REVIEW 33 cited by
Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
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
Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
read the original abstract
Heuristics are widely used for dealing with complex search and optimization problems. However, manual design of heuristics can be often very labour extensive and requires rich working experience and knowledge. This paper proposes Evolution of Heuristic (EoH), a novel evolutionary paradigm that leverages both Large Language Models (LLMs) and Evolutionary Computation (EC) methods for Automatic Heuristic Design (AHD). EoH represents the ideas of heuristics in natural language, termed thoughts. They are then translated into executable codes by LLMs. The evolution of both thoughts and codes in an evolutionary search framework makes it very effective and efficient for generating high-performance heuristics. Experiments on three widely studied combinatorial optimization benchmark problems demonstrate that EoH outperforms commonly used handcrafted heuristics and other recent AHD methods including FunSearch. Particularly, the heuristic produced by EoH with a low computational budget (in terms of the number of queries to LLMs) significantly outperforms widely-used human hand-crafted baseline algorithms for the online bin packing problem.
Forward citations
Cited by 33 Pith papers
-
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
AutoTTS discovers width-depth test-time scaling controllers through agentic search in a pre-collected trajectory environment, yielding better accuracy-cost tradeoffs than hand-designed baselines on math reasoning task...
-
Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
EPB distills NCO models into evolving program portfolios via LLM-driven textual-numerical optimization, matching original performance while exposing stage-dependent heuristic-like behavior.
-
FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
FrontierOR benchmark shows frontier LLMs outperform Gurobi on solution quality and efficiency in only 31% of one-shot cases and 50% with test-time evolution on hard large-scale optimization tasks.
-
Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design
Latent Heuristic Search performs continuous optimization over learned embeddings of heuristics, using normalizing flows and LLM prompting to discover competitive solvers for TSP, CVRP, KSP, and OBP.
-
SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution
SMCEvolve applies Sequential Monte Carlo sampling to LLM program search with adaptive resampling, mutation mixtures, and convergence control, delivering finite-sample complexity bounds and benchmark gains over prior systems.
-
Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers
LLM-generated combinatorial solvers achieve highest correctness when the model formalizes problems for verified backends rather than attempting to optimize search, which often causes regressions.
-
Budget-Efficient Automatic Algorithm Design via Code Graph
A code-graph and correction-based LLM search framework outperforms full-algorithm generation at equal token budgets on three combinatorial optimization problems.
-
AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
AHD Agent trains a 4B-parameter LLM via agentic RL to actively use tools for automatic heuristic design, matching or exceeding larger baselines across eight domains with fewer evaluations.
-
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
AutoTTS discovers superior test-time scaling strategies for LLMs via cheap controller synthesis in a pre-collected trajectory environment, outperforming manual baselines on math benchmarks with low discovery cost.
-
Inference-Time Budget Control for LLM Search Agents
A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.
-
Automated Large-scale CVRP Solver Design via LLM-assisted Flexible MCTS
LaF-MCTS uses LLM-assisted flexible MCTS with a three-tier hierarchy, semantic pruning, and branch regrowth to automatically compose decomposition-enhanced CVRP solvers that outperform state-of-the-art methods on CVRP...
-
C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving
C-TRAIL combines LLM commonsense with a dual-trust mechanism and Dirichlet-weighted Monte Carlo Tree Search to improve trajectory planning accuracy and safety in autonomous driving.
-
AlphaEvolve: A coding agent for scientific and algorithmic discovery
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, ...
-
SpecAHD: Localize to Specialize for Automated Heuristic Design in Large-Scale Routing Problems
A coupled bilevel LLM search that specializes repair heuristics to local regions within one routing solution cuts held-out cost by up to 57.7% versus competing AHD methods.
-
LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning
Online behavioral cloning of a decoder-only Transformer on elite GRASP trajectories beats GPU-accelerated classical GRASP by ~28 makespan units on Taillard 50×20 PFSP.
-
SCOPE: Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization
SCOPE evolves LLM-generated auxiliary objective functions and selects a validated portfolio of them to guide fixed combinatorial search engines under strict black-box query budgets.
-
EvoPINN: Agentic Discovery of Executable Algorithms for Physics-Informed Neural Networks
An LLM-guided, execution-verified evolutionary search discovered PINN training algorithms that beat the seed network on four PDE benchmarks and matched expert-designed baselines on three.
-
Automated Discovery Has No Universally Superior Harness
No fixed discovery harness is reliably superior across 12 model–problem pairs, OpenEvolve-style recipes underperform simpler alternatives, and online pruning of weak partial runs improves budget-matched performance.
-
Evolutionary Algorithm-Guided LLMs for Physics-Informed Neural Network Design
An evolutionary loop that feeds measured PINN outcomes to an LLM produced a 95.38% MSE reduction on a 1D wave equation, though only in one of two runs.
-
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
A survey of 1,250 papers organizes AI self-improvement along two axes—what is improved and loop closure—finding that demonstrated self-improvement strength tracks a verification hierarchy from formal verifiers down to...
-
Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions
A single Qwen3-8B agent co-evolves weights, guidance/evaluation harness code, and solutions, matching GPT-OSS-120B+Claude Code on classification and reaching packing SOTA after repairing broken evaluators.
-
LLM-Driven Heuristic Frame-Level Quantization Parameter Adaptation for VVenC
An LLM evolutionary framework generates executable heuristics for frame-level QP adaptation in VVenC that improve rate-distortion performance over fixed-QP and Lagrangian baselines.
-
RACL: Reasoning-Agent Control Layers for Continuous Metaheuristic Learning
RACL lets a reasoning agent discover and apply control rules to a metaheuristic by observing operational memory and testing bounded interventions, shown on vehicle routing with reported cost improvements over baselines.
-
MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design
MeEvo couples natural evolution and metacognitive evolution in cycles to improve LLM-based automatic heuristic design, reporting stronger and more stable results than prior architectures on five optimization problems.
-
MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design
MeEvo cyclically couples natural and metacognitive evolution in LLM-based automatic heuristic design to achieve stronger performance and lower variance on optimization problems.
-
LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks
UH-NAS uses LLMs as evolutionary operators in a swappable-backend NAS to co-optimize neural architectures for accuracy and inference energy on physical hardware such as optical MZIs, producing more diverse and robust ...
-
Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches
LLM agent translates user prompts into model patches and selects primal-aware re-optimization techniques for large-scale dynamic problems, shown on supply-chain and exam-scheduling cases.
-
HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization
HMACE deploys Proposer, Generator, Evaluator, and Reflector agents in an evolutionary loop to generate and refine heuristics for NP-hard problems, reporting lower optimality gaps and token costs than baselines on TSP ...
-
COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation
COEVO unifies correctness and multi-objective PPA optimization in a single evolutionary loop for LLM RTL generation, reporting 97.5% and 94.5% Pass@1 on VerilogEval/RTLLM benchmarks plus best PPA on 43 of 49 designs.
-
ResearchEVO: An End-to-End Framework for Automated Scientific Discovery and Documentation
ResearchEVO automates the discover-then-explain cycle by evolving algorithms via fitness-driven LLM co-evolution and generating grounded, anti-hallucination research papers through sentence-level RAG.
-
TransGP: Task-Conditioned Transformer-Guided Genetic Programming for Multitask Dynamic Flexible Job Shop Scheduling
TransGP uses a task-conditioned Transformer to guide genetic programming toward elite heuristics and generate task-specific rules for multitask dynamic flexible job shop scheduling, outperforming standard GP and handc...
-
EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation
EvoGens uses rank-based mutation, semantic-aware crossover, and lightweight evaluation to evolve populations of LLM-generated scientific ideas, boosting novelty and diversity metrics.
-
Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches
An LLM agent converts user prompts into optimization-model patches and selects primal-based re-optimization methods from a toolbox to produce feasible solutions for dynamic supply-chain and exam-scheduling problems.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.