Concept record · edition 1.0.0
Agent loop
What the term means here
An iterated cycle of reasoning, acting through tools, and observing results, continuing until a stopping condition.
Why it matters
The loop and its environment are a system distinct from the model inside it. Attributing loop performance to the model is the most common category error in capability reporting.
Related claim records · 3
- si-009
Language models can be trained or prompted to invoke external tools and incorporate returned results.
- si-010
The design of the agent-computer interface materially changes measured coding-agent performance holding the underlying model fixed.
- si-019
Increases in measured long-horizon performance are attributed in part to improved reliability and error recovery rather than to reasoning improvements alone.
Sources used here · 2
ReAct: Synergizing Reasoning and Acting in Language Models
Yao et al. · 2022
The interleaved reason-and-act pattern underlying most agent loops.
Source record →AgentBench: Evaluating LLMs as Agents
Liu et al. · 2023
Multi-environment agent evaluation, cited for evaluation design rather than rankings.
Source record →