# AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement

arXiv: https://arxiv.org/abs/2610.18083 · HTML: https://mlsanity.com/paper/2610.18083/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Self-evolving LLM agents, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 23 of 23)

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [More Agents Is All You Need](https://mlsanity.com/paper/2402.05120/) (2024)
- [RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts](https://mlsanity.com/paper/2411.15114/) (2024)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems](https://mlsanity.com/paper/2506.07398/) (2025)
- [Toward Generalist Autonomous Research via Hypothesis-Tree Refinement](https://mlsanity.com/paper/2606.11926/) (2026)
- [Dream-RSI: Recursive Self-Improvement through Evolving Worlds](https://mlsanity.com/paper/2609.14858/) (2026)
- [EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery](https://mlsanity.com/paper/2606.13662/) (2026)
- [The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams](https://mlsanity.com/paper/2608.23541/) (2026)
- [A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms](https://mlsanity.com/paper/2609.04170/) (2026)
- [Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development](https://mlsanity.com/paper/2608.13417/) (2026)
- [Exploit More, Explore Smarter for Budget-Constrained Agentic Search](https://mlsanity.com/paper/2608.23848/) (2026)
- [ττ-Bench: An Environment for End-To-End, Realistic Agent Construction](https://mlsanity.com/paper/2609.04611/) (2026)
- [Remember, Don't Re-read: Stateful ReAct Agents for Token-Efficient Autonomous Experimentation](https://mlsanity.com/paper/2606.14945/) (2026)
- [AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research](https://mlsanity.com/paper/2608.11216/) (2026)
- [Harnessing agent memory to build lifelong AI partners for materials scientists](https://mlsanity.com/paper/2608.11224/) (2026)
- [BusMA: A Bus Communication Substrate for Multi-Agent Systems](https://mlsanity.com/paper/2609.15054/) (2026)

## Abstract (arXiv)

Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively, more researcher agents can explore more hypotheses, but early evaluation scores might misrepresent their promise, shared findings could lose their applicability conditions, and useful procedures could remain confined to completed investigations. In this paper, we present AReaL-RSI, a framework for organizing a persistent research team of agents without updating backbone LLM weights. We formulate the scaling problem in terms of evaluated outcomes and whole-system resource expenditure. Concretely, a leader agent selects task-appropriate research orientations and guides ongoing investigations; conditional memory sharing distinguishes unresolved problems from supported findings and enables recipient adaptation. During recursive evolution, after each campaign, evidence-based review revises researcher orientation, knowledge, and skills for later campaigns. Experiments compare AReaL-RSI with Codex-Goal on downstream harness optimization, GPU kernel optimization, and AI research tasks using two backbones. Under the reported resource allocations, AReaL-RSI improves Terminal Bench performance by 2.2 percentage points for each backbone and increases mean KernelBench speedup by 32.2-36.8%; further scalability comparisons favor the design of AReaL-RSI over native scaling: combining experience sharing with specialized researcher roles yields 1.9-27.5% lower kernel latency than independent exploration and 1.3-33.9% lower latency than sharing alone across all seven comparable task-backbone pairs.