Corpus Agentis
The field book to agent ecosystems
The field book to agent ecosystems
Design · Topologies

Recursive

Reason-act-observe loop converging toward a goal.

Verified against arxiv.org

Recursive agent topology diagram

A recursive agent loops on itself until a stopping condition is met: reason, act, observe the result, then feed that observation into the next pass. Rather than a fixed pipeline it re-plans each turn with fresh evidence. This is the shape behind most coding and research agents: the model proposes a step, a tool executes it, the outcome revises the plan, and the loop repeats until the task is done or a budget is hit. In anatomy terms it is the reasoning core wired to its own working memory and effectors in a tight feedback cycle.

In the anatomy

The reasoning core, working memory and effectors form a closed reason to act to observe to revise loop; the policy perimeter gates each iteration's writes, and a budget or stop-condition bounds the cycle.

At a glance
PatternRecursive
State modelsession
ExampleClaude Code, Devin
Common use cases
  • ·Coding agents that iterate: write, run, read the error, fix (ChatGPT, Claude, GitHub Copilot).
  • ·Research agents that search, read and refine a query across turns.
  • ·Any open-ended task where the next step depends on the last result.
Strengths
  • ·Handles open-ended, unpredictable tasks a fixed pipeline cannot.
  • ·Self-correcting: each observation improves the next attempt.
  • ·Minimal orchestration: one core, one loop.
  • ·Naturally traceable as a turn-by-turn transcript.
Weaknesses
  • ·Can loop without converging: needs hard budgets and stop conditions.
  • ·Cost and latency compound with every iteration.
  • ·Error accumulation: a bad early step can derail the whole run.
  • ·Harder to guarantee bounded behaviour for safety-critical use.
Agents using this pattern · 36
ChatGPT AgentClaude AgentGemini AgentGitHub CopilotGitHub Copilot Cloud AgentMicrosoft 365 CopilotM365 Copilot ChatCursorSourcegraph CodyDevinGemini Enterprise PlatformMistral VibeXBOWHorizon3.ai NodeZeroZeroPathRogoHebbia MatrixFutureHouse (Robin / Kosmos)Sakana AI ScientistLila SciencesAiderOpenHandsSWE-agentContinue.devZed AIWarp AIBolt.newv0LovableGlass HealthJulius AIHex MagicDatabricks AssistantOpenAI Deep ResearchGemini Deep ResearchPerplexity Deep Research

Mapping classified by the Field Book from each agent's documented control flow.

Basis

Description, use cases and trade-offs: Field Book analysis, synthesised from established agent-architecture literature.

Verified against
https://arxiv.org/abs/2210.03629

The corpus does not rewrite vendor documentation. Where copy is quoted verbatim it is marked as such and attributed to its source.