Add paper: LLM Program Optimization via Retrieval Augmented Search

Open Beginner friendly
#265 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
68/100
Issue type
Documentation
Clarity
Mostly clear
Activity status
Quiet
Tech stack
machine-learning
Domain
documentation

Research direction

Review the repository’s existing paper-list format and locate the appropriate entry point for adding a paper. Use the linked arXiv page and code repository to verify the title, publication details, and links, then follow the surrounding formatting conventions. Done means the paper appears in the relevant list with working links and no formatting inconsistencies.

Written by the indexing model from the issue text.

Description

Hi there!

Thank you for curating this repository! If you're still accepting new papers, I would like to suggest our work "LLM Program Optimization via Retrieval Augmented Search", [arxiv] [code] published in ACL 2026 Findings - it achieves large performance improvements on the PIE benchmark (proposed in "Learning Performance-Improving Code Edits", ICLR 2024).

Disclosure: I am one of the authors of the ACL paper. Please let me know if you would prefer I open a pull request instead.

Best,
Sagnik

Dominant language
No language data
Stars
3.4k
Forks
239
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from codefuse-ai/Awesome-Code-LLM

All issues in codefuse-ai/Awesome-Code-LLM

Similar issues

More Documentation issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.