POLCA: Stochastic Generative Optimization with LLM

• URL: http://arxiv.org/abs/2603.14769v1
• Date: Mon, 16 Mar 2026 03:07:44 GMT
• Title: POLCA: Stochastic Generative Optimization with LLM
• Abstract summary: We introduce Prioritized Optimization with Local Contextualion (POLCA)<n>POLCA is a scalable framework designed to handle parameterity in optimization.<n>We demonstrate POLCA achieves robust, sample and time-efficient performance.
• Score: 26.342554900977003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Optimizing complex systems, ranging from LLM prompts to multi-turn agents, traditionally requires labor-intensive manual iteration. We formalize this challenge as a stochastic generative optimization problem where a generative language model acts as the optimizer, guided by numerical rewards and text feedback to discover the best system. We introduce Prioritized Optimization with Local Contextual Aggregation (POLCA), a scalable framework designed to handle stochasticity in optimization -- such as noisy feedback, sampling minibatches, and stochastic system behaviors -- while effectively managing the unconstrained expansion of solution space. POLCA maintains a priority queue to manage the exploration-exploitation tradeoff, systematically tracking candidate solutions and their evaluation histories. To enhance efficiency, we integrate an $\varepsilon$-Net mechanism to maintain parameter diversity and an LLM Summarizer to perform meta-learning across historical trials. We theoretically prove that POLCA converges to near-optimal candidate solutions under stochasticity. We evaluate our framework on diverse benchmarks, including $τ$-bench, HotpotQA (agent optimization), VeriBench (code translation) and KernelBench (CUDA kernel generation). Experimental results demonstrate that POLCA achieves robust, sample and time-efficient performance, consistently outperforming state-of-the-art algorithms in both deterministic and stochastic problems. The codebase for this work is publicly available at https://github.com/rlx-lab/POLCA.

Related papers

• Execution-Verified Reinforcement Learning for Optimization Modeling [49.171122807323634]
  Execution-verified learning framework treats a mathematical programming solver as a deterministic, interactive verifier.<n>Experiments on NL4OPT, MAMO, IndustryOR, and OptiBench across Gurobi, OR-Tools, and COPT show that EVOM matches or outperforms process-supervised SFT.
  arXiv  Detail & Related papers  (2026-04-01T03:39:11Z)
• TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization [97.18886232580131]
  Large language models have demonstrated strong reasoning capabilities in complex tasks through tool integration.<n>We propose Turn-Level GRPO, a lightweight RL algorithm that performs turn-level group sampling for fine-grained optimization.
  arXiv  Detail & Related papers  (2026-01-23T06:21:33Z)
• SOCRATES: Simulation Optimization with Correlated Replicas and Adaptive Trajectory Evaluations [25.18297372152296]
  SOCRATES is a novel two-stage procedure that automates the design of tailored SO algorithms.<n>An ensemble of digital replicas of the real system is used as a testbed to evaluate a set of baseline SO algorithms.<n>An LLM acts as a meta-optimizer, analyzing the performance trajectories of these algorithms to iteratively revise and compose a final, hybrid optimization schedule.
  arXiv  Detail & Related papers  (2025-11-01T19:57:38Z)
• Optimizing Prompt Sequences using Monte Carlo Tree Search for LLM-Based Optimization [20.44067161623662]
  Large language models (LLMs) have demonstrated remarkable capabilities in code generation and structured reasoning.<n>We propose a novel neural-symbolic framework that formulates prompt selection as a sequential decision process guided by Monte Carlo Tree Search.<n>Our method explores and refines multi-step prompt sequences for the goal of improving code generation quality.
  arXiv  Detail & Related papers  (2025-08-08T04:01:24Z)
• Stochastic Optimal Control via Measure Relaxations [5.786721045975334]
  We cast the optimal control problem of a system as a convex problem over occupation measures.<n>We demonstrate our method on a set of synthetic and realworld scenarios.
  arXiv  Detail & Related papers  (2025-07-26T07:18:16Z)
• OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems [19.586884180343038]
  OPT-BENCH is a benchmark designed to evaluate Large Language Models (LLMs) on large-scale search space optimization problems.<n> OPT-Agent emulates human reasoning when tackling complex problems by generating, validating, and iteratively improving solutions through historical feedback.
  arXiv  Detail & Related papers  (2025-06-12T14:46:41Z)
• Preference Optimization for Combinatorial Optimization Problems [54.87466279363487]
  Reinforcement Learning (RL) has emerged as a powerful tool for neural optimization, enabling models learns that solve complex problems without requiring expert knowledge.<n>Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast action spaces.<n>We propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling.
  arXiv  Detail & Related papers  (2025-05-13T16:47:00Z)
• Indirect Query Bayesian Optimization with Integrated Feedback [17.66813850517961]
  We develop a new class of Bayesian optimization problems where integrated feedback is given via a conditional expectation of the unknown function $f$ to be optimized.<n>The goal is to find the global optimum of $f$ by adaptively querying and observing in the space transformed by the conditional distribution.<n>This is motivated by real-world applications where one cannot access direct feedback due to privacy, hardware or computational constraints.
  arXiv  Detail & Related papers  (2024-12-18T07:20:33Z)
• 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)
• Federated Conditional Stochastic Optimization [110.513884892319]
  Conditional optimization has found in a wide range of machine learning tasks, such as in-variant learning tasks, AUPRC, andAML. This paper proposes algorithms for distributed federated learning.
  arXiv  Detail & Related papers  (2023-10-04T01:47:37Z)
• Global Optimization of Gaussian processes [52.77024349608834]
  We propose a reduced-space formulation with trained Gaussian processes trained on few data points. The approach also leads to significantly smaller and computationally cheaper sub solver for lower bounding. In total, we reduce time convergence by orders of orders of the proposed method.
  arXiv  Detail & Related papers  (2020-05-21T20:59:11Z)

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.