AI Paper Atlas

Research map / Large language models / Agents, code and math

Sharing State Between Prompts and Programs

Ellie Y Cheng, Logan Weber, Tian Jin, Michael Carbin

ICLR 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add specialization to Python and optimizations (eager variable loading, caching) to Nightjar (ablation)Nightjar (Baseline) · SPSBenchruntime overhead: reduces runtime overhead by 2.0-2.1xImproved
use shared program state instead of manual implementationNightjar · SPSBenchlines of code: 42.0 -> 25.1Improved
use shared program state instead of manual implementationNightjar · SPSBenchtask accuracy: +4-19%Improved
use shared program state instead of manual implementationNightjar · SPSBenchruntime: 0.4-4.3x manual implementationsHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy