AI Paper Atlas

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

LLM-Guided Loop Bound Generation for Program Termination Verification

Zan Gong, Biting Huang, Fei He

ICML 2026 · Large language models › Agents, code and math · approach: Execution-based code verification

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 validation-feedback iteration to LoopyLoopy (Gemini-2.5-Flash) · Termination benchmarks (171 programs)programs solved: 125 -> 139Improved
add validation-feedback iteration to LoopyLoopy (Gemini-2.5-Flash) · Termination benchmarks (171 programs)avg time on solved (s): 140.8 -> 336.2Hurt
use loop bounds with LIFT workflow instead of ranking functions with feedbackLIFT vs Loopy+Iter · Termination benchmarks (171 programs)programs solved: 139 -> 152Improved
use ICE-DT as invariant learner instead of LaM4Inv (ablation)LIFT · Termination benchmarks (171 programs)programs solved: 120 -> 152Improved
use ICE-DT as invariant learner instead of LEMUR (ablation)LIFT · Termination benchmarks (171 programs)programs solved: 100 -> 152Improved
add progressive generation (conjunctive then lexicographic) vs unified generation (ablation)LIFT · Termination benchmarks (171 programs)programs solved: 141 -> 152Improved
add diagnostic feedback (violation witness and timeout diagnosis) (ablation)LIFT (Gemini thinking) · Termination benchmarks (171 programs)programs solved: 138 -> 152Improved
use LLM-generated loop bounds with ICE-DT validation instead of ranking functionsLIFT vs PROTON 2.1 · Termination benchmarks (171 programs)programs solved: 144 -> 152Improved
use a stronger LLM (Gemini-2.5-Flash vs DeepSeek-V3.1)LIFT · Termination benchmarks (171 programs)programs solved: 139 -> 152Improved

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