ReasonVul deploys three LLM agents with independent analysis and structured debate to achieve 40% PairAcc and 72.52% F1 on PrimeVul, outperforming baselines by 81% in PairAcc.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.SE 5years
2026 5representative citing papers
LLM agents resolve fewer than half of issues while satisfying design constraints despite passing tests, as shown by a benchmark of 495 issues and 1787 constraints from six repositories.
Controlled experiments show PLM-GNN hybrids improve code tasks over GNN-only baselines, with PLM source having larger impact than GNN backbone.
VulWeaver improves Java vulnerability detection to 0.75 F1 by enhancing dependency graphs with LLM semantic fixes, extracting full context from slices plus implicit usage info, and applying type-specific meta-prompting with majority voting.
Proposes a two-stage on-the-fly input adaptation framework to reduce mispredictions in code language models across understanding tasks without retraining or additional supervision.
citing papers explorer
-
Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection
ReasonVul deploys three LLM agents with independent analysis and structured debate to achieve 40% PairAcc and 72.52% F1 on PrimeVul, outperforming baselines by 81% in PairAcc.
-
Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution
LLM agents resolve fewer than half of issues while satisfying design constraints despite passing tests, as shown by a benchmark of 495 issues and 1787 constraints from six repositories.
-
PLMGH: What Matters in PLM-GNN Hybrids for Code Classification and Vulnerability Detection
Controlled experiments show PLM-GNN hybrids improve code tasks over GNN-only baselines, with PLM source having larger impact than GNN backbone.
-
VulWeaver: Weaving Broken Semantics for Grounded Vulnerability Detection
VulWeaver improves Java vulnerability detection to 0.75 F1 by enhancing dependency graphs with LLM semantic fixes, extracting full context from slices plus implicit usage info, and applying type-specific meta-prompting with majority voting.
-
On-the-Fly Input Adaptation for Reliable Code Intelligence
Proposes a two-stage on-the-fly input adaptation framework to reduce mispredictions in code language models across understanding tasks without retraining or additional supervision.