Skip to content
AI News HubLIVE
Original source2 min read

WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling

Summary

A new arXiv paper introduces WMLLM, a self-evolving optimization-agent framework that uses large language models for predict-then-act world modeling, combined with multi-turn agentic refinement, population-based search, and reinforcement learning to improve sample efficiency and final performance in black-box optimization, achieving state-of-the-art results on multi-objective molecular optimization under a limited evaluation budget.

SourcearXiv Machine LearningAuthor: Zhongzheng Li, Qingsong Ran, Shikun Feng, Nian Ran, Wenhao Li, Xiaoyuan Zhang, Yue Wang, Xiaoguang Zhao
WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 2 Jun 2026]

Title:WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling

View a PDF of the paper titled WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling, by Zhongzheng Li and 7 other authors

View PDF HTML (experimental)

Abstract:Black-box optimization problems remain challenging because of large, weakly structured, and high-dimensional search spaces. Existing methods often suffer from poor sample efficiency because they rely on direct candidate generation or trial-and-error refinement. A natural way to improve search efficiency is to use world modeling, which can help identify promising optimization directions before costly evaluation. Large language models can predict the outcomes of these candidates with nontrivial accuracy because of their implicit knowledge. Motivated by this observation, we propose WMLLM, a self-evolving optimization-agent framework based on predict-then-act world modeling. The agent first predicts promising directions and then acts to generate candidates. Combined with agentic multi-turn refinement, population-based search, and reinforcement learning, WMLLM refines both its implicit world model and its optimization strategy during search. Experiments on black-box optimization tasks, especially multi-objective molecular optimization, show that WMLLM improves sample efficiency and final optimization performance. On the multi-objective molecular optimization benchmark, WMLLM achieves state-of-the-art results under a limited evaluation budget.

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2609.01608 [cs.LG]

(or arXiv:2609.01608v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.01608

arXiv-issued DOI via DataCite

Submission history

From: Zhongzheng Li [view email] [v1] Tue, 2 Jun 2026 15:10:30 UTC (706 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling, by Zhongzheng Li and 7 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-09

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • WMLLM brings world modeling to black-box optimization by predicting promising directions before costly candidate evaluation, reducing trial-and-error waste.
  • The framework integrates agentic multi-turn refinement, population-based search, and reinforcement learning to co-evolve both its implicit world model and optimization strategy during search.
  • On multi-objective molecular optimization, WMLLM achieves state-of-the-art results under a limited evaluation budget while improving sample efficiency.

Highlights and analysis are generated automatically and may contain errors. Check the original source.