Self-improving AI / Reflexion
Reflexion
“We propose Reflexion, a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback.”
Reflexion 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“Reflexion agents verbally reflect on task feedback signals, then maintain their own reflective text in an episodic memory buffer to induce better decision-making in subsequent trials.”
- Does the change last
- Gone when the run ends“The Actor, Evaluator, and Self-Reflection models work together through trials in a loop until the Evaluator deems τt to be correct.”
- Does it improve the improver
- does not improve how it improves“We propose Reflexion, a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback.”
- Who sets the goals
- people set tasks and scoring“between trials, we use exact match answer grading using the environment to give a binary success signal to the agent”
- How it was tested
- own benchmark numbers“Reflexion improves performance over strong baselines by 22% in AlfWorld, 20% in HotPotQA, and 11% on HumanEval.”
Date is arXiv v1. After a failed trial, the agent writes a reflection that is kept in memory for its next attempt at the same task. Memory is capped at a set number of reflections, usually one to three, and the paper describes no reuse across tasks. The LLM is not fine-tuned. On HotPotQA the success signal between trials comes from exact-match grading against the answer; on coding, the agent writes its own unit tests.
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 Reflexion cites, oldest first. Under each: where that work sits on the map, then where Reflexion sits (changes in bold), and what Reflexion's own paper says about it. Its whole family on the citation map
It cites nothing in this catalog, or our copy has no reference list.
Cited by Self-Refine 2023, Voyager 2023, STOP 2023, The AI Scientist 2024, ADAS 2024, Gödel Agent 2024, SICA 2025, AlphaEvolve 2025, Darwin Gödel Machine 2025, Ren, self-improvement 2026, Weco AIDE² 2026, Recursive Harness Self-Improvement 2026, SPADE 2026, Fibona Agent 2026, Harness² 2026, ECG-RSI 2026, Terminal-RSI 2026, Self-HPO 2026, CoEvo-RSI 2026, RSI-Opt 2026, Infinity Machine 2026, RSIV-Harness 2026, VISTA 2026
In the same square
ADAS: Automated Design of Agentic Systems, AlphaEvolve, AREX-2, LM2LM, MLEvolve, ParetoRSI-Gym, PostTrainBench, Promptbreeder, Self-Refine, The AI Scientist