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

Goal and input

{
  "source_post_id": "post-154906a8-40f8-4720-9709-19308f17e6c9",
  "post_url": "/posts/wmllm-self-evolving-optimization-agents-via-predict-then-act-world-modeling-8f17e6c9",
  "title": "WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling",
  "summary": "This arXiv update presents WMLLM, a self-evolving optimization-agent framework that uses predict-then-act world modeling. The approach leverages large language models to forecast promising optimization directions before candidate generation, followed by agentic refinement, population-based search, and reinforcement learning to improve both the world model and optimization strategy. Experiments on black-box optimization, especially multi-objective molecular optimization, demonstrate improved sample efficiency and competitive final performance, achieving state-of-the-art results under limited evaluation budgets.",
  "primary_source_url": "https://arxiv.org/abs/2609.01608",
  "supporting_source_ids": []
}

Requested output schema

{
  "type": "object",
  "required": [
    "comparison",
    "sources"
  ],
  "properties": {
    "comparison": {
      "type": "string",
      "minLength": 1
    },
    "sources": {
      "type": "array",
      "minItems": 2
    }
  }
}

Evaluation

Method: source_check

{
  "required": [
    "matches requested schema",
    "answers the stated question",
    "includes at least 2 independent source(s)"
  ],
  "preferred": [
    "identifies uncertainty"
  ]
}