REVIEW 21 cited by
ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design. The long-standing endeavor of design automation has gained new momentum with the rise of large language models (LLMs). This paper introduces Language Hyper-Heuristics (LHHs), an emerging variant of Hyper-Heuristics that leverages LLMs for heuristic generation, featuring minimal manual intervention and open-ended heuristic spaces. To empower LHHs, we present Reflective Evolution (ReEvo), a novel integration of evolutionary search for efficiently exploring the heuristic space, and LLM reflections to provide verbal gradients within the space. Across five heterogeneous algorithmic types, six different COPs, and both white-box and black-box views of COPs, ReEvo yields state-of-the-art and competitive meta-heuristics, evolutionary algorithms, heuristics, and neural solvers, while being more sample-efficient than prior LHHs.
Forward citations
Cited by 21 Pith papers
-
AutoSND: From Execution Evidence to Structural Policies for Automated Network Dismantling Heuristic Discovery
A three-stage LLM search framework converts execution evidence into structural policies and discovers network dismantling programs with strong quality and low runtime.
-
EvoGit: Decentralized Code Evolution via Git-Based Multi-Agent Collaboration
A Git-based phylogenetic graph lets independent AI agents collaboratively evolve code through mutation and crossover, demonstrated on a website and a meta-level bin-packing solver.
-
Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design
MCTS-AHD organizes LLM-generated heuristics in a Monte Carlo tree and reports better or comparable heuristics than population-based baselines on several NP-hard problems and a Bayesian optimization task.
-
Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis
MinHash-band curriculum fine-tuning of OlympicCoder-7B yields 60% peak success on high-similarity NAS code generation, yet merge drift and interface repair dominate later stages.
-
MeLA: A Metacognitive LLM-Driven Architecture for Automatic Heuristic Design
MeLA evolves the prompt that instructs an LLM to write heuristics, using metacognitive self-reflection and error correction to improve both success rate and solution quality across TSP, bin packing, curriculum sequenc...
-
Large Language Model-Driven Surrogate-Assisted Evolutionary Algorithm for Expensive Optimization
LLM-SAEA uses an LLM scoring expert and an LLM decision expert to dynamically select surrogate models and infill criteria, and it reports competitive results on expensive-optimization benchmarks, though the gain over ...
-
HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges
An LLM-driven two-stage hyper-heuristic framework that evolves a pool of heuristics and adaptively selects among them, outperforming prior LLM hyper-heuristics on TSP, CVRP, MKP, and JSSP.
-
iDSE: Navigating Design Space Exploration in High-Level Synthesis Using LLMs
An LLM-based design space exploration system for HLS combines design-space pruning, LLM-generated seed directives, and convergent/divergent refinement to approximate Pareto-optimal designs with few synthesis evaluations.
-
Explainable AI-assisted Optimization for Feynman Integral Reduction
FunSearch discovered a simple priority function for ordering IBP seeding integrals, reducing the number needed for multi-loop Feynman integral reductions by factors up to 3058.
-
Beyond the Hype: Benchmarking LLM-Evolved Heuristics for Bin Packing
Across 6,064 bin-packing instances from 12 datasets, the hand-designed Best-Fit heuristic outperforms most LLM-evolved heuristics, which do not generalize beyond their training distributions.
-
Evolving Deeper LLM Thinking
Mind Evolution, an LLM-driven evolutionary search guided by a programmatic scorer, solves over 98% of TravelPlanner and Natural Plan instances with Gemini 1.5 Pro, outperforming Best-of-N and sequential revision at co...
-
QUBE: Enhancing Automatic Heuristic Design via Quality-Uncertainty Balanced Evolution
QUBE adds a UCB-style uncertainty term to FunSearch's parent selection and finds better heuristics on bin packing and TSP, with cap set gains only over a same-hardware reproduction.
-
Graph Optimization Foundation Model: Tokenizing Graph via A Language-Model Paradigm
A per-graph BERT-style masked random-walk model is repurposed to generate shortest paths and tours, with mixed quality versus classical solvers and no cross-graph transfer evaluation.
-
Behaviour Space Analysis of LLM-driven Meta-heuristic Discovery
Comparing six LLaMEA prompt and selection variants on 5D BBOB problems, the 1+1 elitist variant using both simplify and random-perturbation prompts produced the best anytime performance, and behaviour metrics link thi...
-
REMoH: A Reflective Evolution of Multi-objective Heuristics approach via Large Language Models
REMoH evolves LLM-written heuristics with NSGA-II and a reflection mechanism, reporting competitive FJSSP results that are weakened by test-set selection.
-
HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs
HSEvo combines diversity metrics, harmony search, and genetic algorithms in LLM-based evolutionary program search to balance exploration and exploitation on bin packing, TSP, and orienteering.
-
Using Large Language Models for Parametric Shape Optimization
An LLM-driven evolutionary search, LLM-PSO, finds near-optimal airfoil and Stokes-flow body shapes on two benchmarks, generally converging faster than classical optimizers.
-
Enhancing CVRP Solver through LLM-driven Automatic Heuristic Design
LLM-evolved ruin heuristics, embedded in an iterated local search solver, produce 8 new best-known solutions on large-scale CVRPLib instances and a lower average gap than HGS and AILS-II.
-
BuildEvo: Designing Building Energy Consumption Forecasting Heuristics via LLM-driven Evolution
BuildEvo evolves interpretable Python heuristics for building energy forecasting via LLM-driven search, reporting lower error on five BDG2 buildings than the baselines tested.
-
STRCMP: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization
STRCMP's GNN-plus-LLM code search for MILP and SAT heuristics does not consistently beat AutoSAT in the paper's own reported numbers.
-
Evolutionary Computation and Large Language Models: A Survey of Methods, Synergies, and Applications
A survey that maps bidirectional synergies between evolutionary computation and large language models and proposes a taxonomy plus research gaps.
Discussion (0). Continue with ORCID to comment.