# Competing at Every Price Point with Agentic Evolution over a Menu of LLMs

arXiv: https://arxiv.org/abs/2608.16207 · HTML: https://mlsanity.com/paper/2608.16207/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 38 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 29 of 29)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models](https://mlsanity.com/paper/2201.03544/) (2022)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation](https://mlsanity.com/paper/2310.02304/) (2023)
- [The Semantic Scholar Open Data Platform](https://mlsanity.com/paper/2301.10140/) (2023)
- [Self-Harness: Harnesses That Improve Themselves](https://mlsanity.com/paper/2606.09498/) (2026)
- [AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite](https://mlsanity.com/paper/2510.21652/) (2025)
- [EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery](https://mlsanity.com/paper/2603.08127/) (2026)
- [Rethinking the Evaluation of Harness Evolution for Agents](https://mlsanity.com/paper/2607.12227/) (2026)
- [Optimizing Model Selection for Compound AI Systems](https://mlsanity.com/paper/2502.14815/) (2025)
- [Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems](https://mlsanity.com/paper/2502.04510/) (2025)
- [HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems](https://mlsanity.com/paper/2606.01779/) (2026)
- [HARBOR: Automated Harness Optimization](https://mlsanity.com/paper/2604.20938/) (2026)
- [Conformal Constrained Policy Optimization for Cost-Effective LLM Agents](https://mlsanity.com/paper/2511.11828/) (2025)
- [BAMAS: Structuring Budget-Aware Multi-Agent Systems](https://mlsanity.com/paper/2511.21572/) (2025)
- [syftr: Pareto-Optimal Generative AI](https://mlsanity.com/paper/2505.20266/) (2025)
- [RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgets](https://mlsanity.com/paper/2604.04347/) (2026)

## Abstract (arXiv)

Consider a firm that surveys its competition for a particular agentic task and seeks to offer superior accuracy at every price point. A firm that Pareto-dominated its competitors would leave no rational customer a reason to buy elsewhere. This paper shows a path to this kind of capability by evolving multi-LLM Python agents from training pools of at most 100 examples. Given a priced menu of nine LLM endpoints; brief documentation of the task, objective, and API; a simple seed agent; and an operator-chosen per-problem cost target--usually set at an incumbent's own price--RoboPhD, an evolutionary meta-agent, evolves complete agent programs that attack the public frontiers of two semantically dissimilar tasks point by point: DS-1000 (execution-checked code generation) and PaperFindingBench (LLM-judged scientific document retrieval). On public leaderboards for each task, the evolved agents hold every Pareto-frontier slot but one, including Pareto domination of both the top-scoring and the lowest-cost competing points.