🛰️ Daily AI Frontier
‹ back to 2026-08-04

Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training

Research Efficiency & Systems

Ranking

Overall 74
Content 80
Popularity 61

Observed public metrics from 1 member.

Merged summary

TL;DR - CoPES is a cooperative coevolutionary evolution-strategy method that splits an LLM's parameter space into lower-dimensional subspaces to make backprop-free, full-parameter post-training of tool-using agents practical on just a few GPUs. It matters because it narrows the memory-vs-training-time gap that has made ES impractical versus gradient-based RL in resource-constrained settings.

  • Motivation: tool-using agents generate long multi-turn trajectories, making gradient-based post-training memory-heavy; ES avoids backpropagation but demands prohibitive GPU-hours on small clusters.
  • Method: Cooperative Parameter-subspace Evolution Strategy (CoPES) decomposes the full parameter space into lower-dimensional subspaces and searches them cooperatively to improve optimization efficiency.
  • Results: post-training a Qwen3.5-4B math agent, under the GPU-hour budget of full-parameter GRPO's best validation checkpoint, CoPES recovers 92% of GRPO's validation-accuracy gain vs. 67% for standard ES, with theoretical GPU memory under one-eighth of full-parameter GRPO.
  • Generality: beats standard ES and LoRA-based GRPO on all pass@k metrics across five benchmarks, with additional gains shown on a question-answering task; code is open-sourced.

Sources (1)

Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training

arXiv cs.AI Zhiyuan Wang, Shengcai Liu, Jiahao Wu, Ning Lu, Hui Ouyang, Shaofeng Zhang, Haoze Lv, Ke Tang 2026-08-03 arXiv:2608.02391
Public signals Hugging Face upvotes 3
Providers: Hugging Face · Upvotes 3 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-03 14:33:24.404087 UTC

TL;DR - CoPES is a cooperative coevolutionary evolution-strategy method that splits an LLM's parameter space into lower-dimensional subspaces to make backprop-free, full-parameter post-training of tool-using agents practical on just a few GPUs. It matters because it narrows the memory-vs-training-time gap that has made ES impractical versus gradient-based RL in resource-constrained settings.

  • Motivation: tool-using agents generate long multi-turn trajectories, making gradient-based post-training memory-heavy; ES avoids backpropagation but demands prohibitive GPU-hours on small clusters.
  • Method: Cooperative Parameter-subspace Evolution Strategy (CoPES) decomposes the full parameter space into lower-dimensional subspaces and searches them cooperatively to improve optimization efficiency.
  • Results: post-training a Qwen3.5-4B math agent, under the GPU-hour budget of full-parameter GRPO's best validation checkpoint, CoPES recovers 92% of GRPO's validation-accuracy gain vs. 67% for standard ES, with theoretical GPU memory under one-eighth of full-parameter GRPO.
  • Generality: beats standard ES and LoRA-based GRPO on all pass@k metrics across five benchmarks, with additional gains shown on a question-answering task; code is open-sourced.
item →