SCOPE: Prompt Evolution for Enhancing Agent Effectiveness
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911725717028864 |
|---|---|
| author | Pei, Zehua Zhen, Hui-Ling Kai, Shixiong Pan, Sinno Jialin Wang, Yunhe Yuan, Mingxuan Yu, Bei |
| author_facet | Pei, Zehua Zhen, Hui-Ling Kai, Shixiong Pan, Sinno Jialin Wang, Yunhe Yuan, Mingxuan Yu, Bei |
| contents | Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts. However, a critical bottleneck remains: while agents have access to this context, their static prompts lack the mechanisms to manage it effectively, leading to recurring Corrective and Enhancement failures. To address this capability gap, we introduce Self-evolving Context Optimization via Prompt Evolution (SCOPE). SCOPE frames context management as an \textit{online optimization} problem, synthesizing guidelines from execution traces to automatically evolve the agent's prompt. We propose a Dual-Stream mechanism that routes guidelines between tactical memory (immediate error correction) and strategic memory, which is continuously refined through conflict resolution, subsumption pruning, and consolidation. To maximize strategy coverage, Perspective-Driven Exploration evolves multiple parallel prompts guided by distinct optimization perspectives. Experiments on the HLE benchmark show that SCOPE improves task success rates from 14.23\% to 38.64\% without human intervention. We make our code publicly available at https://github.com/JarvisPei/SCOPE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_15374 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCOPE: Prompt Evolution for Enhancing Agent Effectiveness Pei, Zehua Zhen, Hui-Ling Kai, Shixiong Pan, Sinno Jialin Wang, Yunhe Yuan, Mingxuan Yu, Bei Artificial Intelligence Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts. However, a critical bottleneck remains: while agents have access to this context, their static prompts lack the mechanisms to manage it effectively, leading to recurring Corrective and Enhancement failures. To address this capability gap, we introduce Self-evolving Context Optimization via Prompt Evolution (SCOPE). SCOPE frames context management as an \textit{online optimization} problem, synthesizing guidelines from execution traces to automatically evolve the agent's prompt. We propose a Dual-Stream mechanism that routes guidelines between tactical memory (immediate error correction) and strategic memory, which is continuously refined through conflict resolution, subsumption pruning, and consolidation. To maximize strategy coverage, Perspective-Driven Exploration evolves multiple parallel prompts guided by distinct optimization perspectives. Experiments on the HLE benchmark show that SCOPE improves task success rates from 14.23\% to 38.64\% without human intervention. We make our code publicly available at https://github.com/JarvisPei/SCOPE. |
| title | SCOPE: Prompt Evolution for Enhancing Agent Effectiveness |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2512.15374 |