# Don't Gamble, GAMBLe: An Analytical Framework for AI-Driven Research Systems

arXiv: https://arxiv.org/abs/2606.02863 · HTML: https://mlsanity.com/paper/2606.02863/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 12 of 12)

- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization](https://mlsanity.com/paper/2602.20133/) (2026)
- [Barbarians at the Gate: How AI is Upending Systems Research](https://mlsanity.com/paper/2510.06189/) (2025)
- [CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery](https://mlsanity.com/paper/2604.01658/) (2026)
- [Glia: A Human-Inspired AI for Automated Systems Design and Optimization](https://mlsanity.com/paper/2510.27176/) (2025)
- [Networks of Networks: Complexity Class Principles Applied to Compound AI Systems Design](https://mlsanity.com/paper/2407.16831/) (2024)
- [Improving Coherence and Persistence in Agentic AI for System Optimization](https://mlsanity.com/paper/2603.21321/) (2026)
- [Agentic Systems as Boosting Weak Reasoning Models](https://mlsanity.com/paper/2605.14163/) (2026)

## Built on by (most cited first, 2 of 2)

- [Evolution or Illusion? Rethinking Evaluation in LLM Evolutionary Search](https://mlsanity.com/paper/2609.19799/) (2026)
- [ROAR: Unifying Runs across Heterogeneous AI-Driven Research Systems](https://mlsanity.com/paper/2610.03966/) (2026)

## Abstract (arXiv)

AI-Driven Research Systems (ADRS) -- systems coupling LLMs with automated evaluation to discover algorithms, proofs, and designs -- are being optimized and adopted across domains, but the tools to analyze them have not kept pace. ADRS performance depends on component interactions that are poorly understood, expensive to explore, and (as we show) not well captured by standard convergence guarantees. These guarantees rely on structural assumptions that do not hold under the ADRS process we formalize. We introduce GAMBLe, a framework that decomposes ADRS behavior into four parameters (generator G, assessor A, discovery mechanism M, budget B) and one compositional object, the effective landscape Leff = A circ G, which reveals that distinct generator-assessor pairs induce structurally different per-problem optimization landscapes. We exercise the framework on 760+ replicated runs (>46,000 iterations) spanning generators from single LLMs to dynamically-adaptive ensembles, mechanisms from greedy selection to co-evolutionary meta-search, and three NP-hard problems whose assessors range from continuous scoring to cliff functions. The experiments reveal no total ordering of generators or mechanisms: frontier models can underperform open-source alternatives and the simplest mechanism sometimes outperforms state-of-the-art meta-search. Results show that even under limited budgets (60 iterations per run), the right component choices can improve performance by 13-67% and search efficiency by 6-39x.