Many AI projects call themselves self-improving. Three questions separate them: what do they change about themselves, does the change outlast the run, and does the system get better at improving? 16 projects and papers, each placed by its own source.
● improves the improver◐ improves the task agent; no evidence the improver got better○ does not improve how it improves◌ not stated
The dashed corner is the deepest kind of change: its own weights or research process, handed on to the next version. Which entries count as RSI depends on the definition you pick above. Placement describes what each source says about itself; it is not a ranking.
Every entry, with the line that places it
2025-05-14 · Google DeepMind · project
AlphaEvolve
“an evolutionary coding agent powered by large language models for general-purpose algorithm discovery and optimization”
What it changes
Prompts, memory, context“These programs are evaluated by evaluators and stored in the programs database. This database implements an evolutionary algorithm that determines which programs will be used for future prompts.”
Does the change last
Gone when the run ends“This database implements an evolutionary algorithm that determines which programs will be used for future prompts.”
Does it improve the improver
does not improve how it improves“uses an evolutionary framework to improve upon the most promising ideas”
Who sets the goals
people set tasks and scoring“the user must provide a mechanism for automatically assessing generated solutions”
How it was tested
own benchmark numbers“it sped up this vital kernel in Gemini's architecture by 23%, leading to a 1% reduction in Gemini's training time”
AlphaEvolve improves algorithms, not itself. Inside its own system, the programs database that feeds its prompts is what changes. The blog says it helped train the models underlying AlphaEvolve itself; the number it gives is a 1% cut in training time, not a change to how AlphaEvolve improves.
2025-05-29 · Sakana AI, University of British Columbia, Vector Institute · paper
Darwin Gödel Machine
“We introduce the Darwin Gödel Machine (DGM), a self-improving system that iteratively modifies its own code (thereby also improving its ability to modify its own codebase) and empirically validates each change using coding benchmarks.”
What it changes
Tools, harness, its own code“a self-improving system that iteratively modifies its own code”
Does the change last
Becomes the next version“Only agents that compile successfully and retain the ability to edit a given codebase are added to the DGM archive, as only they can continue self-modification.”
Does it improve the improver
improves the improver“the DGM is a single system that both solves downstream tasks (i.e., coding problems) and refines its own implementation (i.e., its codebase), removing the need for a fixed, handcrafted meta-agent”
Who sets the goals
people set tasks and scoring“Each newly generated agent is quantitatively evaluated on a chosen coding benchmark to estimate its coding abilities.”
How it was tested
tested on held-out tasks“Since each agent was optimized without ever accessing the alternate benchmark, these evaluations represent truly held-out tests.”
The outer loop stays fixed: the paper says archive maintenance and parent selection are fixed and not modifiable by the DGM. The model weights are not changed.
2026-09-14 · University of Maryland, Google DeepMind, University of Virginia, and others · paper
Dream-RSI
“we introduce Dream-RSI , a framework for scalable, recursively self-improving meta-exploration in agent-driven discovery.”
What it changes
Tools, harness, its own code“We first make exploration programmable through a lightweight orchestration layer that controls branching, parallelism, and stopping”
Does the change last
Becomes the next version“The refined policy is redeployed for the next round of exploration.”
Does it improve the improver
improves the task agent; no evidence the improver got better“In the offline dreaming phase, a fixed agent iteratively revises the code for the exploration policy”
Who sets the goals
people set tasks and scoring“each node in the tree is an discovery attempt and is scored by a fixed evaluator”
How it was tested
own benchmark numbers“Across 9 tasks in 4 domains, Dream-RSI achieves competitive quality and improves discovery efficiency in several settings.”
The exploration policy is what improves. The paper says only the policy code changes; the models, evaluator and execution interfaces stay fixed. Measured set to self-reported: the six held-out datasets test the Lasso solver it discovered, not the improved policy on new tasks.
“Fibona Agent is a minimal, general-purpose, self-improving agent that writes its own code as it runs.”
What it changes
Tools, harness, its own code“The agent could then decide how each step works by writing its own harness code as it runs.”
Does the change last
Gone when the run ends“session changes are not automatically preserved across runs”
Does it improve the improver
improves the task agent; no evidence the improver got better“the smallest possible immutable core that can act and repair the agent”
Who sets the goals
people set tasks and scoring“The welcome screen waits for a task before any model call.”
How it was tested
demos only“Try the online demo in your browser.”
The line about runs is in the terminal bootstrap README, not the top-level README. The core that drives self-modification is immutable by design. No benchmark numbers in the README or tech report.
2024-10-06 · Peking University, UC Santa Barbara, University of Arizona · paper
Gödel Agent
“we introduce Gödel Agent, a self-evolving framework inspired by the Gödel machine, enabling agents to recursively improve themselves without relying on predefined routines or fixed optimization algorithms.”
What it changes
Tools, harness, its own code“Gödel Agent leverages LLMs to dynamically modify its own logic and behavior”
Does the change last
Gone when the run ends“It employs monkey patching to directly read and modify its own code in runtime memory”
Does it improve the improver
improves the improver“Furthermore, Gödel Agent enhances its optimization process by not only retrieving error messages but also using the error-trace library for more detailed analysis.”
Who sets the goals
people set tasks and scoring“We perform 6 independent self-improvement cycles on the validation dataset for each task”
How it was tested
tested on held-out tasks“After obtaining the optimized agent, we test it on the test set.”
Changes live in runtime memory. The paper tests the optimized agent afterwards but does not describe it being kept and improved further. The evidence that the optimizer itself improved is a Game of 24 case study.
2026-03-19 · FAIR at Meta, Meta Superintelligence Labs, University of British Columbia, and others · paper
Hyperagents (DGM-H)
“We introduce hyperagents, self-referential agents that integrate a task agent (which solves the target task) and a meta agent (which modifies itself and the task agent) into a single editable program.”
What it changes
Tools, harness, its own code“into a single editable program”
Does the change last
Becomes the next version“these meta-level improvements transfer across domains and accumulate across runs”
Does it improve the improver
improves the improver“Crucially, the meta-level modification procedure is itself editable, enabling metacognitive self-modification, improving not only the task-solving behavior, but also the mechanism that generates future improvements.”
Who sets the goals
people set tasks and scoring“For domains where we create AI judges to reflect human data (i.e., paper review and Olympiad-level math grading), we construct a validation subset”
How it was tested
tested on held-out tasks“This domain is reserved as a held-out meta-evaluation to test whether DGM-H's improvements to its self-improvement process transfer across domains and continue to compound over time.”
Extends the Darwin Gödel Machine so the meta agent is editable too. The paper compares against a variant whose meta agent stays fixed.
2026-06-04 · Shanghai Artificial Intelligence Laboratory, East China Normal University · paper
MLEvolve
“We present MLEvolve, an LLM-based self-evolving multi-agent framework for end-to-end machine learning algorithm discovery.”
What it changes
Prompts, memory, context“a dynamic global memory that automatically accumulates and retrieves historical experience during search”
Does the change last
Gone when the run ends“a dynamic global memory that automatically accumulates and retrieves historical experience during search”
Does it improve the improver
does not improve how it improves“gradually shifts the search from broad exploration to focused exploitation with an entropy-inspired progressive schedule”
Who sets the goals
people set tasks and scoring“MLE-Bench comprises 75 carefully curated Kaggle competitions”
How it was tested
own benchmark numbers“MLEvolve achieves a 65.3% average medal rate on MLE-Bench under a 12-hour budget”
Self-evolving here means memory and search state that grow during one task's search. The abstract gives no number for the AlphaEvolve comparison.
2026-03-09 · ELLIS Institute Tübingen, MPI-IS, Tübingen AI Center, University of Tübingen, Thoughtful Lab · paper
PostTrainBench
“We introduce PostTrainBench to benchmark how well LLM agents can perform post-training autonomously under bounded compute constraints (10 hours on one H100 GPU).”
What it changes
Prompts, memory, context“The model processes context, generates plans, and decides which tools to invoke.”
Does the change last
Gone when the run ends“An agent receives a base LLM, target benchmark, and 10 hours on one H100 GPU, then post-trains the model to maximize performance.”
Does it improve the improver
does not improve how it improves“We ask frontier agents (e.g., Claude Code with Opus 4.6) to optimize the performance of a base LLM on a particular benchmark”
Who sets the goals
people set tasks and scoring“An agent receives a base LLM, target benchmark, and 10 hours on one H100 GPU, then post-trains the model to maximize performance.”
How it was tested
own benchmark numbers“23.2% for the best agent vs. 51.1% for official instruction-tuned models”
A benchmark. The agents train a separate small base model, not themselves, so on the changes axis only the agent's working context changes. Measured set to self-reported, not heldout: the target benchmark is the thing the agent optimizes. Agents sometimes trained on the test set; an LLM judge flags such runs.
“we introduce Recursive Harness Self-Improvement (RHI), which represents the harness as a prompt-level specification of the agent loop and iteratively refines it using pairwise feedback over its own revision history.”
What it changes
Prompts, memory, context“which represents the harness as a prompt-level specification of the agent loop”
Does the change last
Saved for later runs“the prompt-represented harness is rewritten from self-comparison history and reused in later executions”
Does it improve the improver
improves the task agent; no evidence the improver got better“the base model, evaluator, and harness optimizer are fixed”
Who sets the goals
people set tasks and scoring“Each task requires generating a complete code repository with standardized deliverables, and outputs are evaluated using pairwise LLM-as-a-judge comparisons.”
How it was tested
own benchmark numbers“Across 30 synthetic machine-learning research tasks spanning quantitative finance, robotics, and pharmacy, a few RHI iterations suffice to substantially raise the performance ceiling of low-reasoning-effort agents”
The harness here is a prompt, so it sits at context rather than scaffold. Harnesses are optimized per task and scored on those tasks. All six authors are also authors of Sakana MASS.
2026-09-21 · Google Cloud AI Research, Stanford University, Washington University in St. Louis, UNC-Chapel Hill · paper
RRSI (Regularized Recursive Self-Improvement)
“We introduce Regularized Recursive Self-Improvement of Agent Harnesses (RRSI), which incorporates the principles of regularizations into harness self-improvement by constraining the evolution candidate proposal and selection.”
What it changes
Tools, harness, its own code“Prompts, control flow, configuration, context management, tools, skills, memory and sub-agents may all be modified”
Does the change last
Saved for later runs“accepting one fast-forwards the branch, so the incumbent is always a commit”
Does it improve the improver
improves the task agent; no evidence the improver got better“The proposer, the analyst that writes the cross-round failure feedback and the leakage critic are all Claude Opus 4.8.”
Who sets the goals
people set tasks and scoring“In each domain the harness is evolved on a single suite”
How it was tested
tested on held-out tasks“In each domain the harness is evolved on a single suite, and is then run unchanged on held-out benchmarks.”
The harness around a frozen model is what changes. The paper does not describe the proposer, analyst or critic being edited by the loop. Persistence set to saved: accepted harnesses are kept as commits, and the system that edits them stays the same.
“We introduce Multi-Agent Self-Supervision (MASS). One shared model solves tasks through a team of virtual subagents, searches for better multi-agent workflows, then uses its own judgments to select the best ones.”
What it changes
Its model weights“Fine-tune the shared model with LoRA”
Does the change last
Becomes the next version“The updated model then resumes all three roles.”
Does it improve the improver
improves the improver“We train the model only on task-solving trajectories and observe that the capabilities of the workflow optimizer and workspace evaluator also improve.”
Who sets the goals
people set the aim, the system picks tasks“only a self-evaluation signal (whose correctness is unknown) guides the overall learning loop”
How it was tested
tested on held-out tasks“three tasks held out from post-training”
Two cycles from a 27B open-weights model. The model judges its own workflows and training data; external judges are used only to measure. The evidence that the optimizer role improved is a workflow-transfer comparison: the base model running first-round workflows wins 64% against base-search workflows. On public benchmarks, score per output token was 0.96x on Terminal-Bench 2.0 and 0.94x on SWE-bench Verified, so transfer is uneven by Sakana's own account.
2026-08-19 · University of Washington, Stanford University, Northeastern University, Carnegie Mellon University, and others · paper
SPADE
“We introduce SPADE (Self-Play in Adaptive Synthetic Executable Environments), a self-play RL framework in which a single LLM plays two roles”
What it changes
Its model weights“so updates for either role affect the same policy”
Does the change last
Becomes the next version“alternates between generating executable training environments and learning to solve them”
Does it improve the improver
improves the task agent; no evidence the improver got better“a Reasoning Agent that learns to act in them”
Who sets the goals
people set the aim, the system picks tasks“alternates between generating executable training environments and learning to solve them”
How it was tested
tested on held-out tasks“SPADE improves over the strongest fixed-environment baseline by +5.3 on average across eight held-out math, science, code, and reasoning benchmarks”
The same model writes its own training environments and is trained on them, so the environment designer is also updated. Recursion set to task, not improver: the paper says each ablation control changes more than one factor, and the one that removes designer training also removes memory.
2023-10-03 · Microsoft Research, Stanford University, OpenAI · paper
STOP: Self-Taught Optimizer
“In this work, we use a language-model-infused scaffolding program to improve itself.”
What it changes
Tools, harness, its own code“we use a language-model-infused scaffolding program to improve itself”
Does the change last
Becomes the next version“This is iterated for a prespecified number of iterations T, per available resources.”
Does it improve the improver
improves the improver“the resulting improved improver generates programs with significantly better performance than its seed improver”
Who sets the goals
people set tasks and scoring“improves an input program according to a given utility function”
How it was tested
tested on held-out tasks“we find the improved improver, detailed in Appendix H, outperforms the seed improver on each new downstream task without further optimization”
The authors say this is not full recursive self-improvement because the language models are not altered. With GPT-3.5 and Mixtral, performance degraded.
“we introduce Tev-Gym, the first long-horizon agent training dataset with verifiable, dense, progressive rewards -- 1,170 verified task environments across 7 domains.”
What it changes
Its model weights“Training with this recipe yields Tev-27B”
Does the change last
Saved for later runs“We introduce Tev-9B and Tev-27B, trained with PPRS on the unit tier and the full corpus of Tev-Gym, respectively.”
Does it improve the improver
does not improve how it improves“We propose latent-world-first synthesis, a pipeline that constructs long-horizon agentic tasks backward from a known-correct world”
Who sets the goals
people set tasks and scoring“via progress-potential reward shaping (PPRS), we convert progress into a dense per-step reward”
How it was tested
tested on held-out tasks“Despite training only on ALE-related data, it generalizes to the Terminal-Bench (TB) 3.0 and 4.0 subsets”
A building block, not a self-improving system: a fixed synthesis pipeline builds environments and a model is trained on them once. The paper names RSI as motivation.
2023-05-25 · NVIDIA, Caltech, UT Austin, Stanford, UW Madison · paper
Voyager
“We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention.”
What it changes
Tools, harness, its own code“Voyager incrementally builds a skill library by storing the action programs that help solve a task successfully.”
Does the change last
Saved for later runs“Voyager is able to utilize the learned skill library in a new Minecraft world to solve novel tasks from scratch”
Does it improve the improver
improves the task agent; no evidence the improver got better“Voyager interacts with GPT-4 via blackbox queries, which bypasses the need for model parameter fine-tuning.”
Who sets the goals
people set the aim, the system picks tasks“The curriculum is generated by GPT-4 based on the overarching goal of "discovering as many diverse things as possible".”
How it was tested
tested on held-out tasks“Voyager is able to utilize the learned skill library in a new Minecraft world to solve novel tasks from scratch, while other techniques struggle to generalize.”
What grows is a library of skill programs. GPT-4 is queried as a black box and not fine-tuned. The curriculum is generated by GPT-4 from an overarching goal the authors set.
“We present AIDE^2, a system that implements this loop for a frontier AI research agent.”
What it changes
Tools, harness, its own code“It proposes changes to its own code, benchmarks modified versions of itself on a suite of AI R&D tasks, and keeps the changes that perform best on hidden evaluations.”
Does the change last
Becomes the next version“each accepted rewrite becomes the agent that the next round edits”
Does it improve the improver
improves the task agent; no evidence the improver got better“we do not think this is strong enough evidence of ignition, given that AIDE 47 is not asymptotically better”
Who sets the goals
people set tasks and scoring“the candidate is graded by running it as an optimizer on AI R&D tasks”
How it was tested
tested on held-out tasks“These gains generalize to four held-out benchmarks spanning machine learning engineering, heuristic algorithm engineering, and physics-based weather forecasting”
Date is the blog post; the arXiv paper followed on 2026-09-22. The two loops run different agents: the outer loop, which proposes rewrites, runs Weco's hand-tuned research agent. Weco places AIDE² on Level 1 of its own ladder and says the ignition test does not yet show Level 2.