Signals 4 · free daily AI digest

Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark

Paper recorded by Signals 4 on 2026-09-23 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-23 on arXiv · recorded by Signals 4 on 2026-09-24

Category: cs.AI · 人工智能 · first seen 2026-09-24

Abstract

Large language models (LLMs) are increasingly used in coding tasks, but their ability to reason about code execution remains unclear. Existing repository-level QA benchmarks mainly evaluate static code understanding and often rely on LLM-based evaluation, while execution-reasoning benchmarks are mostly limited to snippets or functions. We introduce SWE-Flux, a repository-level benchmark for dynami

Read on arXiv →

#3 most recent of 380 cs.AI papers we have recorded · ↑ newer: Where Should I Join? Robot Group Joining via Language-Guided Goal Pred · ↓ older: Order-Invariant Answers, Order-Sensitive Representations in Mathematic
Cite this page: Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark: the #3 most recent of 380 cs.AI papers we have recorded (as of 2026-09-23). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/can-llms-reason-about-runtime-behavior-a-repository-level-dynamic-benchmark.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions