NeurIPS 2026In-context learning & prompting Huawei Technologies Ltd.National University of Singapore

SePO: Self-Evolving Prompt Agent for System Prompt Optimization

SePO evolves its own prompt agent's system prompt via self-referential open-ended search to optimize task agents, outperforming baselines by 4.49 points across five benchmarks.

Wangcheng Tao, Han Wu, Weng-Fai Wong

Published 2026Sydney Poster Session 5 · Thu, Dec 10, 10:00 AM–1:00 PM local time · Hall 1-4▲ 7 on Hugging Face arXiv ↗OpenReview ↗

83%

OverallMust read

OverallMust readVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.

Readers

–

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel13/20reviewers recommend it

lenient 4/5

medium 7/10

strict 2/5

AI panel?Vote to see what the 20 AI reviewers said

Abstract

System prompt optimization improves agent behavior without modifying the underlying model, yielding human-readable, model-agnostic instructions. Existing methods build a prompt agent that refines task agents' system prompts, yet leave the prompt agent's own system prompt hand-engineered and fixed. We propose Self-Evolving Prompt Optimization (SePO), which treats the prompt agent's own system prompt as an optimization target alongside task agents' system prompts. SePO adopts a self-referential design. A single prompt agent improves both task agents' system prompts and its own under an open-ended evolutionary search that maintains an archive of candidate prompts as stepping stones. Training proceeds in two stages: pre-training evolves the prompt agent on a multi-task pool, and fine-tuning then applies it to a target task. Across five benchmarks spanning math (AIME'25), abstract reasoning (ARC-AGI-1), graduate-level science (GPQA), code generation (MBPP), and logic puzzles (Sudoku), SePO consistently outperforms Manual-CoT, TextGrad, and MetaSPO, improving the average accuracy by 4.49 points compared to Manual-CoT. The prompt optimization skill from pre-training also generalizes to tasks beyond the pre-training mixture, rather than memorizing per-task prompts.