Mapping the Landscape of AI and Research
Mapping the Landscape of AI and Research
Introduction
About me
- Dominik Lukeš
- [email protected]
- AI Consultant, AI Competency Centre
AI Consultant work
Work on academic productivity
Research in: Translation, Linguistics, Metaphor
Michealmas 2026 Mapping the Landscape Series
20 October · 12:30
27 October · 12:30
3 November · 12:30
10 November · 12:30
Michaelmas 2026 Workshops on Agents
9 November · 10:00–16:00
20 November · 10:00–16:00
30 November · 10:00–16:00
AI and research: A quick history
AI and research is changing
- AI writes or edits papers
- AI answers questions
- AI discovers literature
- AI hallucinates and makes errors
- AI makes independent discoveries
- AI autonomously runs full research workflows
- AI opens up more possibilities
- AI finds errors in published literature
Research roles through time
2021–2026: prediction and connected research tools
2021 · AlphaFold
- Prediction
- Predict protein structures
2023 · Coscientist
- Tool use and experimentation
- Connect an LLM to search, code and lab automation
2026 · AI scientist systems
- Research coordination
- Combine several research activities in one workflow
2026: AI scientists combine different research roles
25 March · The AI Scientist
- Code, experiments and writing
- Generate ideas, run computational work and write a manuscript
19 May · Co-Scientist
- Hypothesis generation
- Generate and critique hypotheses for experimental checking
19 May · Robin
- Analysis and laboratory feedback
- Link literature and analysis agents with experiments
Model knowledge benchmarks are saturated
Recent news
2026: labs report AI for scientific discovery
March–April · Chinese research labs
- Scientific models and infrastructure
- Intern-S1-Pro report — CAS ScienceOne announcement
16 April · OpenAI GPT-Rosalind
- Life-sciences research
- A lab announcement and developer evaluations
23 September · Anthropic Claude
- Biological discovery
- A lab report about an enzyme system
AI in Research Landscape
- Autonomous discovery
- Assisted discovery
- 3Researcher support
- Project management
- Expanded methods
- More types of data
- More mini experiments
- Increased ambition
- More work
Tools for AI in research
Tools for research
Deep Research history
Deep Research tools as of 2025
New paper review services
Everything is different in the age of agents
Dean W. Ball, Among the Agents, 2026
By the end of this year, the least important thing you will be able to do with frontier AI systems will be getting chatbots to answer questions, but this is still how most people will think of “AI.” Expect cognitive dissonance as a result.
Dean W. Ball, Among the Agents, 2026
Timeline of AI
- Capabilities: answer questions, summarise, translate
- Chatbots: ChatGPT, Gemini, Claude
- Specialist apps: NotebookLM, Elicit, Consensus
- Capabilities: write code, manage code base
- Outcomes: create scripts, dashboards, simulations and workflows
- Tools: Cursor, Lovable, Google AI Studio
- Capabilities: plan, work with files, run utilities
- Outcomes: more ambitious projects, manage data and replicate analyses
- Desktop agents: Codex, Claude Code, Antigravity
What are agents
What are agents
What makes an agent useful?
The agentic loop
Tools Agents can use
- Search files
- Search web
- Command commands
- CLI tools
- APIs
- Other models
- Custom scripts
- Browser
- Applications 🆕
Move from Oracle to Tool User and Tool Maker
Use external tools
Codex used SketchEngine API to run simple corpus analysis.
Run mini experiments
Codex made a plan to run mini experiment on compression, used local tools to convert images in various sizes and present results for visual inspection as HTML with a table.
Run long-running research loops
Simulate full scientific discovery
What agents enable
- More control and reproducibility
- More experiments
- More data processing
Desk top agents work on local files
| Aspect | Advantage | Trade-off |
|---|---|---|
| File handling | Files stay in your normal folder structure | You need to manage that structure properly |
| Retrieval | Outputs are easier to find later | You need to save and name things well |
| Scale | Easier to work across many local files | You need to know what folder you are giving it access to |
| Privacy | Some tasks can stay mostly local | Some tasks still require remote model processing |
| Persistence | The work is tied to your project folder | It does not automatically follow you to every machine |
Their work can be fully inspected
Full transcripts of all chats are stored as text files on disk. You can ask your agent to inspect them and give you a summary and analyse tool calls and token use.
You can even build an app to analyse them
Literature review example
Elicit (on the web)
Search Elicit via API
Run an Elicit literature survey on how university students use coding agents, then file the papers in a new Zotero collection.
I’ll load the Elicit skill first so I can follow its research workflow and choose the appropriate tools.
load_skill elicitTool results
Loaded the Elicit research skill. Available tools: search papers, screen results, extract findings.
I’ll search for empirical work on coding agents in university study and research, then screen the results for relevance.
elicit.search_papers {"query":"university students using AI coding agents for study and research"}Tool results
Found 18 candidate papers.
I’ll prioritise studies involving university students and extract the participants, tasks, findings and limitations for a comparable survey.
elicit.screen_and_extract {"criteria":"Empirical studies involving university students","fields":["Participants","Agent","Task","Findings","Limitations"]}Tool results
Selected 8 relevant papers. Prepared a survey summary and bibliographic metadata.
The selected papers are ready. I’ll load the Zotero skill to determine how to access the desktop library and organise them.
load_skill zoteroTool results
Loaded the Zotero skill. Read the guidance for accessing the desktop library through the local API.
I’ll check that Zotero is running and that the local API supports the operations needed to create and populate a collection.
zotero.local_api.inspect {}Tool results
Zotero is running. The library is accessible and collection creation is available.
Before importing anything, I’ll match the selected papers against existing library items to avoid duplicates.
zotero.find_existing_items {"papers":"the 8 selected papers"}Tool results
Found 3 existing items. Prepared 5 new items for import.
I’ll create a collection named for the survey, then file both the existing and newly imported papers there.
zotero.create_collection {"name":"Coding agents in university study — Elicit survey"}Tool results
Created collection A1B2C3D4.
I’ll import the five missing papers, add all eight to the collection, and verify its contents before reporting completion.
zotero.import_and_file {"collection":"A1B2C3D4","existing_items":3,"new_items":5}Tool results
Imported 5 papers. Verified that all 8 papers belong to the collection.
Your Zotero collection is created: “Coding agents in university study — Elicit survey”.
It contains 8 papers: 3 already in your library and 5 newly imported.
Open the collection in Zotero: zotero://select/library/collections/A1B2C3D4
Import and tag papers into Zotero collections
Create a visualisation of references for easier review
From paper summaries to visualisations and replications
More small experiments
Small experiments: Breakfast TM example
What a small experiment looked like a year ago
A small research project today: Audio Archive Project
Created from 340 hours of audio files over the weekend
Research process
Lessons from audio archive project
- What would have taken a project team weeks can be done in by one person in a few days
- Agents can act as the research coordinator while researcher acts as PI
- Smart models can make good choices about research design process along the way
- It is possible to document the process and inspect all decisions
Impact on research process
Key consequences
- Impact on the research environment
- Project team roles
- Project design
- Project funding
- Researcher education
Journals struggle with paper overproduction
Some fields study with glut of results and identity crisis
Existing results are finding errors
Impact on research projects
- Timelines
- Aims
- Roles
- Costs
Impact on researcher education
- Speed of change
- Gaps in supervision
- Uncertain method impact
- New challenges to results review
- Lack of expert trainers