Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.

An 18 notebook course that isolates and measures each component of agentic loop engineering on real, industry standard software datasets.

🪞 Systematic self-reflection for AI agents. GENERATE → CRITIQUE → REFINE → CHECK. Based on peer-reviewed research. Zero API cost. Works with Claude Code, Cursor, Copilot, Codex CLI, and 10+ more platforms.

A small Claude-Code/agent skill: a disciplined reflect→critique→improve loop over a plan or a code change, iterating until relatively perfect. Project-grounded variant of Self-Refine/Reflexion.

매일 쌓이는 메일을 빠르게 파악하고, 중요한 정보를 놓치지 않도록 돕는 LLM Agent 기반 Chrome Extension 서비스입니다.

Self-Refine prompt, logic, flow, and Mermaid graph extraction package

Empirical study of latent quality in LLMs under critical engagement

Prompt, logic, flow, and Mermaid graph extractions for AI Scientist v2, Self-Refine, and Reflexion

ARSENAL — Unified master LLM agent pipeline combining the best of AI Scientist v2, Self-Refine, Reflexion, Meta-Prompting, LATS, APE, and The Prompt Report

Predefined, reusable agent loops for Pi — declarative YAML pipelines with review gates, scoring, and goal-loop convergence. Built on pi-subagents.

Domain-neutral critic→plan→execute loop for large LLM-generated JSON state. Surgical RFC 6902 patching with path_finder + context narrowing sub-agents. At 100 entities full-regen breaks (0% fix); this stack stays at 100% with 5× fewer tokens.