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

• URL: http://arxiv.org/abs/2509.11361v2
• Date: Tue, 07 Oct 2025 09:25:03 GMT
• Title: MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization
• Abstract summary: We propose a novel framework that reconceptualizes prompt optimization as a collaborative process among specialized agents.<n>Each agent focuses on a distinct refinement dimension, such as instruction clarity, example selection, format structure, or stylistic adaptation.<n>We show that MAPGD consistently surpasses single-agent and random baselines in both accuracy and efficiency.
• Score: 11.108961365820136
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• PG-MAP: Joint MAP Optimization for Inference-Time Alignment of Diffusion and Flow-Matching Models [0.8594140167290097]
  Inference-time alignment of pretrained text-to-image models is typically performed along a single control axis.<n>We propose PG-MAP, a training-free framework that formulates inference-time alignment as a trajectory-level Gibbs-MAP / proximal energy optimization.
  arXiv  Detail & Related papers  (2026-06-22T07:36:36Z)
• A Unified Framework for Gradient Aggregation in Multi-Objective Optimization [23.311857116714176]
  We develop a unifying framework for gradient aggregation in MOO.<n>We show that feasibility can be ensured through projection onto the dual cone, broadening the scope of methods that admit convergence guarantees.<n>We present a primal optimization perspective of gradient aggregation that encompasses established algorithms, clarifies their theoretical relationships, and enables the design of new variants.
  arXiv  Detail & Related papers  (2026-05-28T18:21:53Z)
• Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt Optimization [10.37712840622514]
  Multi-Agent Systems (MAS) empower Large Language Models to tackle complex reasoning computation tasks.<n>Existing black-boxs struggle to attribute trajectory-level failure to specific local components.<n>We argue that tractable MAS optimization needs structural inductive biases to disentangle error signals.
  arXiv  Detail & Related papers  (2026-05-28T16:57:57Z)
• Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models [69.55139736609367]
  Agent-GWO is a dynamic prompt optimization framework for complex reasoning.<n>We show that Agent-GWO consistently improves accuracy and stability over existing prompt optimization methods.
  arXiv  Detail & Related papers  (2026-04-14T07:35:37Z)
• Structure-Aware Robust Counterfactual Explanations via Conditional Gaussian Network Classifiers [0.26999000177990923]
  This work presents a structure-aware robustness-and-counterfactual search method based on conditional conditional graphs.<n>Results show that our method achieves strong consistency, with direct optimization of the original formulation providing especially stable dependencies.<n>The proposed framework lays the groundwork for future advances in counterfactual reasoning under noncyclic constraints.
  arXiv  Detail & Related papers  (2026-02-08T15:51:45Z)
• Towards Efficient General Feature Prediction in Masked Skeleton Modeling [59.46799426434277]
  We propose a novel General Feature Prediction framework (GFP) for efficient mask skeleton modeling.<n>Our key innovation is replacing conventional low-level reconstruction with high-level feature prediction that spans from local motion patterns to global semantic representations.
  arXiv  Detail & Related papers  (2025-09-03T18:05:02Z)
• Pareto Actor-Critic for Communication and Computation Co-Optimization in Non-Cooperative Federated Learning Services [18.291028557265864]
  We introduce PAC-MCoFL, a game-theoretic multi-agent reinforcement learning (MARL) framework where SPs act as agents to jointly optimize client assignment, adaptive quantization, and resource allocation.<n>We develop PAC-MCoFL-p, a scalable variant featuring a parameterized conjecture generator that substantially reduces computational complexity with a provably bounded error.
  arXiv  Detail & Related papers  (2025-08-22T02:09:48Z)
• Multi-Agent Trust Region Policy Optimisation: A Joint Constraint Approach [17.48210470289556]
  Heterogeneous-Agent Trust Region Policy Optimization (HATRPO) enforces per-agent trust region constraints using Kullback-Leibler (KL) divergence to stabilize training.<n> assigning each agent the same KL threshold can lead to slow and locally optimal updates, especially in heterogeneous settings.<n>We propose two approaches for allocating the KL divergence threshold across agents: HATRPO-W, a Karush-Kuhn-Tucker-based (KKT-based) method that optimize threshold assignment under global KL constraints, and HATRPO-G, a greedy algorithm that prioritizes agents based on improvement-to
  arXiv  Detail & Related papers  (2025-08-14T04:48:46Z)
• Collab: Controlled Decoding using Mixture of Agents for LLM Alignment [90.6117569025754]
  Reinforcement learning from human feedback has emerged as an effective technique to align Large Language models.<n>Controlled Decoding provides a mechanism for aligning a model at inference time without retraining.<n>We propose a mixture of agent-based decoding strategies leveraging the existing off-the-shelf aligned LLM policies.
  arXiv  Detail & Related papers  (2025-03-27T17:34:25Z)
• Learning to Solve the Min-Max Mixed-Shelves Picker-Routing Problem via Hierarchical and Parallel Decoding [0.3867363075280544]
  The Mixed-Shelves Picker Routing Problem (MSPRP) is a fundamental challenge in logistics, where pickers must navigate a mixed-shelves environment to retrieve SKUs efficiently.<n>We propose a novel hierarchical and parallel decoding approach for solving the min-max variant of the MSPRP via multi-agent reinforcement learning.<n> Experiments show state-of-the-art performance in both solution quality and inference speed, particularly for large-scale and out-of-distribution instances.
  arXiv  Detail & Related papers  (2025-02-14T15:42:30Z)
• Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency [52.60557300927007]
  We present a $textbfMA-OSMA$ algorithm to transfer the discrete submodular problem into a continuous optimization.<n>We also introduce a projection-free $textbfMA-OSEA$ algorithm, which effectively utilizes the KL divergence by mixing a uniform distribution.<n>Our algorithms significantly improve the $(frac11+c)$-approximation provided by the state-of-the-art OSG algorithm.
  arXiv  Detail & Related papers  (2025-02-07T15:57:56Z)
• Contextually Entangled Gradient Mapping for Optimized LLM Comprehension [0.0]
  Entually Entangled Gradient Mapping (CEGM) introduces a new approach to gradient optimization.<n>It treats gradients as dynamic carriers of contextual dependencies rather than isolated numerical entities.<n>The proposed methodology bridges critical gaps in existing optimization strategies.
  arXiv  Detail & Related papers  (2025-01-28T11:50:35Z)
• SPGD: Steepest Perturbed Gradient Descent Optimization [0.0]
  This paper presents the Steepest Perturbed Gradient Descent (SPGD) algorithm.<n>It is designed to generate a set of candidate solutions and select the one exhibiting the steepest loss difference.<n>Preliminary results show a substantial improvement over four established methods.
  arXiv  Detail & Related papers  (2024-11-07T18:23:30Z)
• Unleashing Network Potentials for Semantic Scene Completion [50.95486458217653]
  This paper proposes a novel SSC framework - Adrial Modality Modulation Network (AMMNet) AMMNet introduces two core modules: a cross-modal modulation enabling the interdependence of gradient flows between modalities, and a customized adversarial training scheme leveraging dynamic gradient competition. Extensive experimental results demonstrate that AMMNet outperforms state-of-the-art SSC methods by a large margin.
  arXiv  Detail & Related papers  (2024-03-12T11:48:49Z)
• Conflict-Averse Gradient Optimization of Ensembles for Effective Offline Model-Based Optimization [0.0]
  We evaluate two algorithms for combining gradient information: multiple gradient descent algorithm (MGDA) and conflict-averse gradient descent (CAGrad) Our results suggest that MGDA and CAGrad strike a desirable balance between conservatism and optimality and can help robustify data-driven offline MBO without compromising optimality of designs.
  arXiv  Detail & Related papers  (2023-03-31T10:00:27Z)
• Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration [71.95914457415624]
  Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. We propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines.
  arXiv  Detail & Related papers  (2022-11-29T17:10:24Z)
• An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization [78.36413169647408]
  We study the effectiveness of various ZO optimization methods for optimizing molecular objectives. We show the advantages of ZO sign-based gradient descent (ZO-signGD) We demonstrate the potential effectiveness of ZO optimization methods on widely used benchmark tasks from the Guacamol suite.
  arXiv  Detail & Related papers  (2022-10-27T01:58:10Z)
• ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement [80.94378602238432]
  We propose an efficient structure named Correspondence Efficient Transformer (ECO-TR) by finding correspondences in a coarse-to-fine manner. To achieve this, multiple transformer blocks are stage-wisely connected to gradually refine the predicted coordinates. Experiments on various sparse and dense matching tasks demonstrate the superiority of our method in both efficiency and effectiveness against existing state-of-the-arts.
  arXiv  Detail & Related papers  (2022-09-25T13:05:33Z)
• Revisiting GANs by Best-Response Constraint: Perspective, Methodology, and Application [49.66088514485446]
  Best-Response Constraint (BRC) is a general learning framework to explicitly formulate the potential dependency of the generator on the discriminator. We show that even with different motivations and formulations, a variety of existing GANs ALL can be uniformly improved by our flexible BRC methodology.
  arXiv  Detail & Related papers  (2022-05-20T12:42:41Z)
• Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision [74.9260745577362]
  This paper proposes a unified optimization-inspired learning framework to aggregate Generative, Discriminative, and Corrective (GDC) principles. We construct three propagative modules to effectively solve the optimization models with flexible combinations. Experiments across varied low-level vision tasks validate the efficacy and adaptability of GDC.
  arXiv  Detail & Related papers  (2020-12-10T03:24:53Z)
• Domain Adaptive Person Re-Identification via Coupling Optimization [58.567492812339566]
  Domain adaptive person Re-Identification (ReID) is challenging owing to the domain gap and shortage of annotations on target scenarios. This paper proposes a coupling optimization method including the Domain-Invariant Mapping (DIM) method and the Global-Local distance Optimization ( GLO) GLO is designed to train the ReID model with unsupervised setting on the target domain.
  arXiv  Detail & Related papers  (2020-11-06T14:01:03Z)
• Optimizing Cooperative path-finding: A Scalable Multi-Agent RRT* with Dynamic Potential Fields [11.872579571976903]
  This study introduces the multi-agent RRT* potential field (MA-RRT*PF), an innovative algorithm that addresses computational efficiency and path-finding efficacy in dense scenarios. The empirical evaluations highlight MA-RRT*PF's significant superiority over conventional multi-agent RRT* (MA-RRT*) in dense environments.
  arXiv  Detail & Related papers  (2019-11-16T13:02:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.