last_modified_at: 2026-09-06

The New Era of Research Tools — From Passive Chat to Autonomous Research Workflows — https://www.pirahansiah.com/notes/slides/research-tools/ Presentation: the modern research stack — Hermes Agent, LeapSpace, PaperBanana, AI citation finders, agent swarms, peer review, and your Obsidian second brain.

Last updated: 2026-09-06.

RESEARCH TOOLS · 2026

The New Era of Research Tools

From Passive Chat to Autonomous Research Workflows

16
Hermes research skills
6+
AI citation finders
99%
token reduction possible
parallel subagents

Dr. Farshid Pirahansiah
AI & Computer Vision Engineer • pirahansiah.com

The Shift: Old vs New Research Stack

📚 The Old Way

• Manual literature reading, 10,000+ papers/year.

• Copy-paste BibTeX, broken repos, grep-the-whole-repo.

• Passive chatbot that forgets context.

• Write abstract → intro → methods (wrong order).

🤖 The New Era

• Autonomous agents sweep, reproduce, draft.

• Verifiable citation finders, zero hallucinated refs.

• Persistent memory + reusable skills.

• Paper drafted methods → abstract (evidence-first).

Tools now act, not just answer. The researcher directs; the stack executes.

The Modern Research Toolbox

🛠️ Orchestration

Hermes Agent — terminal + skills + subagents.

Google Opal [Experiment] — AI app builder (sign-in).

Agent swarms (kimi.com → fan-out) for parallel sweeps.

🖼️ Insight & Illustration

LeapSpace (Elsevier) — Deep Research + Trust Cards.

PaperBanana — text-to-figure diagrams & charts.

Atlas — query your own library with cited passages.

📑 Citations & KB

Sourcely / Citely / Paperpal — find & verify refs.

Scite — support / challenge / mention labels.

Obsidian — your second brain, agent-editable.

Hermes ties them together: deepdive ≈ Deep Research · factcheck ≈ Trust Cards · cite ≈ citation finders · obsidian ≈ second brain.

Hermes Research Skills Catalog

8 new research skills + 8 existing — literature sweeps, critique, synthesis & citation.

Skill Trigger / what it does Status
deepdiveDeep multi-source investigation; cited synthesis with confidence + disagreement mappingNEW
researchgapFinds gaps, contradictions & open problems in a topic's literature; proposes research questionsNEW
criticRigorous critique of a paper/claim/argument with severity-rated weaknesses + verdictNEW
literature-reviewThemed survey of a topic with annotated bibliographyNEW
synthesiseMerges several sources into one attributed synthesis; flags consensus vs open questionsNEW
factcheckVerifies claims against sources; labels each supported/contradicted/unverifiableNEW
question-stormGenerates diverse, prioritized research questions across levelsNEW
citeFormats references in a citation style (APA/MLA/IEEE/BibTeX); finds real sourcesNEW
arxivSearch arXiv papers by keyword/author/categoryexisting
llm-wikiBuild/query interlinked markdown knowledge baseexisting
grounded-citationsGround answers in cited verifiable sourcesexisting
reference-curationAudit/curate doc reference linksexisting
polymarketQuery Polymarket markets/pricesexisting
competitor-news-monitorWatch companies for material newsexisting
blogwatcherMonitor blogs/RSS feedsexisting
research-paper-writingAuthoring structure for research papersexisting

LeapSpace & Your Research Profile

Elsevier's research-grade AI workspace (Scopus data) — and the author record it surfaces.

🪐 LeapSpace (Elsevier)

• AI workspace powered by Scopus + Elsevier full-text.

Deep Research reports: patterns, contradictions, evidence gaps.

Trust Cards + Claim Radar: sources & contradictions shown.

Writing Coach, Funding Scout, Author Search, collaborators.

researcher.elsevier.com/eur

👤 Farshid Pirahansiah — Scopus

h-index 6 · 12 publications · 73 citations

• Affiliation: Center for AI Technology, Bangi, Malaysia.

• Active years: 2010–2022.

• Topics: camera calibration, robot localization, image segmentation, OCR, license-plate recognition.

• Profile generated by LeapSpace, Sun Sep 06 2026.

Hermes mapping: deepdive/literature-review ≈ Deep Research · grounded-citations/factcheck ≈ Trust Cards/Claim Radar · cite ≈ Author Search.

PaperBanana: Automating Academic Illustration

Text-to-figure AI for researchers — publication-ready diagrams & charts from a description.

🔧 What it does

Methodology diagrams — model architectures, algorithm flows, encoders, system pipelines.

Statistical plots — generates executable Matplotlib code from raw data (no numeric hallucination).

Aesthetic enhancement — turns hand sketches / whiteboard notes into top-venue art.

Styles — Transformer, GAN, RAG, Multi-Agent templates; posters & more.

🤖 How it works

5-agent closed loop (Planner → Visualizer → …) for faithful, precise, polished figures.

Planner turns text into structured visual layouts.

Visualizer renders via Nano-Banana-Pro — exact shapes, connectors, icons.

Trusted by SNU, Stanford, UC Berkeley, CMU, Tsinghua, SJTU, Yonsei, IIT Madras, Monash, Broad Institute.

Example: prompt "encoder–decoder segmentation pipeline with skip connections" → ready architecture diagram in seconds. Reference: paper-banana.org

Best Reference Finder — AI Citation Tools

Dedicated finders query Crossref / Semantic Scholar — no hallucinated refs like chatbots.

Tool Best for Standout Styles
SourcelyBulk / paragraphScans essays, highlights text needing support, summaries700+ (BibTeX, RIS)
Citely AIClaim verificationPaste claim → matched to verified DOIsAPA, MLA
GrammarlyIn-line writingFlags missing sources in editor, inserts citationsAPA, MLA, Chicago
PaperpalMS Word flow250M+ articles, search by title/DOI10,000+
SciSpacePartial metadataBroken URL/author → complete citationBibTeX, RIS, CSV
WritelessPDF uploadsFilter by min year, inline insertionAPA, MLA, Harvard…

Beyond find: Scite labels citations support/challenge/mention · Google Scholar (free, manual) · Consensus (Consensus Meter) · manage with Zotero / Mendeley / MyBib. Hermes: cite formats, factcheck verifies, grounded-citations grounds.

How to Write a Paper — Write in This Order

Draft bottom-up: build the evidence first, then frame it. Read top-down.

  1. 1 · Methods — Lock the protocol, setup, datasets & metrics. The foundation everything cites.
  2. 2 · Results — Report what happened, raw: numbers, curves, observed behaviour.
  3. 3 · Figures — Build the visuals: plots, diagrams, architecture art. One idea each.
  4. 4 · Tables — Assemble comparison/benchmark tables; numbers must match figures.
  5. 5 · Discussion — Interpret: why it works, limits, implications, relation to prior work.
  6. 6 · Introduction — Open with the gap & motivation; now you know what you proved.
  7. 7 · Abstract — Written last: the 200-word distillation of the finished paper.

Hermes: researchgap scopes the gap · critic stress-tests claims · cite formats refs · research-paper-writing structures the draft.

Agent Swarms: Parallel Research at Scale

One orchestrator fans out to many specialized workers, then merges results.

🐝 How a swarm runs

Orchestrator splits the task into independent sub-goals.

Swarm = N parallel subagents, each with its own context & tools.

Merge: results aggregated, deduplicated, cross-checked.

Hermes: delegate_task spawns concurrent workers (no shared context bloat).

🌊 Example: kimi.com → swarm

1. kimi.com receives the research question (e.g. "compare 2025 VLM agents").

2. → swarm: fans out to subagents — ArXiv sweep, benchmark mining, repo cloning.

3. → …: each worker returns findings; orchestrator synthesizes one report + BibTeX.

• Same pattern in Hermes: 3 delegate_task calls → one literature matrix.

Why: 10× speedup vs serial search, isolated failures, no single context overflow. Pair with synthesise + critic.

Academic Peer-Review Loop

From submission to camera-ready — and how Hermes shortens each cycle.

📤 Submit

• Format to venue template (IEEE/ACM).

grounded-citations checks every claim links to a real source.

cite exports clean BibTeX/references.

🔍 Review

• Editors assign 2–3 anonymous reviewers.

critic pre-empts weaknesses before submission.

factcheck flags unsupported claims.

✏️ Revise

• Address each point (accept / rebut).

deepdive gathers new evidence for gaps.

synthesise merges reviewer feedback.

Loop repeats per round (R1 → R2 → …) until accept; then camera-ready + research-paper-writing polish. Average: 2–4 months per round.

Second Brain: Obsidian × Hermes

Turn your notes into a queryable, agent-editable knowledge base.

🧠 Connect Obsidian

• Vault = plain markdown; Hermes reads/writes via the obsidian skill.

• Path from OBSIDIAN_VAULT_PATH or ~/Documents/Obsidian Vault.

• Use [[wikilinks]] + YAML frontmatter (tags, aliases) for structure.

• Two-way sync: edit in Obsidian, Hermes sees it next turn.

🔌 Hermes skills for your vault

obsidian — search, read, create, edit notes & wikilinks.

llm-wiki — build interlinked markdown KB.

synthesise — merge notes into one.

cite — attach BibTeX to literature notes.

factcheck / grounded-citations — verify before saving.

Flow: capture → Hermes tags & links → query with search_files → surface in deepdive / literature-review. Your second brain, always current.

Google Opal Experiment

Google's experimental AI app platform — verified facts only; function not yet documented publicly.

🔎 What is confirmed

• Official Google product labelled "Opal [Experiment]".

• Web app (opal.google) loading in a sandboxed iframe.

• Requires Google sign-in (OAuth) to use.

• Requests camera & microphone permissions.

❓ Not yet public

• Exact purpose / feature set is not in the page source.

• Positioned in Google's "experiments" track (like Labs).

• Likely an AI app-/agent-building surface — unconfirmed.

• Check opal.google after sign-in for live capability.

Hermes angle: if Opal is an app/agent builder, it parallels skill_manage (custom skills) & delegate_task (subagents) — but treat as speculation until docs ship.

The New Research Stack

Act, don't just answer: agents sweep, reproduce, draft & verify.

Verifiable by default: citation finders & Trust Cards kill hallucinated refs.

Evidence-first writing: methods → results → figures → tables → discussion → intro → abstract.

Parallel & persistent: swarms via delegate_task, memory + Obsidian second brain.

Explore the tooling & code: pirahansiah.com

Thank You & Discussion

The New Era of Research Tools

All PresentationsGitHub Repositories