Appendix: Optimization Instructions

These are the instructions provided to CodeEvolver for each benchmark experiment.

HotpotQA Instructions

HotpotQA is designed to contain information from Wikipedia.

What's Allowed

Constraints

Available Services

Wikipedia colbert-server (Via dspy.Retrieve)

Ideas for Optimization

HoVer Instructions

HoVer is designed to retrieve information from 2017 Wikipedia Abstracts (5.9M) using multi-hop retrieval.

Task Type: Document Retrieval

This is a document retrieval task. The metric measures whether the correct supporting documents are retrieved — it does NOT measure claim verification or fact-checking accuracy. Do not add claim verification, fact-checking, or classification modules. Focus on improving retrieval recall and precision through better queries, re-ranking, or retrieval strategies.

What's Allowed

Constraints

Available Services

Wikipedia colbert-server (Via dspy.Retrieve)

Ideas for Optimization

Additional note: If you increase k retrieved per query, do not increase it greater than 25 per query as it may overload the Colbert server.

PhantomWiki Instructions

Task Type: Document Retrieval + Question Answering

This is a document retrieval + Question Answering task. The metric measures F1 score — which includes the precision of predicted answers as well as the recall of all available answers. Some questions have multiple correct answers.

To score high, the system requires being able to reason over multiple retrieval steps. Additionally, many questions have multiple correct answers, so the system must be able to reason over multiple chains of logic simultaneously.

The core difficulty of PhantomWiki is the large amount of information that must be processed across multiple chains of logic. Additionally, if context accumulates across multiple chains of logic and the context is too long, the model can suffer from context rot.

What's Allowed

Constraints

Ideas for Optimization

Available Services

Additional notes: Many answers are surfaced over multiple steps of reasoning and retrieving (i.e., pure parallel querying is unlikely to work without multiple retrieval steps). Different questions require different numbers of retrieval steps. RLMs underperformed in a previous trial and are not recommended.