MARINE: Theoretical Optimization and Design for Multi-Agent Recursive IN-context Enhancement

• URL: http://arxiv.org/abs/2512.07898v1
• Date: Fri, 05 Dec 2025 11:19:18 GMT
• Title: MARINE: Theoretical Optimization and Design for Multi-Agent Recursive IN-context Enhancement
• Authors: Hongwei Zhang, Ji Lu, Yongsheng Du, Yanqin Gao, Lingjun Huang, Baoli Wang, Fang Tan, Peng Zou,
• Abstract summary: Large Language Model (LLM)-based agents demonstrate advanced reasoning capabilities, yet practical constraints frequently limit outputs to single responses.<n>This paper introduces MARINE, a framework that reconceptualizes test-time reasoning as iterative refinement of a persistent reference trajectory.<n>Proposed MARINE delivers higher-quality samples to alignment and optimization processes than traditional sampling-and-ranking strategies.
• Score: 5.852607388888843
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Model (LLM)-based agents demonstrate advanced reasoning capabilities, yet practical constraints frequently limit outputs to single responses, leaving significant performance potential unrealized. This paper introduces MARINE (Multi-Agent Recursive IN-context Enhancement), a theoretically grounded framework that reconceptualizes test-time reasoning as iterative refinement of a persistent reference trajectory, fundamentally departing from conventional one-shot or multi-sample paradigms. The MARINE refinement operator systematically converts a base model's pass@N capabilities into near-optimal pass@1 performance. Rigorous theoretical analysis establishes that minimal feasible batches maximize expected performance gains under fixed invocation budgets, while logarithmically growing batch schedules ensure continuous improvement without computational constraints. Comprehensive evaluation on the BrowserComp-ZH benchmark demonstrates state-of-the-art results, with a 685B-parameter implementation achieving 46.0% pass@1 accuracy. Meanwhile, MARINE establishes a new paradigm for parameter-efficient reasoning: an 80B-parameter model augmented with MARINE matches the performance of standalone 1000B-parameter agents, reducing parameter requirements by over an order of magnitude. Notably, within a fixed computational budget, the proposed MARINE delivers higher-quality samples to alignment and optimization processes than traditional sampling-and-ranking strategies. Consequently, it has great potential to boost post-training efficiency.

Related papers

• High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning [57.85676271833619]
  Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning.<n>We present textbfSMoA, a high-rank textbfStructured textbfMOdulation textbfAdapter that uses fewer trainable parameters while maintaining a higher rank.
  arXiv  Detail & Related papers  (2026-01-12T13:06:17Z)
• Efficient Thought Space Exploration through Strategic Intervention [54.35208611253168]
  We propose a novel Hint-Practice Reasoning (HPR) framework that operationalizes this insight through two synergistic components.<n>The framework's core innovation lies in Distributional Inconsistency Reduction (DIR), which dynamically identifies intervention points.<n> Experiments across arithmetic and commonsense reasoning benchmarks demonstrate HPR's state-of-the-art efficiency-accuracy tradeoffs.
  arXiv  Detail & Related papers  (2025-11-13T07:26:01Z)
• Benchmarking Generative AI Against Bayesian Optimization for Constrained Multi-Objective Inverse Design [0.15293427903448018]
  This paper investigates the performance of Large Language Models (LLMs) as generative feasibles for solving constrained multi-objective regression tasks.<n>The best-performing LLM (Math-7B) achieved a Generational Distance (GD) of 1.21, significantly outperforming the traditional BoTorch Ax baseline.<n>The findings have direct industrial applications in optimizing formulation design for resins, rheological, and chemical properties.
  arXiv  Detail & Related papers  (2025-10-29T10:37:09Z)
• Approximate Quantum State Preparation with Tree-Based Bayesian Optimization Surrogates [4.946006905837039]
  We study the problem of approximate state preparation on near-term quantum computers.<n>The goal is to construct a parameterized circuit that reproduces the output distribution of a target quantum state while minimizing resource overhead.<n>We propose CircuitTree, a surrogate-guided optimization framework based on Bayesian Optimization with tree-based models.
  arXiv  Detail & Related papers  (2025-09-30T18:19:37Z)
• Quantum-Inspired DRL Approach with LSTM and OU Noise for Cut Order Planning Optimization [0.0]
  Cut order planning (COP) is a critical challenge in the textile industry, directly impacting fabric utilization and production costs.<n>We propose a novel Quantum-Inspired Deep Reinforcement Learning framework that integrates Long Short-Term Memory networks with Ornstein-Uhlenbeck noise.<n>A comparative analysis reveals that the proposed approach achieves fabric cost savings of up to 13% compared to conventional methods.
  arXiv  Detail & Related papers  (2025-08-13T05:00:50Z)
• Accelerated Test-Time Scaling with Model-Free Speculative Sampling [58.69141724095398]
  We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach.<n>We show that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding.<n>As a model-free approach, STAND can be applied to any existing language model without additional training.
  arXiv  Detail & Related papers  (2025-06-05T07:31:18Z)
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning [78.63421517563056]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks.<n>We present a unified probabilistic framework that formalizes LLM reasoning through a novel graphical model.<n>We introduce the Bootstrapping Reinforced Thinking Process (BRiTE) algorithm, which works in two steps.
  arXiv  Detail & Related papers  (2025-01-31T02:39:07Z)
• Optimizing Hyperparameters with Conformal Quantile Regression [7.316604052864345]
  We propose to leverage conformalized quantile regression which makes minimal assumptions about the observation noise. This translates to quicker HPO convergence on empirical benchmarks.
  arXiv  Detail & Related papers  (2023-05-05T15:33:39Z)
• When to Update Your Model: Constrained Model-based Reinforcement Learning [50.74369835934703]
  We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL) Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
  arXiv  Detail & Related papers  (2022-10-15T17:57:43Z)
• Optimization of Annealed Importance Sampling Hyperparameters [77.34726150561087]
  Annealed Importance Sampling (AIS) is a popular algorithm used to estimates the intractable marginal likelihood of deep generative models. We present a parameteric AIS process with flexible intermediary distributions and optimize the bridging distributions to use fewer number of steps for sampling. We assess the performance of our optimized AIS for marginal likelihood estimation of deep generative models and compare it to other estimators.
  arXiv  Detail & Related papers  (2022-09-27T07:58:25Z)

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.