LLMs concept guide
Large Language Models
Large neural networks trained on text and other modalities to predict, generate, reason over, and transform information.
Linked research
12
Published MachinoAI explainers currently connected to this concept.
Questions and answers
Search Large Language Models questions
No published Q&A entries are available for this concept yet. Once the database is populated, up to 10 answers with images, metadata, linked papers, references, and SEO tags will appear here.
Research papers
Papers that connect to Large Language Models
OpenForgeRL
OpenForgeRL connects real agent harnesses, remote environments, and standard RL infrastructure so agents can be trained in deployment-like conditions.
Transformer
The original Transformer paper: architecture, attention mathematics, training recipe, benchmark evidence, ablations, and engineering trade-offs.
Agent-Editing World Model
AEWM turns world modeling into agent-state judgment and revision: keep useful decisions, edit noisy ones, then ground the trajectory with real execution.
Jev AI
Jev is TypeSafe AI’s first System One Model: state in, typed probabilistic decisions out.
GPT-6 Sol
A source-grounded deep dive into GPT-6 Sol covering model behavior, API/runtime design, benchmarks, effort economics, safety, limitations, and production agent architecture.
Grok 4.7 — Long-Horizon Agents
A source-grounded technical walkthrough of Grok 4.7 training changes, runtime controls, multimodal input, tool use, context management and long-horizon agent engineering.
AgentActionBench
A process-level benchmark for reliable research-agent execution.
Magenta
Verification-guided mathematical reasoning with Lean 4.
RRSI
Production-oriented agent harness evolution with transfer-aware regularization.
Opus 5.5
Opus 5.5 is a 1M-context, adaptive-thinking model optimized for long-running agents. The release’s standout theme is cost-adjusted capability: stronger task completion with lower per-token prices, lower token consumption, and faster generation, alongside production safeguards for high-risk workloads.
ToolGrad
Generate the successful tool-use workflow first, then synthesize the user query around it.
Agentic Reasoning
A tool-using agent framework that extends LLM reasoning with web search, coding, and structured reasoning memory for deep research tasks.