PAGENT integrates static and dynamic program analysis guidance with an LLM agent to improve automated proof-of-concept generation success by 132% over prior agentic methods.
Mirage- bench: Llm agent is hallucinating and where to find them.arXiv preprint arXiv:2507.21017, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Trajel introduces a five-type taxonomy and benchmark for trajectory-level hallucinations in multi-agent LLM workflows, showing existing final-answer benchmarks miss common failures.
citing papers explorer
-
Program Analysis Guided LLM Agent for Proof-of-Concept Generation
PAGENT integrates static and dynamic program analysis guidance with an LLM agent to improve automated proof-of-concept generation success by 132% over prior agentic methods.
-
Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows
Trajel introduces a five-type taxonomy and benchmark for trajectory-level hallucinations in multi-agent LLM workflows, showing existing final-answer benchmarks miss common failures.