ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback

• URL: http://arxiv.org/abs/2604.04940v1
• Date: Thu, 05 Mar 2026 04:52:11 GMT
• Title: ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback
• Abstract summary: We propose ReVEL: Multi-Turn Reflective LLM-Heuristic Evolution via Structured Performance Feedback.<n>The core of ReVEL lies in two mechanisms: (i) performance-profile grouping and (ii) multi-turn feedback-driven reflection.<n>Our results highlight multi-turn reasoning with structured grouping as a principled paradigm for automated design.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Designing effective heuristics for NP-hard combinatorial optimization problems remains a challenging and expertise-intensive task. Existing applications of large language models (LLMs) primarily rely on one-shot code synthesis, yielding brittle heuristics that underutilize the models' capacity for iterative reasoning. We propose ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback, a hybrid framework that embeds LLMs as interactive, multi-turn reasoners within an evolutionary algorithm (EA). The core of ReVEL lies in two mechanisms: (i) performance-profile grouping, which clusters candidate heuristics into behaviorally coherent groups to provide compact and informative feedback to the LLM; and (ii) multi-turn, feedback-driven reflection, through which the LLM analyzes group-level behaviors and generates targeted heuristic refinements. These refinements are selectively integrated and validated by an EA-based meta-controller that adaptively balances exploration and exploitation. Experiments on standard combinatorial optimization benchmarks show that ReVEL consistently produces heuristics that are more robust and diverse, achieving statistically significant improvements over strong baselines. Our results highlight multi-turn reasoning with structured grouping as a principled paradigm for automated heuristic design.

Related papers

• Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs [51.60575965819268]
  We propose a plug-and-play Token-Reweighting (ToR) strategy that explicitly models this interdependence.<n>ToR delivers consistent performance gains across multiple multi-modal reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-03-26T06:25:27Z)
• Rectifying LLM Thought from Lens of Optimization [48.98086817378953]
  Long chain-of-thought (CoT) prompting enables thorough exploration and deliberation.<n>Despite advances, long-CoT LLMs often exhibit suboptimal reasoning behaviors.<n>We introduce RePro, a novel approach to refine LLM reasoning during post-training.
  arXiv  Detail & Related papers  (2025-12-01T17:41:08Z)
• Pareto-Grid-Guided Large Language Models for Fast and High-Quality Heuristics Design in Multi-Objective Combinatorial Optimization [8.950269044886621]
  Multi-objective optimization problems (MOCOP) frequently arise in practical applications that require the simultaneous optimization of conflicting objectives.<n>We introduce Multi-heuristics for MOCOP via Pareto-Grid-guided Evolution of LLMs (MPaGE)<n>MPaGE utilizes LLMs to prioritize with semantically distinct logical structures during variation, thus promoting diversity and mitigating redundancy within the population.
  arXiv  Detail & Related papers  (2025-07-28T15:26:43Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey [69.45421620616486]
  This work presents the first structured taxonomy and analysis of discrete tokenization methods designed for large language models (LLMs)<n>We categorize 8 representative VQ variants that span classical and modern paradigms and analyze their algorithmic principles, training dynamics, and integration challenges with LLM pipelines.<n>We identify key challenges including codebook collapse, unstable gradient estimation, and modality-specific encoding constraints.
  arXiv  Detail & Related papers  (2025-07-21T10:52:14Z)
• REMoH: A Reflective Evolution of Multi-objective Heuristics approach via Large Language Models [39.85828629779943]
  Multi-objective optimization is fundamental in complex decision-making tasks.<n>Recent advances in Large Language Models (LLMs) offer enhanced explainability, adaptability, and reasoning.<n>This work proposes Reflective Evolution of Multi-objective Heuristics (REMoH), a novel framework integrating NSGA-II with LLM-based generation.
  arXiv  Detail & Related papers  (2025-06-09T13:38:28Z)
• Generalizable Heuristic Generation Through Large Language Models with Meta-Optimization [14.919482411153185]
  Heuristic design with large language models (LLMs) has emerged as a promising approach for tackling optimization problems.<n>Existing approaches often rely on manually predefined evolutionary generalizations and single-task training schemes.<n>We propose Meta-Optimization of Heuristics (MoH), a novel framework that operates at the level of meta-learning.
  arXiv  Detail & Related papers  (2025-05-27T08:26:27Z)
• Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models [83.8639566087953]
  We propose a direct retrieval-augmented optimization framework, named DRO, that enables end-to-end training of two key components.<n>DRO alternates between two phases: (i) document permutation estimation and (ii) re-weighted, progressively improving RAG components.<n>Our theoretical analysis reveals that DRO is analogous to policy-gradient methods in reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-05T23:54:53Z)
• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning [53.817538122688944]
  We introduce Reinforced Meta-thinking Agents (ReMA) to elicit meta-thinking behaviors from Reasoning of Large Language Models (LLMs)<n>ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions.<n> Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-12T16:05:31Z)
• Can Large Language Models Be Trusted as Evolutionary Optimizers for Network-Structured Combinatorial Problems? [8.431866560904753]
  Large Language Models (LLMs) have shown strong capabilities in language understanding and reasoning across diverse domains.<n>In this work, we propose a systematic framework to evaluate the capability of LLMs to engage with problem structures.<n>We adopt the commonly used evolutionary (EVO) and propose a comprehensive evaluation framework that rigorously assesses the output fidelity of LLM-based operators.
  arXiv  Detail & Related papers  (2025-01-25T05:19:19Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)

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.