Self-improving AI / Recursive Harness Self-Improvement (RHI)
Recursive Harness Self-Improvement (RHI)
“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.”
Recursive Harness Self-Improvement (RHI) 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“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.
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 Recursive Harness Self-Improvement cites, oldest first. Under each: where that work sits on the map, then where Recursive Harness Self-Improvement sits (changes in bold), and what Recursive Harness Self-Improvement's own paper says about it. Its whole family on the citation map
Cites STaR 2022, Reflexion 2023, Self-Refine 2023, Voyager 2023, STOP 2023, Self-Rewarding Language Models 2024, ADAS 2024, AlphaEvolve 2025, Darwin Gödel Machine 2025
Cited by RRSI 2026, Harness² 2026, Organon 2026, CoEvo-RSI 2026