跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 26 天前AI 評分41

GEPA-Curator:以策展式學習提升自我改進智能體

GEPA-Curator: Curated Learning for Self Improving Agents

AI 導讀

GEPA-Curator透過篩除不可靠的失敗訊號及檢索過往成功經驗,改善智能體的提示詞優化。框架包含任務策展和過往成功軌跡檢索,並在 GoBrowse、ALFWorld、AppWorld 和 τ-bench 上,以 Gemini 3.1 Pro 和 Claude Opus 5 作為優化模型進行評估。

正文

Published on Oct 27

Authors:

,

,

,

,

,

,

,

,

,

Abstract

GEPA-Curator improves agentic prompt optimization by filtering unreliable failure signals and retrieving past successes, boosting performance across multiple benchmarks.

Large Language Models (LLMs) are increasingly used in multi-turn agentic workloads that require sustained interaction with complex environments. Existing reflective prompt optimizers such as GEPA learn from failed rollouts, but agentic failures can also come from prompt weaknesses, harness limitations, stochastic execution, or noisy judges. We argue that such failures may not provide useful learning signal, and may even be harmful; and thus it is essential to curate which tasks are provided to the prompt optimizer for better performance. We introduce GEPA-Curator, a framework that augments the prompt optimizer to select which agent experiences should shape prompt optimization. In particular, GEPA-Curator consists of two components: task curation, which filters out tasks that are likely to provide noisy or unreliable learning signals, and prior success retrieval, which selectively retrieves past successful trajectories for a task and provides them as additional context to the prompt optimizer. We evaluate GEPA-Curator on GoBrowse, ALFWorld, AppWorld, and τ-bench, using both Gemini 3.1 Pro and Claude Opus 5 as optimizer models. GEPA-Curator matches or exceeds the mean performance of both baselines, with gains of up to 20.7% over GEPA and 21.2% over ACE.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.37651

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.37651 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.37651 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.37651 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co