Search Results for "agent based"

Agent Executor (AX) is a Google research project for learning discrete choice models through differentiable maximum likelihood estimation. It is designed for situations where a model needs to predict choices from a finite set of alternatives, such as ranking, recommendation, preference modeling, or decision behavior analysis. The project provides JAX-based tools for defining and training choice models with automatic differentiation.

Shepherd is an early-stage Python runtime for building agents and meta-agents around reversible, inspectable execution traces. It records interactions and workspace changes as durable run histories instead of immediately applying an agent's output. Each result can be reviewed, executed separately, selected, merged, released, or discarded. Tasks are declared as Python functions whose signatures and documentation define the agent contract and required resources. Read-only and read-write...

DSH Routing Suite packages a runtime injector and task-aware reasoning presets for the DSH agent environment. Its injector can add, hot-reload, promote, remove, and repair routes without restarting the runtime. The included router presets choose among planning, execution, weak self-classification, and deeper reasoning behaviors based on the task and model. Near-field guidance is injected after user messages to keep routing focused and resist drift.