RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience

• URL: http://arxiv.org/abs/2607.11358v1
• Date: Mon, 13 Jul 2026 10:24:34 GMT
• Title: RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience
• Abstract summary: Automatic Heuristic Design (AHD) has emerged as a transformative approach for solving optimization problems.<n>This paper proposes RefineEvo, a novel evolutionary framework that transforms AHD into a planning-guided, experience-driven system.
• Score: 25.80220644131568
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic Heuristic Design (AHD) has emerged as a transformative approach for solving combinatorial optimization problems. While recent Large Language Model (LLM)-based methods have shown promise, they predominantly rely on fixed evolutionary operators and struggle to effectively accumulate and reuse historical search experience. This paper proposes RefineEvo, a novel evolutionary framework that transforms AHD from a static trial-and-error process into a planning-guided, experience-driven system. RefineEvo introduces a Planner to dynamically schedule evolutionary operators and trigger refinement based on the current search state, and a Reflector to distill valuable lessons into a Bidirectional Experience Pool containing both positive insights and negative pitfalls. This synergistic framework enables the system to adapt its search tools to the evolving complexity of the problem and leverage trajectory-aware, situation-conditioned insights to guide generation. Experiments on several classic combinatorial optimization benchmarks demonstrate that RefineEvo consistently outperforms strong baselines. In particular, RefineEvo delivers superior solution quality while improving token efficiency, enabling more efficient and autonomous heuristic design.

Related papers

• Self-Improving Large Language Models via Progressive Experience Evolution [52.03479747358687]
  We propose textbfSPEE (textbfSelf-textbfProgressive textbfExperience textbfEvolution), a unified post-training framework that sequentially performs explicit experience evolution followed by implicit policy optimization.<n> Experiments on five mathematical reasoning benchmarks demonstrate that SPEE consistently outperforms both test-time and training-time self-evolution baselines across three model scales.
  arXiv  Detail & Related papers  (2026-08-03T12:27:32Z)
• Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving [79.71689985927625]
  We propose IRR-Drive, an adaptive multimodal reflection framework for autonomous driving.<n>IRR-Drive explicitly models anticipated scene evolution, enabling the model to rigorously self-correct and refine its initial intent.<n>Our method achieves state-of-the-art performance on the benchmark in both PDMS and NAVSIMS.
  arXiv  Detail & Related papers  (2026-06-22T06:53:58Z)
• EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learning [39.60899845728349]
  Multimodal Large Language Model (MLLM)-driven image restoration agent demonstrates effectiveness in degradation coupling scenarios.<n>Training-based methods embed intrinsic experience into parameters, achieving high inference efficiency but lacking compatibility with new tools or degradation.<n>We propose EvoIR-Agent, which first systematically formulates the experience components of a training-free image restoration agent.
  arXiv  Detail & Related papers  (2026-05-21T09:14:25Z)
• Advancing Automated Algorithm Design via Evolutionary Stagewise Design with LLMs [69.91297564489464]
  EvoStage is a novel evolutionary paradigm that bridges the gap between the rigorous demands of industrial-scale algorithm design and the LLM-based algorithm design methods.<n>EvoStage decomposes the algorithm design process into sequential, manageable stages and integrates real-time intermediate feedback to iteratively refine algorithm design directions.<n>When deployed on a commercial-grade 3D chip placement tool, EvoStage significantly surpasses the original performance metrics, achieving record-breaking efficiency.
  arXiv  Detail & Related papers  (2026-03-09T05:13:44Z)
• ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback [0.0]
  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.
  arXiv  Detail & Related papers  (2026-03-05T04:52:11Z)
• Socio-cognitive agent-oriented evolutionary algorithm with trust-based optimization [70.49434432747293]
  Trust-Based Optimization (TBO) is a novel extension of the island model in evolutionary computation that replaces conventional periodic migrations with a flexible, agent-driven interaction mechanism based on trust or reputation.<n> Experimental results demonstrate that TBO generally outperforms the standard island model evolutionary algorithm across various optimization problems.
  arXiv  Detail & Related papers  (2025-10-29T01:59:26Z)
• Experience-Guided Reflective Co-Evolution of Prompts and Heuristics for Automatic Algorithm Design [124.54166764570972]
  Combinatorial optimization problems are traditionally tackled with handcrafted algorithms.<n>Recent progress has highlighted the potential of automatics design powered by large language models.<n>We propose the Experience-Evolution Reflective Co-Guided of Prompt and Heuristics (EvoPH) for automatic algorithm design.
  arXiv  Detail & Related papers  (2025-09-29T09:24:09Z)
• EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment [42.41408547627677]
  EvolvingGrasp is an evolutionary grasp generation method that continuously enhances grasping performance through preference alignment.<n>Our results validate that EvolvingGrasp enables evolutionary grasp generation, ensuring robust, physically feasible, and preference-aligned grasping in both simulation and real scenarios.
  arXiv  Detail & Related papers  (2025-03-18T15:01:47Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)

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.