AI Paper Atlas

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

ABSINT-AI: Agentic Heap Abstractions for Abstract Interpretation

Michael Wang, Kexin Pei, Armando Solar-Lezama

ICML 2026 · Large language models › Agents, code and math · approach: Neural program synthesis and transpilation

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 LM-guided per-allocation-site abstraction selection (vs fixed symbolic cascade) (ablation)ABSINT-AI · 53-benchmark JS suite# false positives: 820 -> 618.7 (GPT-4.1-mini)Improved
make the LM agentic (interpreter queries, extra loop iterations) rather than single-shot (ablation)ABSINT-AI · 53-benchmark JS suite, GPT-4.1-minimean false positives: 645.7 -> 618.7Improved
make the LM agentic rather than single-shot (ablation)ABSINT-AI · 53-benchmark JS suite, GPT-4.1-miniintersection false positives: 572 -> 555Improved
add field_value widening strategy (ablation)ABSINT-AI · 53-benchmark JS suitemean false positives: 642.5 -> 618.7 (+23.8 when removed)Improved
add recency merging strategy (ablation)ABSINT-AI · 53-benchmark JS suitemean false positives: 637.6 -> 618.7 (+18.9 when removed)Improved
add role merging and depth widening strategies (ablation)ABSINT-AI · 53-benchmark JS suitemean false positives: role +11.3, depth +9.1 when removedImproved
intersect warnings across multiple runsABSINT-AI · 53-benchmark JS suite, GPT-4.1-mini# false positives: 618.7 -> 555; full intersection 499Improved
use a newer GPT-5 family model instead of older modelsABSINT-AI · 53-benchmark JS suitemean false positives: 616.9 (Qwen3-32B) to 640.3 (GPT-5.4-mini)No clear effect
replace TAJS/WALA with ABSINT-AIstatic analysis for null/undefined access · 53-benchmark JS suite# false positives: TAJS 711 -> 618.7; WALA 1327 -> 618.7Improved
replace TAJS/WALA with ABSINT-AIrun time · 53-benchmark JS suiterun time: about 20 seconds -> about 500 secondsHurt

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