Papers by Jessie Zeng

GenGO

Omakase Read Later

Search

Papers by Jessie Zeng

Findings

2026.findings-acl

data generation approach
CUA-as-a-Judge
optimization process enhances task scores
pre-shift mean CUA rating
addressing *
full-lifecycle application synthesis
heuristic optimization problem
continuous integration
user-demand task scores
optimization step

2026

1 papers

Apeiron: A Scalable LLM-agentic Framework for Autonomous Full-lifecycle Demand-optimized Application Synthesis (2026.findings-acl)

Copied to clipboard

Junyan Cheng, Ankit Srivastava, Jessie Zeng, Milenko Drinic, Jack W. Stokes

Challenge:	Traditional, rigid, 'one-size-fits-all' apps are struggling in the contemporary landscape.
Approach:	They propose a scalable and extensible framework for addressing amorphous user demands through autonomous, full-lifecycle application synthesis.
Outcome:	The proposed framework outperforms baselines in CUA ratings and user-demand task scores across 300 app scenarios, 2,400 personas, and 46,338 demands.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations