Pith. sign in

REVIEW 10 cited by

Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2501.08603 v3 pith:FH7ELPHA submitted 2025-01-15 cs.AI

Zhi Zheng , Zhuoliang Xie , Zhenkun Wang , Bryan Hooi This is my paper
classification cs.AI
keywords heuristicsheuristicllm-basedtreeautomaticcarlocomplexdesign
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Handcrafting heuristics for solving complex optimization tasks (e.g., route planning and task allocation) is a common practice but requires extensive domain knowledge. Recently, Large Language Model (LLM)-based automatic heuristic design (AHD) methods have shown promise in generating high-quality heuristics without manual interventions. Existing LLM-based AHD methods employ a population to maintain a fixed number of top-performing LLM-generated heuristics and introduce evolutionary computation (EC) to iteratively enhance the population. However, these population-based procedures cannot fully develop the potential of each heuristic and are prone to converge into local optima. To more comprehensively explore the space of heuristics, this paper proposes to use Monte Carlo Tree Search (MCTS) for LLM-based heuristic evolution. The proposed MCTS-AHD method organizes all LLM-generated heuristics in a tree structure and can better develop the potential of temporarily underperforming heuristics. In experiments, MCTS-AHD delivers significantly higher-quality heuristics on various complex tasks. Our code is available.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. AutoSND: From Execution Evidence to Structural Policies for Automated Network Dismantling Heuristic Discovery

    cs.AI 2026-08 conditional novelty 7.0 of 10

    A three-stage LLM search framework converts execution evidence into structural policies and discovers network dismantling programs with strong quality and low runtime.

  2. SpecAHD: Localize to Specialize for Automated Heuristic Design in Large-Scale Routing Problems

    cs.AI 2026-07 conditional novelty 6.5 of 10

    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.

  3. EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models

    cs.CV 2026-03 conditional novelty 6.0 of 10

    Iterative latent thought refinement plus terminal text grounding lets diffusion models solve multi-step visual reasoning tasks at 92.1% average accuracy, beating DiffThinker by 8.3 points.

  4. iDSE: Navigating Design Space Exploration in High-Level Synthesis Using LLMs

    cs.AR 2025-05 conditional novelty 6.0 of 10

    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.

  5. Reasoning LLMs are Wandering Solution Explorers

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Six current reasoning LLMs, including commercial systems, exhibit structured-search failures on verifiable computation tasks and degrade as the solution space grows.

  6. Explainable AI-assisted Optimization for Feynman Integral Reduction

    hep-ph 2025-02 conditional novelty 6.0 of 10

    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.

  7. URS: A Unified Neural Routing Solver for Cross-Problem Zero-Shot Generalization

    cs.LG 2025-09 conditional novelty 5.0 of 10

    A single RL-trained route-construction model, fed a unified data representation plus LLM-written feasibility masks, produces competitive solutions on 107 VRP variants including 96 unseen at training time.

  8. Large Language Models Reasoning Abilities Under Non-Ideal Conditions After RL-Fine-Tuning

    cs.AI 2025-08 reject novelty 5.0 of 10

    RL fine-tuning of LLMs improves clean-benchmark accuracy while degrading accuracy under three injected-distractor evaluation scenarios, though one of the three scenarios contradicts the headline claim.

  9. Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Large reasoning models frequently ignore explicitly injected ground-truth solutions mid-trajectory and continue to overthink, often ending on incorrect answers.

  10. A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving

    cs.NE 2025-09 conditional novelty 4.0 of 10

    A literature survey that classifies LLM-based optimization research into modeling and solving, with solving divided into LLMs as optimizers, low-level components, and high-level managers.

Pith tools