AI News HubLIVE
Original source2 min read

Predicting Performance of Symbolic and Prompt Programs with Examples

The research paper introduces a coin-flip model to predict program performance from few examples, finding that symbolic programs have all-or-nothing priors while prompt programs have diffuse priors, explaining why passing a few tests certifies symbolic but not prompt programs. RAP method retrieves similar tasks to construct proxy priors.

SourcearXiv Machine LearningAuthor: Chengqi Zheng, Keya Hu, Shuzhi Liu, Tao Wu, Kevin Ellis, Yewen Pu

[2605.21515] Predicting Performance of Symbolic and Prompt Programs with Examples

[Submitted on 15 May 2026]

Title:Predicting Performance of Symbolic and Prompt Programs with Examples

View a PDF of the paper titled Predicting Performance of Symbolic and Prompt Programs with Examples, by Chengqi Zheng and 5 other authors

View PDF HTML (experimental)

Abstract:LLM prompting is widely used for naturally stated tasks, yet it is unreliable it may succeed on a few test cases but fail at deployment time. We study performance prediction: given a program, either symbolic (e.g. Python) or a prompt executed on an LLM, and a few in-domain examples, predict its performance on unseen tasks from the same domain. We use a simple coin-flip model, treating each pass/fail program execution as a Bernoulli random variable, whose success probability is the programs unknown performance. In this model, performance depends entirely on: 1) the observed execution outcomes on test cases, and 2) a prior over performances. We compile empirical performance priors from a corpus of diverse programs and tasks, and find that performance for symbolic programs (e.g., Python) are all or nothing, while prompt programs have a diffuse prior with many nearly-correct programs. This difference explains why a few passing tests can certify symbolic programs but not prompt programs. Building on this insight, we develop RAP (Retrieved Approximate Prior), which retrieves similar tasks and prompt programs from an existing corpus to construct a proxy prior, which is then used to predict performance. We show RAP achieves solid performances.

Subjects:

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

Cite as: arXiv:2605.21515 [cs.LG]

(or arXiv:2605.21515v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.21515

arXiv-issued DOI via DataCite

Submission history

From: Chengqi Zheng [view email] [v1] Fri, 15 May 2026 10:58:01 UTC (2,847 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Predicting Performance of Symbolic and Prompt Programs with Examples, by Chengqi Zheng and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-05

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?)