From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling

• URL: http://arxiv.org/abs/2604.25847v1
• Date: Tue, 28 Apr 2026 16:53:37 GMT
• Title: From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling
• Abstract summary: Agora-Opt is a modular agentic framework for optimization modeling.<n>It combines decentralized debate with a read-write memory bank.<n>It achieves the strongest overall performance among all compared methods.
• Score: 15.496636322208841
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Optimization modeling underpins real-world decision-making in logistics, manufacturing, energy, and public services, but reliably solving such problems from natural-language requirements remains challenging for current large language models (LLMs). In this paper, we propose \emph{Agora-Opt}, a modular agentic framework for optimization modeling that combines decentralized debate with a read-write memory bank. Agora-Opt allows multiple agent teams to independently produce end-to-end solutions and reconcile them through an outcome-grounded debate protocol, while memory stores solver-verified artifacts and past disagreement resolutions to support training-free improvement over time. This design is flexible across both backbones and methods: it reduces base-model lock-in, transfers across different LLM families, and can be layered onto existing pipelines with minimal coupling. Across public benchmarks, Agora-Opt achieves the strongest overall performance among all compared methods, outperforming strong zero-shot LLMs, training-centric approaches, and prior agentic baselines. Further analyses show robust gains across backbone choices and component variants, and demonstrate that decentralized debate offers a structural advantage over centralized selection by enabling agents to refine candidate solutions through interaction and even recover correct formulations when all initial candidates are flawed. These results suggest that reliable optimization modeling benefits from combining collaborative cross-checking with reusable experience, and position Agora-Opt as a practical and extensible foundation for trustworthy optimization modeling assistance. Our code and data are available at https://github.com/CHIANGEL/Agora-Opt.

Related papers

• CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging [59.836482609414816]
  We propose a conflict-driven preference optimization framework for model merging (CoMerge)<n>CoMerge enables the model to mitigate parameter-space conflicts while preserving task-specific capabilities.<n>Experiments show that CoMerge achieves an average normalized performance of 0.9968 on MergeBench.
  arXiv  Detail & Related papers  (2026-09-02T08:21:28Z)
• Joint Optimization of Training and Inference in Federated Edge Learning via Constrained Multi-Objective Deep Reinforcement Learning [9.37821062000313]
  Federated edge learning (FEEL) has emerged as a promising paradigm for achieving edge intelligence (EI)<n>We put forth an online optimization framework that jointly manages federated training and inference on resource-constrained edge devices.
  arXiv  Detail & Related papers  (2026-05-25T14:51:07Z)
• Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches [14.24802309734814]
  This paper introduces an agentic re-optimization framework in which a large language model (LLM) acts as an OR expert.<n>The proposed framework enables interactive and continuous adaptation of deployed optimization models.
  arXiv  Detail & Related papers  (2026-05-18T17:28:25Z)
• Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs [0.41998444721319217]
  This work proposes a multi-agent negotiation-based alignment framework that aligns large language models to Collective Agency (CA)<n>To enable scalable training, two self-play instances of the same LLM, assigned opposing personas, engage in structured turn-based dialogue to synthesize mutually beneficial solutions.<n>Experiments show that the resulting model achieves CA alignment comparable to a single-agent baseline while substantially improving conflict-resolution performance without degrading general language capabilities.
  arXiv  Detail & Related papers  (2026-03-11T06:58:55Z)
• Adaptive Acquisition Selection for Bayesian Optimization with Large Language Models [29.41740966512592]
  LMABO is a novel framework that casts a pre-trained Large Language Model as a zero-shot, online strategist for the BO process.<n>We show that the LLM's behavior is a comprehensive strategy that adapts to real-time progress, proving its advantage stems from its ability to process and synthesize the complete optimization state into an effective, adaptive policy.
  arXiv  Detail & Related papers  (2026-02-08T10:53:52Z)
• Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation [50.22481337087162]
  Referring Video Object (RVOS) aims to segment objects in videos based on textual queries.<n>Refer-Agent is a collaborative multi-agent system with alternating reasoning-reflection mechanisms.
  arXiv  Detail & Related papers  (2026-02-03T14:48:12Z)
• SOLID: a Framework of Synergizing Optimization and LLMs for Intelligent Decision-Making [13.975554366504587]
  SOLID is a framework that integrates mathematical optimization with the contextual capabilities of large language models (LLMs)<n>The framework retains theoretical convergence guarantees under convexity assumptions, providing insight into the design of LLMs prompt.<n> Empirical results demonstrate convergence under various scenarios and indicate annualized returns compared to a baseline-only method.
  arXiv  Detail & Related papers  (2025-11-19T07:44:36Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs [102.48588475875749]
  We introduce Generative Self-Refinement (GSR), a novel parallel test-time scaling framework.<n>GSR generates a set of candidate responses in parallel and then performs self-refinement to synthesize a new superior solution.<n>We show that our method achieves state-of-the-art performance across five mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T06:51:48Z)
• From Natural Language to Solver-Ready Power System Optimization: An LLM-Assisted, Validation-in-the-Loop Framework [1.7136832159667206]
  This paper introduces a novel Large Language Models (LLMs)-assisted agent that automatically converts natural-language descriptions of power system optimization scenarios into compact, solver-ready formulations.<n>The proposed method focuses on discovering a mathematically compatible formulation that can be efficiently solved by off-the-shelf optimization solvers.
  arXiv  Detail & Related papers  (2025-08-11T16:22:57Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)
• Large Language Models to Enhance Bayesian Optimization [57.474613739645605]
  We present LLAMBO, a novel approach that integrates the capabilities of Large Language Models (LLM) within Bayesian optimization. At a high level, we frame the BO problem in natural language, enabling LLMs to iteratively propose and evaluate promising solutions conditioned on historical evaluations. Our findings illustrate that LLAMBO is effective at zero-shot warmstarting, and enhances surrogate modeling and candidate sampling, especially in the early stages of search when observations are sparse.
  arXiv  Detail & Related papers  (2024-02-06T11:44:06Z)
• Slimmable Domain Adaptation [112.19652651687402]
  We introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank. Our framework surpasses other competing approaches by a very large margin on multiple benchmarks.
  arXiv  Detail & Related papers  (2022-06-14T06:28:04Z)

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.