Reflection

Definition

Reflection asks an agent or model to inspect an outcome, feedback, or trajectory and produce a critique, diagnosis, or revised plan. It can improve later attempts, but it remains correlated self-review unless a separate verifier, model lineage, deterministic tool, or accountable expert independently challenges the result.

Research and practical use show promise, while reliability, calibration, and independence remain task-dependent.

Why it matters

Reflection creates a feedback artifact that can alter the next loop turn.

It should be treated as a builder improvement mechanism, not the final acceptance authority.

System anatomy

Signal

Test output, tool result, user correction, or other evidence.

Critique

A diagnosis of why the attempt succeeded or failed.

Update

A revised plan, memory item, or candidate output.

Important distinctions

Independent verification

Self-reflection shares model context and blind spots; independent verification separates judgment and block authority.

Retry

Reflection should introduce new evidence or a changed strategy before another attempt.

Implementation signals

• Ground critique in external evidence
• Keep builder reflection separate from release acceptance
• Evaluate whether reflections improve outcomes rather than merely sound persuasive

Failure modes

• Confident rationalization of the original error
• Poisoned feedback becomes durable memory

Sources and further study

1. arXiv / NeurIPS — Reflexion: Language Agents with Verbal Reinforcement Learning

   Introduces a feedback pattern in which an agent converts signals into verbal reflections retained for later attempts.

   Use in this library: Primary definition. Self-reflection can improve subsequent attempts in some tasks but is not independent verification and can preserve or amplify a model’s blind spots.

   paper · paper · Published 2023-03-20
2. DeepLearning.AI — Agentic AI

   A practitioner course organizing agentic systems around reflection, tool use, planning, multi-agent workflows, evaluation, and optimization.

   Use in this library: Official guidance. Course taxonomy is instructional rather than normative; it does not itself define enterprise authorization or assurance requirements.

   course · course · Published 2025
3. Anthropic — Demystifying evals for AI agents

   A practical treatment of evaluating trajectories, outcomes, graders, tasks, and agent-environment interaction.

   Use in this library: Official guidance. This is first-party engineering guidance drawn from Anthropic deployments. Evaluation designs remain task- and environment-specific, and the article does not establish independent verifier ownership by itself.

   engineering · engineering · Published 2026-01-09