Self-improving AI / SPADE
SPADE
“We introduce SPADE (Self-Play in Adaptive Synthetic Executable Environments), a self-play RL framework in which a single LLM plays two roles”
SPADE 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
- Its model weights“so updates for either role affect the same policy”
- Does the change last
- Becomes the next version“Both rewards update the shared policy via GRPO.”
- 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.
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)): does not count
- Autonomous (Anthropic, When AI builds itself): does not count
How it got here
Earlier work in this catalog that SPADE cites, oldest first. Under each: where that work sits on the map, then where SPADE sits (changes in bold), and what SPADE's own paper says about it. Its whole family on the citation map
2023 Reflexion sets itself apart
Prompts, memory → Model weights · gone when the run ends → becomes the next version · does not improve the improver → improves the task agent
“Harness engineering improves how an agent acts within a given environment at inference time, through tool orchestration and self-correction (Yao et al., 2023; Shinn et al., 2023), but it changes no weights, so its gains are tied to each hand-built harness, rather than improving general capabilities the model carries to new tasks.”
2026 Hyperagents builds on it
Tools, own code → Model weights · becomes the next version · improves the improver → improves the task agent
“HyperAgents (Zhang et al., 2026a) extends self-referential code evolution by fusing the task-solver and the meta-improver into a single editable program, so the self-modification mechanism is itself modifiable; tasks are externally fixed and the foundation model is frozen.”
“HyperAgents explicitly leaves co-evolving the task distribution as future work, which SPADE addresses directly.”
2026 SPADE
Model weights · becomes the next version · improves the task agent
Also cites Self-Rewarding Language Models 2024
In the same square
CoEvo-RSI, ECG-RSI, MTA-Zero, R²Orch, Sakana MASS (Multi-Agent Self-Supervision), Self-HPO, Self-Rewarding Language Models, STaR: Self-Taught Reasoner, Terminal-RSI