AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910161385291776 |
|---|---|
| author | Ray, Pretam Brahma, Pratik Prabhanjan Liu, Zicheng Barsoum, Emad |
| author_facet | Ray, Pretam Brahma, Pratik Prabhanjan Liu, Zicheng Barsoum, Emad |
| contents | Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large language models (LLMs) during inference. This setting raises a central question: how can an agent dynamically select an LLM that is sufficiently capable for the current generation step while remaining computationally efficient? While model cascades offer a practical mechanism for balancing this trade-off, existing routing strategies typically rely on static heuristics or external controllers and do not explicitly account for model uncertainty. We introduce AdaptEvolve: Adaptive LLM Selection for Multi-LLM Evolutionary Refinement within an evolutionary sequential refinement framework that leverages intrinsic generation confidence to estimate real-time solvability. Empirical results show that confidence-driven selection yields a favourable Pareto frontier, reducing total inference cost by an average of 37.9% across benchmarks while retaining 97.5% of the upper-bound accuracy of static large-model baselines. Our code is available at https://github.com/raypretam/adaptive_llm_selection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11931 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection Ray, Pretam Brahma, Pratik Prabhanjan Liu, Zicheng Barsoum, Emad Computation and Language Artificial Intelligence Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large language models (LLMs) during inference. This setting raises a central question: how can an agent dynamically select an LLM that is sufficiently capable for the current generation step while remaining computationally efficient? While model cascades offer a practical mechanism for balancing this trade-off, existing routing strategies typically rely on static heuristics or external controllers and do not explicitly account for model uncertainty. We introduce AdaptEvolve: Adaptive LLM Selection for Multi-LLM Evolutionary Refinement within an evolutionary sequential refinement framework that leverages intrinsic generation confidence to estimate real-time solvability. Empirical results show that confidence-driven selection yields a favourable Pareto frontier, reducing total inference cost by an average of 37.9% across benchmarks while retaining 97.5% of the upper-bound accuracy of static large-model baselines. Our code is available at https://github.com/raypretam/adaptive_llm_selection. |
| title | AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2602.11931 |