal reasoning chains across scientific visualizations and model analysis. Scientific Modality Routing. For scientific files, the Router detects modality-specific extensions and applies one of two handling paths. Translate-then-reason applies to four currently supported modalities: protein (.faa; .fasta/.fa with per-record conservative content classification) translated by Esm2Text, protein structures (.pdb, .cif, .mmcif) by Prot2Text, small molecules (.smi, .smiles) by BioT5+, and single-cell transcriptomics via Cell2Sentence (C2S). Each translator output carries provenance metadata, allowing the main agent to reason over structured expert observations. VCF, BED, GFF, and MGF are unsupported and fail closed; raw content is not routed to the general reasoner. Multimodal translation caches store scientific and visual observations by content hash, enabling repeated requests to reuse expert evidence without recomputing final conclusions. 3.6 Infrastructure (Layer 5) The Infrastructure layer provides the durable substrate that anchors research activity to the local workspace. Local Scientific Memory stores papers, datasets, parsed documents, scientific file manifests, embeddings, indexes, tool outputs, run metadata, and artifact caches. The Modular Capability System packages computational functionality as Skills, MCP servers, Plugins, HTTP services, or worker processes—each independently versioned and upgradeable. Scientific Connectors normalize external resources such as papers, datasets, databases, APIs, instruments, notebooks, analysis scripts, reference managers, LIMS/ELN systems, and institutional storage into a unified access layer. The Reproducible Run Substrate records execution-target contracts, run and job state, logs, and artifact manifests so that downstream evidence can refer to concrete execution records. SciForge remains workspace-anchored and local-first; selected data may flow through explicitly configured model providers, connectors, or remote execution services. 4 Use Cases 4.1 Agentic Research Sprint: From Question to Manuscript Package Setting. A human PI poses the biological question “Which molecular systems drive mammalian germ cells into meiosis?” and delegates execution to SciForge, an AI4S research workbench. Codex—an AI coding agent replacing the human expert role—orchestrates SciForge’s agent-accessible services—literature search, candidate gene identification, structured hypothesis formulation, parallel sub-agents for multi-omics evidence synthesis, AlphaFold 3 structural assessment [ abramson2024alphafold3 ] , and iterative methodology hardening—within a multi-day, PI-controlled agentic loop (Fig. 3 ), with Codex serving as the PI’s AI delegate. Outputs are reviewed through evidence summaries, reviewer-style self-audits, and human decisions. After 132 stages and 199+ Git-tracked commits, the repository 1 1 1 https://github.com/AGI4Sci/scenario-01-research-sprint (archive available at time of writing) records the control loop as a local workspace log. Figure 3: Automated research pipeline executed during the SciForge scenario-01 research sprint. The 132-stage, 199+-commit agentic loop progresses from a biological research question through literature mining (DCT-M3), candidate gene curation, AlphaFold3 structural prediction, evidence triangulation, manuscript synthesis, and submission packaging. Quantitative metrics: 132 research stages, 199+ Git commits, 6 parallel child-agent runs, 9 generated figures