paper-with-me

홈 › Papers

SCOPE: Prompt Evolution for Enhancing Agent Effectiveness

2025-12-17 · Zehua Pei, Hui-Ling Zhen, Shixiong Kai, Sinno Jialin Pan, Yunhe Wang, Mingxuan Yuan, Bei Yu arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.15374

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering

2025-10-22 · Marianne Menglin Liu, Daniel Garcia, Fjona Parllaku, Vikas Upadhyay 외 arxiv

Large language model (LLM) agents rely on external tools to solve complex tasks, but real-world toolsets often contain redundant tools with overlapping names and descriptions, introducing ambiguity and reducing selection…

AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

2025-08-22 · Dawei Gao, Zitao Li, Yuexiang Xie, Weirui Kuang 외 arxiv

Driven by rapid advancements of Large Language Models (LLMs), agents are empowered to combine intrinsic knowledge with dynamic tool use, greatly enhancing their capacity to address real-world tasks. In line with such an …

MulVul: Retrieval-augmented Multi-Agent Code Vulnerability Detection via Cross-Model Prompt Evolution

2026-01-26 · Zihan Wu, Jie Xu, Yun Peng, Chun Yong Chong 외 arxiv

Large Language Models (LLMs) struggle to automate real-world vulnerability detection due to two key limitations: the heterogeneity of vulnerability patterns undermines the effectiveness of a single unified model, and man…

Vulnerability DetectionPrompt Engineering

Very Large-Scale Multi-Agent Simulation in AgentScope

2024-07-25 · Xuchen Pan, Dawei Gao, Yuexiang Xie, Yushuo Chen 외

Recent advances in large language models (LLMs) have opened new avenues for applying multi-agent systems in very large-scale simulations. However, there remain several challenges when conducting multi-agent simulations w…

Automating Bibliometric Analysis with Sentence Transformers and Retrieval-Augmented Generation (RAG): A Pilot Study in Semantic and Contextual Search for Customized Literature Characterization for High-Impact Urban Research

2024-10-08 · Haowen Xu, Xueping Li, Jose Tupayachi, Jianming 외

Bibliometric analysis is essential for understanding research trends, scope, and impact in urban science, especially in high-impact journals, such Nature Portfolios. However, traditional methods, relying on keyword searc…

AI AgentArticlesRAGRetrieval+2