A matched-pair protocol and Accurate Differentiation Rate metric reveal that conventional LLM accuracy on SAT problems is often inflated by over-predicting satisfiability, while cross-representation agreement exceeds 80 percent for most models.
arXiv preprint arXiv:2502.18474 (2025)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
The increasing complexity of software systems has driven significant advancements in program analysis, as traditional methods unable to meet the demands of modern software development. To address these limitations, deep learning techniques, particularly Large Language Models (LLMs), have gained attention due to their context-aware capabilities in code comprehension. Recognizing the potential of LLMs, researchers have extensively explored their application in program analysis since their introduction. Despite existing surveys on LLM applications in cybersecurity, comprehensive reviews specifically addressing their role in program analysis remain scarce. In this survey, we systematically review the application of LLMs in program analysis, categorizing the existing work into static analysis, dynamic analysis, and hybrid approaches. Moreover, by examining and synthesizing recent studies, we identify future directions and challenges in the field. This survey aims to demonstrate the potential of LLMs in advancing program analysis practices and offer actionable insights for security researchers seeking to enhance detection frameworks or develop domain-specific models.
years
2026 3representative citing papers
RSCB-MC is a risk-sensitive contextual bandit memory controller for LLM coding agents that chooses safe actions including abstention, achieving 60.5% proxy success with 0% false positives and low latency in 200-case validation.
A multi-agent, multi-stage LLM framework (VIC-RAGENT) outperforms direct prompting, CoT, and CodeAgent baselines on F1-score for detecting vulnerability-inducing commits on the V-SZZ dataset.
citing papers explorer
-
Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability
A matched-pair protocol and Accurate Differentiation Rate metric reveal that conventional LLM accuracy on SAT problems is often inflated by over-predicting satisfiability, while cross-representation agreement exceeds 80 percent for most models.
-
Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents
RSCB-MC is a risk-sensitive contextual bandit memory controller for LLM coding agents that chooses safe actions including abstention, achieving 60.5% proxy success with 0% false positives and low latency in 200-case validation.
-
Detecting Vulnerability-Inducing Commits via Multi-Stage Reasoning with LLM-Based Agents
A multi-agent, multi-stage LLM framework (VIC-RAGENT) outperforms direct prompting, CoT, and CodeAgent baselines on F1-score for detecting vulnerability-inducing commits on the V-SZZ dataset.