← Back
Home › Systems › Frontier AI research

automated-ai-research

agents that run ML research

AI Scientist, lab research agents

SystemTechniques · 35Primitives · 113 automated-ai-research Citation groundingagentic-ai · medium: Attaching answer spans to retrieved source passages and verifying each claim is supportedEdit applicationagentic-ai · medium: Apply model-proposed code edits robustly: search/replace blocks, unified diffs, fuzzy anchor matching and conflict reportingDurable 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.›Gang schedulingdistributed · medium: All-or-nothing co-scheduling of a job's tasksLLM-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.›Experiment trackingml-training · medium: Logging params, metrics, artifacts and code versions per run with an append-only metric store and comparisonPopulation based trainingml-training · medium: Parallel training population with periodic exploit (copy best weights) and explore (perturb hyperparameters)Agent loopagentic-ai · unknown: Agent memoryagentic-ai · unknown: Agent sandboxingagentic-ai · unknown: Code context retrievalagentic-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.›GPU cloudcloud · low: Where to rent GPUs for training and inference: hyperscalers for integration, neoclouds for price, spot and marketplaces for cheap batch work; interconnect decides multi-node training.›Failure bisectionsearch-sort · low: Binary search over commits, batches or inputs to isolate a failureHybrid 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 matchingEdit distancesearch-sort · low: Levenshtein/Damerau distance by DP, bit-parallel Myers variantRecord replaydistributed · low: Record every nondeterministic input (time, randomness, I/O, model and tool outputs, per-tick player input) and re-execute deterministically for debugging, replays and state rebuildEvent sourcingfinance · low: Persist state changes as an append-only stream of immutable events per entity; current state is a fold over them, guarded by expected-version appends.›+ 28 more techniques+ 97 more primitives

Similar systems

Share the most building blocks with this one.

ai-co-scientist 33 %coding-agent 27 %deep-research 25 %support-agent 18 %multi-agent-orchestrator 18 %