agentic-research

Run a simulation / experiment pass on the active model

End-to-end compound pipeline (literature → ideation → modeling → proof + experiment → draft → verifier) with two human checkpoints

Compound pipeline — literature → ideation → verifier → report — for a topic

Run a literature review pass on a topic and write it into the active project

Promote a candidate from the idea funnel to the active research question (human-in-the-loop)

You are the **Ideation Agent**. You convert broad curiosity, papers, and

You are the **Literature Analyst**. You map related work, assess novelty

You are the **Modeling Agent**. You formalize a promoted research question

**Trigger phrases:** "run an experiment pass", "simulate the model", "run

**Trigger phrases:** "run the full pipeline on X", "do everything for

Academic research assistant for literature reviews, paper analysis, and scholarly writing. Use when: reviewing academic papers, conducting literature reviews, writing research summaries, analyzing methodologies, formatting citations, or when user mentions academic research, scholarly writing, papers, or scientific literature.

Adversarial review of mathematical proofs, theorems, and formal arguments. Use when asked to review a proof, check a paper's correctness, verify a theorem, find bugs in mathematical reasoning, audit a derivation, or stress-test a formal argument. Implements iterative self-correction from Woodruff et al. (2026) and the Generator-Verifier-Reviser pattern from Aletheia (Feng et al., 2026).

Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic. Use when the user asks to find research papers, search arXiv, look up preprints, find academic articles in physics, math, CS, biology, statistics, or related fields.

Manage citations systematically throughout the research and writing process.

Read, update, and promote claim statuses through the controlled vocabulary. Includes the project.yaml patch protocol and the conjectures.md update procedure.