Pith. sign in

REVIEW 4 cited by

Minimizing False Positives in Static Bug Detection via LLM-Enhanced Path Feasibility Analysis

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.10322 v1 pith:V3ORUWOB submitted 2025-06-12 cs.SE

classification cs.SE
keywords analysisdetectionfalsefeasibilityllm4pfapathpositivesstatic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Static bug analyzers play a crucial role in ensuring software quality. However, existing analyzers for bug detection in large codebases often suffer from high false positive rates. This is primarily due to the limited capabilities of analyzers in path feasibility validation with multiple conditional branches and complex data dependencies. While current LLM-based approaches attempt to address this issue, their effectiveness remains limited due to insufficient constraint cascade analysis and scalability challenges in large projects. To address this challenge, we propose an iterative path feasibility analysis framework LLM4PFA. By leveraging LLM agent based targeted constraint reasoning, and key context-aware analysis driven by agent planning, LLM4PFA effectively enhances complex inter-procedural path feasibility analysis for minimizing false positives in static bug detection. Evaluation results show that LLM4PFA precisely filters out 72% to 96% false positives reported during static bug detection, significantly outperforming all the baselines by 41.1% - 105.7% improvements; meanwhile LLM4PFA only misses 3 real bugs of 45 true positives.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments

    cs.CR 2026-07 conditional novelty 7.0 of 10

    Adaptive adversarial source-code comments evade four LLM vulnerability detectors at >90% success on 125 real null-pointer bugs without altering program behavior.

  2. Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills

    cs.CR 2026-05 conditional novelty 7.0 of 10

    SKILLSCOPE detects undisclosed security behaviors in LLM skill implementations via security property graphs and taxonomy-based consistency checking, identifying confirmed inconsistencies in 9.4% of 4,556 evaluated ski...

  3. Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering

    cs.SE 2026-01 conditional novelty 6.0 of 10

    LLM agents can remove most SAST false positives (from 98.3% to 6.3% on OWASP in the best setup), but the benefit depends strongly on backbone model and weakness category, and can suppress real vulnerabilities.

  4. Using LLMs to Adjudicate Static-Analysis Alerts with Error Reduction Techniques

    cs.SE 2026-07 conditional novelty 5.5 of 10

    Mid-tier reasoning LLMs with consistency checks and LLM reasoning evaluation adjudicate static-analysis alerts at ≥98% recall and ≥94.8% specificity across Juliet, FormAI, and SV-COMP.

Pith tools