Self-improving AI / Hyperagents (DGM-H)
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.”
Hyperagents (DGM-H) 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
- Tools, harness, its own code“into a single editable program”
- Does the change last
- Becomes the next version“selected parent hyperagents from the archive generate modified versions of themselves”
- 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.
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)): counts
- Durable (Ren et al., self-improvement survey (2026)): counts
- Strict (Roman Yampolskiy, From Seed AI to Technological Singularity (2015)): counts
- Autonomous (Anthropic, When AI builds itself): does not count
How it got here
Earlier work in this catalog that Hyperagents cites, oldest first. Under each: where that work sits on the map, then where Hyperagents sits (changes in bold), and what Hyperagents' own paper says about it. Its whole family on the citation map
2003 Schmidhuber, the Gödel machine sets itself apart
A definition: the Gödel machine
“One prominent example is the Gödel Machine (Schmidhuber, 2003), which proposes agents that rewrite themselves when provably beneficial, though such approaches remain impractical in real-world settings.”
2024 ADAS uses it
Prompts, memory → Tools, own code · gone when the run ends → becomes the next version · does not improve the improver → improves the improver
“This baseline replicates the approach of (Hu et al., 2025, ADAS,) in this setting.”
2025 Darwin Gödel Machine builds on it
Tools, own code · becomes the next version · improves the improver
“The DGM-Hyperagents (DGM-H) extends the Darwin Gödel Machine (DGM) (Zhang et al., 2025b) beyond coding tasks, enabling agents to improve not only their task performance but also their ability to improve themselves, across any computable task.”
“The Darwin Gödel Machine (DGM) (Zhang et al., 2025b) demonstrates that open-ended self-improvement is achievable in coding.”
2026 Hyperagents
Tools, own code · becomes the next version · improves the improver
Also cites Good, the intelligence explosion 1965, STaR 2022, Voyager 2023, Promptbreeder 2023, STOP 2023, The AI Scientist 2024, Gödel Agent 2024, SICA 2025, AlphaEvolve 2025
Cited by Weco, levels of recursive self-improvement 2026, Weco AIDE² 2026, SPADE 2026, Dream-RSI 2026, RRSI 2026, Fibona Agent 2026, Harness² 2026, ECG-RSI 2026, R²Orch 2026, Self-HPO 2026, Organon 2026, CoEvo-RSI 2026, ParetoRSI-Gym 2026, Pu, recursive self-improvement 2026, Skill∞ 2026, Infinity Machine 2026
In the same square
Darwin Gödel Machine, Dream-RSI, Infinity Machine, RSI-Opt, SICA: A Self-Improving Coding Agent, Skill∞, STOP: Self-Taught Optimizer, VISTA, Weco AIDE²