Self-improving AI / Self-Refine
Self-Refine
“we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement.”
Self-Refine is one of the projects on the self-improving AI map. Below is what it changes about itself, whether the change lasts, and whether it improves the improver, each with the line from its own source.
Where it sits
Columns: what it changes, from the surface to the deepest change. Rows: whether the change outlasts the run. A number is how many projects sit in that square. See it on the 3D map
- What it changes
- Prompts, memory, context“we retain the history of previous feedback and outputs by appending them to the prompt”
- Does the change last
- Gone when the run ends“The feedback-refine iterations continue until the desired output quality or task-specific criterion is reached, up to a maximum of 4 iterations.”
- Does it improve the improver
- does not improve how it improves“Self-Refine relies on a suitable language model and three prompts (for initial generation, feedback, and refinement), and does not require training.”
- Who sets the goals
- people set tasks and scoring“p_{\text{gen}} is a task-specific few-shot prompt (or instruction) for an initial generation”
- How it was tested
- own benchmark numbers“Across all evaluated tasks, outputs generated with Self-Refine are preferred by humans and automatic metrics over those generated with the same LLM using conventional one-step generation”
Date is arXiv v1. One LLM drafts an answer, critiques it, and rewrites it, up to four times per input. What improves is that one output; the model and the few-shot prompts stay the same, and the paper describes no carry-over between inputs. The task prompts and few-shot examples are written by people: taken from previous work where available, otherwise by the authors.
Does it count as RSI?
It depends on the definition. Under the four used on What counts as RSI, by what its own source says:
- Loose (Eliezer Yudkowsky, Intelligence Explosion Microeconomics (2013)): does not count
- Durable (Ren et al., self-improvement survey (2026)): does not count
- Strict (Roman Yampolskiy, From Seed AI to Technological Singularity (2015)): does not count
- Autonomous (Anthropic, When AI builds itself): does not count
How it got here
Earlier work in this catalog that Self-Refine cites, oldest first. Under each: where that work sits on the map, then where Self-Refine sits (changes in bold), and what Self-Refine's own paper says about it. Its whole family on the citation map
2023 Reflexion sets itself apart
Prompts, memory · gone when the run ends · does not improve the improver
“Compared to a concurrent work, Reflexion [Shinn et al. (2023)](https://arxiv.org/html/2303.17651#bib.bib41), our approach involves correction using feedback, whereas their setup involves finding the next best solution in planning using ReAct.”
“While ReAct and Reflexion provide a free-form reflection on whether a step was executed correctly and potential improvements, our approach is more granular and structured, with multi-dimensional feedback and scores.”
2023 Self-Refine
Prompts, memory · gone when the run ends · does not improve the improver
Cited by Promptbreeder 2023, ADAS 2024, Gödel Agent 2024, SICA 2025, Darwin Gödel Machine 2025, Ren, self-improvement 2026, Recursive Harness Self-Improvement 2026, Harness² 2026, ECG-RSI 2026, Self-HPO 2026, RSIV-Harness 2026
In the same square
ADAS: Automated Design of Agentic Systems, AlphaEvolve, AREX-2, LM2LM, MLEvolve, ParetoRSI-Gym, PostTrainBench, Promptbreeder, Reflexion, The AI Scientist