AgentFlow builds a framework-agnostic Agent Dependency Graph from agent program source code to support static analyses such as BOM generation and prompt-to-tool risk detection, evaluated on 5,399 real programs across five frameworks.
Available: http://doi.acm.org/10.1145/2892208.2892235
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
NESA presents a neuro-symbolic framework that decomposes static analyses into policy-defined sub-problems solved by parsers and LLMs to enable compilation-free customizable analysis with reduced hallucinations.
BugScope structures LLM bug detection into three human-mirroring steps and distills guidelines from examples, reaching 0.87 F1 on 33 real bugs while outperforming Claude and Cursor tools and uncovering 184 new issues in production code.
CHOP applies convex hull optimization to runtime profiles to eliminate an average of 80.12% of dynamic bounds checks, yielding up to 95.80% performance improvement over SoftBound on evaluated benchmarks.
CoVer extended to Fortran preserves analysis accuracy, reveals a bug in MPI-BugBench, and runs substantially faster than MUST while supporting multiple languages.
citing papers explorer
-
NESA: Relational Neuro-Symbolic Static Program Analysis
NESA presents a neuro-symbolic framework that decomposes static analyses into policy-defined sub-problems solved by parsers and LLMs to enable compilation-free customizable analysis with reduced hallucinations.
-
CHOP: Bypassing Runtime Bounds Checking Through Convex Hull OPtimization
CHOP applies convex hull optimization to runtime profiles to eliminate an average of 80.12% of dynamic bounds checks, yielding up to 95.80% performance improvement over SoftBound on evaluated benchmarks.