An answer with references and polished charts still needs source support, correct analysis, independent reproduction and disciplinary judgment before it becomes a research conclusion. This guide checks materials as of November 15, 2026 and combines current product documentation, university cases and peer-reviewed papers into a traceable workflow. The prompts and four data rows are original teaching examples. The offline script checks synthetic arithmetic.

Read the progress in 2026 by type of evidence

This year's developments connect language models to materials, programs and feedback. Paper2Agent works with a paper and its callable methods. ERA searches over code candidates that can be scored. Research labs are beginning to interpret many existing experimental observations in parallel. Their results depend on different inputs, objectives and checks, so tool selection starts with the task and study design.

Nature: Paper2Agent · Nature: Empirical Research Assistance

Four kinds of public evidence support different conclusions
Date and materialWhat was observedScope of the conclusion
2026-11-06, BioBasicsBenchScores on 100 tasks using raw wet-lab evidenceVendor benchmark. Check the scoring and failure cases in the original
2026-10-21, Rosalind analysis caseParallel interpretation of existing experimental dataVendor collaboration and preprint. Follow-up hypotheses require experiments
2026-09-16, Nature Paper2AgentPapers and code exposed as callable methodsPeer-reviewed computational study, constrained by code and environment availability
2026-08-27, Bocconi/OpenAIAssignment performance in a classroom randomized experimentTechnical report and institutional account. The grading dimensions affect interpretation

OpenAI: BioBasicsBench, 2026-11-06 · OpenAI: distributed biological analysis, 2026-10-21 · Nature: Paper2Agent · OpenAI and Bocconi: ChatGPT and causal-thinking training

Record the sample, comparator, execution budget and endpoint as you read. Algorithm scores, expert preferences and experimental validation belong in separate fields even within one study. A model's own confidence label can go into the list of items to check. The researcher still needs to locate the underlying support.

Identify the product, access permissions and storage location

ChatGPT file analysis can help explore tables and inspect analysis code. The API lets a team design its own orchestration and records of tool calls. Specialized scientific models have additional access requirements. Current official help distinguishes Rosalind Research, Discovery and product approvals. The Academic Plan includes no API access or API credits. Labs should check current eligibility before applying.

OpenAI Help: current GPT-Rosalind access · OpenAI Help: data analysis with ChatGPT

Choose the surface by the artifact you need
SurfaceUseful first tasksChecks before formal research
ChatGPT and data analysisOrganize public material, explore small tables, draft codeExportable inputs, analysis code, results and human edits
Your own API workflowDefined retrieval scope, versioned tasks, batch recordsInstitutional approval, usage costs, external tool permissions and logs
Specialized access such as RosalindConnect scientific tools within the approved scopeOrganization and user approval, the specific product and separate API eligibility
Paper-specific agentsReuse the program and method from a paperVersion, license, dependencies, test data and applicable field

OpenAI Help: current GPT-Rosalind access · Nature: Paper2Agent · OpenAI API: web search sources and citations · OpenAI Help: data analysis with ChatGPT

Workspaces have a lifecycle too. The current Prism announcement says it will close on January 1, 2027 and asks users to export in advance. Teams using it can move source files, references and figures into materials they can retain and open themselves. Check that a new tool can export research artifacts before committing a project to it.

OpenAI: current Prism announcement

Turn the research question into a checkable task

Before searching, write one page describing the population or object, intervention or comparison, outcome measures, time range and exclusion rules. An exploratory project can retain unknowns while marking choices made after seeing the data. Ask the model to identify conflicting definitions before generating subquestions. This helps prevent related but distinct topics from merging into one conclusion.

For example, a graduate student comparing two forms of teaching support should define assignment quality, immediate testing and delayed unaided testing separately. Each measures a different activity. Agree on the endpoint first so you can assess what a polished assignment says about learning. Assign people to check literature, analysis code and the interpretation in the relevant field.

A reusable prompt for a research task
Task: Create a checkable analysis plan using only my question and supplied materials.
List the population or object, comparison, primary outcome, time range and exclusion rules.
Identify incomplete definitions and retain unknowns.
Distinguish prespecified analyses from exploration added after seeing results.
For each step, list inputs, artifacts, verification method and human owner.
List papers whose original text you have not read as candidates to check.
Do not invent DOIs, sample sizes, measurements or experimental results.

Turn search results into a record of claims and sources

A search tool can return citations with URLs and the sources it consulted. Open the original, locate the methods, sample and results, and check whether they support the sentence you are writing. A title, abstract and full text provide different levels of evidence. When full text is unavailable, record what you actually read and look for an author archive or other accessible material.

OpenAI API: web search sources and citations

Keep fields for source_id, stable link, version date, passage or table, support, limitations and reviewer. Connect a preprint to its later version and retain negative and conflicting findings. A systematic review also needs the discipline's records for databases, search strings, deduplication and inclusion decisions. Completeness requires its own check.

A reusable prompt for literature evidence
Using only original material actually read in this round, record every important claim.
Fields: claim_id, source_id, URL/DOI, version date, page or table,
study design, sample/denominator, direct support, limitations and unresolved checks.
Separate reported results, authors' interpretations and your own inferences.
Keep conflicting findings side by side. Do not vote by citation count.
Identify the evidence most likely to overturn the conclusion and the next search question.
List sources for which you saw only an abstract or could not access the full text.

Let the model write code while retaining reproducible inputs

Before analysis, retain a read-only original and its checksum. Define missing values, units, duplicate records and the sampling unit. Separate cleaning scripts from result tables and keep the actual plotting data. ChatGPT can show the analysis code it generated. Read the important transformations and recalculate in an environment your team controls.

OpenAI Help: data analysis with ChatGPT

The four rows below demonstrate records and arithmetic checks. The script verifies unique row IDs, group labels and integer types, then calculates means of 3 for A and 5 for B, with a difference of 2. It includes no random assignment, error model or external validation, and explicitly keeps the causal-claim field false. For real research, add appropriate statistical analysis and independent data.

Offline example using the Python standard library, ready to save and run
import json
from fractions import Fraction

# Synthetic classroom fixture. No model call or external data.
rows = [
    {"id": "s1", "group": "A", "value": 2},
    {"id": "s2", "group": "A", "value": 4},
    {"id": "s3", "group": "B", "value": 4},
    {"id": "s4", "group": "B", "value": 6},
]
assert len({row["id"] for row in rows}) == len(rows)
assert {row["group"] for row in rows} == {"A", "B"}
assert all(type(row["value"]) is int for row in rows)

means = {}
for group in ("A", "B"):
    values = [row["value"] for row in rows if row["group"] == group]
    assert len(values) == 2
    means[group] = Fraction(sum(values), len(values))
difference = means["B"] - means["A"]
assert difference == 2

result = {
    "schema": "research-check-fixture/v1",
    "synthetic": True,
    "n": len(rows),
    "mean_A": str(means["A"]),
    "mean_B": str(means["B"]),
    "difference_B_minus_A": str(difference),
    "causal_claim_supported": False,
}
print(json.dumps(result, sort_keys=True))

When execution fails, record the input version, error, repair and new output together. Once a program runs, inspect leakage, grouping units, train/test splits and dimensions. Changes to the metric or removal of unusual records should produce a reviewable difference for the research lead to accept or reject.

The Stanford case shows how a paper becomes callable

Paper2Agent packages papers, data and programs as methods an agent can call. In Nature's computational biology corpus, 74 of 100 papers were converted successfully. Missing code, data or a working environment were important failure causes. This supports reusable research engineering and suggests checking material availability before choosing a project.

Nature: Paper2Agent

Stanford's account explains that failed attempts and experimental judgments beyond the paper still need the authors' input. Before connecting a paper agent, reproduce the paper's own example, then test new held-out inputs and mark assumptions the authors have clarified. When several paper agents collaborate, record units, input constraints and uncertainty at each handoff.

Stanford Medicine: Paper2Agent research case

The Rosalind case turns existing data into follow-up questions

On October 21, OpenAI reported that it, PerturbAI and Scripps Research used thousands of agents to interpret existing mouse brain-cell experimental data in 32 minutes and generate follow-up leads. The linked study is a preprint. The timing belongs to that analysis run. Proposed biological mechanisms need further experiments.

OpenAI: distributed biological analysis, 2026-10-21

A transferable approach is to divide work into independently checkable objects, then combine reports in one record. Retain inputs, citations, candidate explanations and counterevidence for each object. The consolidating reviewer checks for repeated sources being counted as independent evidence and shared faulty assumptions across agents. More agents also require more capacity for deduplication and review.

Use raw experimental evidence to expose model blind spots

BioBasicsBench, published on November 6, contains 100 raw wet-lab tasks. Astra at xhigh earned 66.7% of available credit on average. This is rubric-based mean reward. The official failures include an assumption overriding experimental controls, showing how a correct local image observation can still produce a wrong conclusion.

OpenAI: BioBasicsBench, 2026-11-06

An experimental agent can therefore report observations, interpretations and proposed actions in separate fields. Observations identify image regions, measurements and controls. Interpretations list competing hypotheses. Actions specify the evidence still needed for a domain researcher to decide. Ambiguous images, missing controls and contradictory readings should allow an insufficient-evidence outcome and retain the originals for review.

Compare models through the task and validation design

Nature's Co-Scientist paper describes Gemini agents generating and refining hypotheses, with validation in defined biomedical applications including in vitro experiments. ERA searches code candidates around scorable tasks and reports held-out evaluations. These approaches emphasize candidate-question quality and performance after a method is executed.

Nature: Empirical Research Assistance · Nature: Co-Scientist

Give four kinds of research output their own acceptance checks
Research objectMain model outputIndependent check to retain
Search and synthesisLiterature set, evidence table, draft interpretationOriginal support, inclusion decisions and contradictory results
Computational method and programCleaning code, fitting, simulation and predictionRetained inputs, test split, recalculation and external data
Experimental hypothesisCandidate mechanism and reasons for a proposed experimentControls, replication and disciplinary review
Multi-agent synthesisReports across objects and cross-disciplinary connectionsDeduplication, shared assumptions, review queue and stop conditions

When selecting a system locally, provide the same material, tools and budget to each candidate. Hide reference results and include unfinished tasks and human rework in the denominator. A better hypothesis score still needs a separate check on your images, programs or reproduction tasks.

Education research needs both assignments and unaided learning

In OpenAI's March study of over 300 students, the primary ITT result improved in microeconomics while the neuroscience difference was not distinguishable. August's Bocconi randomized experiment found ChatGPT support and causal-thinking training improved different assignment dimensions. These institutional studies retain their task and assessment boundaries.

OpenAI: understanding AI and learning outcomes · OpenAI and Bocconi: ChatGPT and causal-thinking training

Suggested checks for a graduate course
GoalAI-assisted activityIndependent measure
Master a methodAsk for steps and counterexamplesUnaided transfer problems and delayed tests
Judge literatureOrganize supporting and conflicting materialsStudent explains orally why a citation supports a claim
Programming capabilityDraft code and suggested testsAdapt code to new data and explain failures
Original questionsGenerate candidate directions and challenge assumptionsAssess novelty and testability beyond the preset rubric

Set the primary endpoint and grader blinding before the experiment, and record actual use and attrition. Distinguish the effect of being offered access from intensity of use. Schedule delayed testing separately. Language, accessibility and device conditions also matter so that comparison groups can access the basic learning resources.

Attach confidentiality, responsibility and disclosure to the artifacts

ICMJE requires disclosure of AI use under the applicable journal's rules and keeps authorship responsibility with humans. Nature Computational Science's policy also restricts uploading confidential review material to public or unsecured AI systems. Before submission, the corresponding author checks the target journal, institution and project requirements.

ICMJE: authors' responsibilities when using AI · Nature Computational Science: transparent use of AI

OpenAI documents default training use for business, education and API data. Connected apps, organizational access and retention still need separate checks. A research team can maintain a list of uploadable materials, with institutional review of the handling route for unpublished data, personal information, licensed material and participant consent.

OpenAI: business and education data privacy

  1. Keep the research question, data provenance, licenses and applicable approvals.
  2. Record the model, date, tool permissions, prompt version and human edits.
  3. Package original inputs, code, outputs and failure logs for export.
  4. Assign different roles to check citation support, numerical analysis and disciplinary conclusions.
  5. Record the actual AI contribution and disclose it under journal and institutional rules.
  6. Assign a maintainer for source corrections, environment changes and broken links.

Measure value through accepted artifacts and review effort

Start with ten small tasks with known answers or feasible human verification. Define acceptance criteria before the agents run. Count original sources found, code reproduced, usable charts and appropriate insufficient-evidence responses separately. Record failures, waiting and repairs too, so the next round can address the tool or the task definition.

Raw measures for a small pilot
MeasureCalculationContext to retain
Accepted delivery rateTasks passing preset checks ÷ all assigned tasksDifficulty, attrition and failures
Total human timePreparation + supervision + review + repairsCompare with a manual process held to the same quality standard
Cost per accepted itemTotal pilot expense ÷ accepted deliveriesIf none qualify, report that the ratio is unavailable
External reproductionResults repeated by an independent person or on independent dataReplication design, materials and versions
Error recoverySteps required to withdraw a wrong output and rerunWhether it already entered a report or external decision

Extra speed can matter, especially for repeated organization and script drafts. Check whether review queues consume the time saved before accepting a claimed gain. Summarize error types weekly and fix repeated causes such as missing inputs, inconsistent units and unreproducible environments first.

Give every result a path back to its source

  1. Prespecify the question, outcomes and permitted materials
  2. Read originals and connect claims to exact source locations
  3. Fix the inputs and environment, retain model and code versions
  4. Generate candidate explanations, programs or experiments
  5. Check controls, held-out data and independent review
  6. Get the research lead's sign-off and disclose the actual AI contribution
  7. Retain failures and uncertainty to plan the next validation
From the research question to verification and the next question

These are conditional judgments based on the materials above, with time measured from November 2026. The nearest opportunities connect checkable artifacts, including search to code, papers to tools, and analysis to candidate explanations. Longer-term gains also depend on data permission, external validation, experimental scheduling and team maintenance. One model update cannot establish their timetable.

Trends, conditions and evidence that could overturn the forecast
Horizon and trendConditions neededCounterevidence to keep watching
Next 0–12 months, more papers with callable methodsAuthors publish maintainable code, data and environmentsFrequent dependency failures make reproduction costlier than manual adaptation
Next 0–12 months, more specialized scientific toolsDisciplinary evaluation, access approval and integration with existing toolsA general model suffices while specialized access adds administrative effort
Next 12–36 months, larger multi-step computation and experiment loopsInstrument interfaces, approvals, recovery and validation advance togetherToo many candidates for available experiments, with review becoming the bottleneck
Next 12–36 months, courses assess more of the research processCredible measures of unaided understanding, transfer and retentionOnly final text improves and learning gains do not persist

A lab can start now with one repeatable task using low-sensitivity material. Record the existing process's time and quality, then run a comparable pilot. Keep citations, code and review decisions and expand according to the results. As models improve, the team will already have a research record it can compare and migrate.