SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration

2026-06-17 · Ziyi Zhu, Luka Smyth, Saki Shinoda, Jinghong Chen arxiv

Context engineering has emerged as a primary lever for improving AI systems without parameter updates. Recent work showing that textual gradients do not function as real gradients motivates treating automatic prompt optimization (APO) as black-box search. We introduce SPO (Stochastic Prompt Optimization), a framework for stochastic search over prompt space, and compare three strategies of increasing sophistication: error-informed random search, a genetic algorithm with evolutionary operators, and SAGE (SPO via Agent-Guided Exploration), a multi-agent pipeline with diagnostic code execution. Across three benchmarks, no single strategy dominates; effectiveness depends on the interaction of landscape structure with error type. We further deploy SAGE on a mental-health chatbot under a continuous optimization paradigm, where it compounds eight cycles of individually-noisy A/B tests into a statistically robust gain in next-day retention. We argue that coupling qualitative diagnosis with quantitative validation is what makes agentic optimization effective for open-ended task-oriented dialogue.

📄 PDF Abstract BibTeX arXiv:2606.18902

Code (0)

등록된 구현이 없습니다.

RSAgent: Learning to Reason and Act for Text-Guided Segmentation via Multi-Turn Tool Invocations

2025-12-30 · Xingqi He, Yujie Zhang, Shuyong Gao, Wenjie Li 외 arxiv

Text-guided object segmentation requires both cross-modal reasoning and pixel grounding abilities. Most recent methods treat text-guided segmentation as one-shot grounding, where the model predicts pixel prompts in a sin…

Reinforcement Learning Object Segmentation

Environment-Grounded Automated Prompt Optimization for LLM Game Agents

2026-06-16 · Rean Clive Fernandes, Lukas Fehring, Theresa Eimer, Marius Lindauer 외 arxiv

LLM agents in interactive environments are highly sensitive to their prompts, yet prompt engineering remains a manual, task-specific process. We introduce an automated prompt optimization framework for LLM agents that de…

Prompt Engineering

POLCA: Stochastic Generative Optimization with LLM

2026-03-16 · Xuanfei Ren, Allen Nie, Tengyang Xie, Ching-An Cheng arxiv

Optimizing complex systems, ranging from LLM prompts to multi-turn agents, traditionally requires labor-intensive manual iteration. We formalize this challenge as a stochastic generative optimization problem where a gene…

Code Translation

FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents

2025-10-03 · Imene Kerboua, Sahar Omidi Shayegan, Megh Thakkar, Xing Han Lù 외 arxiv

Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens of thousands of tokens. This saturates context limits and increases comp…

Error Taxonomy-Guided Prompt Optimization

2026-02-01 · Mayank Singh, Vikas Yadav, Eduardo Blanco arxiv

Automatic Prompt Optimization (APO) is a powerful approach for extracting performance from large language models without modifying their weights. Many existing methods rely on trial-and-error, testing different prompts o…

Question Answering Logical Reasoning