← Back
Home › Systems › Frontier AI research

ai-co-scientist

hypothesis generation and lab automation

Google AI co-scientist, FutureHouse

SystemTechniques · 18Primitives · 77 ai-co-scientist Citation groundingagentic-ai · medium: Attaching answer spans to retrieved source passages and verifying each claim is supportedHuman-in-the-loop approvalagentic-ai · medium: Classify each proposed action as auto, ask or deny; park asks as durable pending records a human approves, edits or rejects, executing once, with timeouts that deny.›Durable workflow executiondistributed · medium: Ordinary code made crash-proof by logging every side-effect result and replaying the code from that log; activities run at least once, workflow logic must be deterministic.›Density-based clustering (DBSCAN)machine-learning · medium: Group points that are packed densely, label the rest as noise: no k, arbitrary shapes, two parameters (eps, minPts), cost set by the neighbour index.›Entity linkingmachine-learning · medium: Map each mention to a knowledge-base id, or to NIL, by generating candidates from an alias table, scoring them on prior and context, and thresholding.›LLM-as-judgemachine-learning · medium: Grade open-ended outputs with a language model under a rubric, then correct its known biases by order swapping, voting and calibration against human labels.›Relation extractionmachine-learning · medium: Extracting (subject, relation, object) triples from text with classifiers or LLMsEmbeddingsmachine-learning · low: A learned table mapping discrete ids to dense vectors: gather forward, sparse scatter-add backward, row-wise optimizers to keep huge tables cheap.›Bradley terry modelstatistics · low: Pairwise comparison model P(i beats j)=s_i/(s_i+s_j); MLE fit, link to Elo and reward modelsAgent loopagentic-ai · unknown: Agent memoryagentic-ai · unknown: Context window managementagentic-ai · low: Keep an agent's growing history inside the model's window by truncating, clearing and summarizing old turns in a cheap-to-lossy ladder, at turn boundaries.›Subagent orchestrationagentic-ai · unknown: Task planningagentic-ai · unknown: Tool callingagentic-ai · low: The model emits a structured call (id, name, JSON arguments) instead of prose; your code validates, runs it and returns a result tagged with the same id.›Elo ratinggame-networking · low: One number per competitor, moved by K × (actual − expected score) after each pairwise result; expected score is logistic in the rating difference.›PDF text extractionmachine-learning · low: Rebuild words, lines, columns and reading order from the glyph positions a born-digital PDF stores, and route pages without usable text to OCR.›Self consistency votingml-training · low: Sample several answers and pick by majority or execution agreement to raise reliabilityHybrid search and rank fusionsearch-sort · low: Merge a keyword (BM25) result list and a vector (ANN) list into one ranking, by ranks (RRF) or by normalized scores (convex combination).›Text chunkingmachine-learning · low: Cut documents into token-bounded pieces along structure boundaries, keeping offsets and section paths, so each piece embeds well and can be cited.›Fuzzy string matchingsearch-sort · low: Edit distance, Jaro-Winkler and trigram indexes for approximate name and address matchingStatechartsgraphics · low: State machines with nesting, parallel regions, history and entry/exit actions, so UI and animation logic stays linear in size instead of exploding.›Dual control approvalsecurity · low: Four-eyes / maker-checker approval with quorum policies for sensitive operations+ 11 more techniques+ 61 more primitives

Similar systems

Share the most building blocks with this one.

deep-research 36 %automated-ai-research 33 %support-agent 26 %multi-agent-orchestrator 23 %coding-agent 18 %