paper-with-me

Papers

MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization

2025-09-14 · Yichen Han, Yuhang Han, Siteng Huang, Guanyu Liu, Zhengpeng Zhou, Bojun Liu, Yujia Zhang, Isaac N Shi, Lewei He, Tianyu Shi arxiv

Prompt engineering is crucial for fully leveraging large language models (LLMs), yet most existing optimization methods follow a single trajectory, resulting in limited adaptability, gradient conflicts, and high computational overhead. We propose MAPGD (Multi-Agent Prompt Gradient Descent), a novel framework that reconceptualizes prompt optimization as a collaborative process among specialized agents. Each agent focuses on a distinct refinement dimension, such as instruction clarity, example selection, format structure, or stylistic adaptation, and their contributions are coordinated through semantic gradient embedding, conflict detection, and fusion. To further enhance robustness and stability, MAPGD introduces two new mechanisms: Hypersphere Constrained Gradient Clustering (HCGC), which enforces angular margin constraints for compact and well-separated clusters, and Channel Adaptive Agent Weighting (CAAW), which dynamically reweights agent contributions based on validation performance. Experiments on classification and reasoning benchmarks show that MAPGD consistently surpasses single-agent and random baselines in both accuracy and efficiency. Ablation studies confirm the effectiveness of gradient fusion, agent specialization, and conflict resolution. Together, these components establish MAPGD as a unified, gradient-based, and interpretable framework for robust prompt optimization with theoretical convergence guarantees.

📄 PDF Abstract BibTeX arXiv:2509.11361

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

Automatic Prompt Optimization with "Gradient Descent" and Beam Search

2023-05-04 · Reid Pryzant, Dan Iter, Jerry Li, Yin Tat Lee 외

Large Language Models (LLMs) have shown impressive performance as general purpose agents, but their abilities remain highly dependent on prompts which are hand written with onerous trial-and-error effort. We propose a si…

LLM Jailbreak

Iterative Pre-Conditioning for Expediting the Gradient-Descent Method: The Distributed Linear Least-Squares Problem

2020-08-06 · Kushal Chakrabarti, Nirupam Gupta, Nikhil Chopra

This paper considers the multi-agent linear least-squares problem in a server-agent network. In this problem, the system comprises multiple agents, each having a set of local data points, that are connected to a server. …

Polymatrix Competitive Gradient Descent

2021-11-16 · Jeffrey Ma, Alistair Letcher, Florian Schäfer, Yuanyuan Shi 외

Many economic games and machine learning approaches can be cast as competitive optimization problems where multiple agents are minimizing their respective objective function, which depends on all agents' actions. While g…

Multi-agent Reinforcement Learning

Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning

2026-02-23 · Shan Yang, Yang Liu arxiv

Scaling cooperative multi-agent reinforcement learning (MARL) is fundamentally limited by cross-agent noise. When agents share a common reward, each agent's learning signal is computed from a shared return that depends o…

Multi-agent Reinforcement Learning

Can Gradient Descent Simulate Prompting?

2025-06-26 · Eric Zhang, Leshem Choshen, Jacob Andreas

There are two primary ways of incorporating new information into a language model (LM): changing its prompt or changing its parameters, e.g. via fine-tuning. Parameter updates incur no long-term storage cost for model ch…

Meta-Learning