BenchJack audits 10 AI agent benchmarks, synthesizes exploits achieving near-perfect scores without task completion, surfaces 219 flaws, and reduces hackable-task ratios to under 10% on four benchmarks via iterative patching.
arXiv preprint arXiv:2502.17521 , year =
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
representative citing papers
LiveFact is a new time-aware benchmark that evaluates LLMs on reasoning with dynamic and incomplete information for fake news detection, identifying a significant reasoning gap in model behavior.
CFMS is a coarse-to-fine framework that uses MLLMs to create a multi-perspective knowledge tuple as a reasoning map for symbolic table operations, yielding competitive accuracy on WikiTQ and TabFact.
STELLAR-E modifies the TGRT Self-Instruct framework to produce tailored synthetic LLM evaluation datasets that score an average 5.7% higher on LLM-as-a-judge metrics than existing language-specific benchmarks.
Authors call for contamination-resistant LLM benchmarks that exploit Transformer training-inference asymmetry and require new mathematical methods for cross-architecture interoperability.
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
citing papers explorer
-
Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack
BenchJack audits 10 AI agent benchmarks, synthesizes exploits achieving near-perfect scores without task completion, surfaces 219 flaws, and reduces hackable-task ratios to under 10% on four benchmarks via iterative patching.
-
LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection
LiveFact is a new time-aware benchmark that evaluates LLMs on reasoning with dynamic and incomplete information for fake news detection, identifying a significant reasoning gap in model behavior.
-
CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning
CFMS is a coarse-to-fine framework that uses MLLMs to create a multi-perspective knowledge tuple as a reasoning map for symbolic table operations, yielding competitive accuracy on WikiTQ and TabFact.
-
STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator
STELLAR-E modifies the TGRT Self-Instruct framework to produce tailored synthetic LLM evaluation datasets that score an average 5.7% higher on LLM-as-a-judge metrics than existing language-specific benchmarks.
-
LLM Benchmark Datasets Should Be Contamination-Resistant
Authors call for contamination-resistant LLM benchmarks that exploit Transformer training-inference asymmetry and require new mathematical methods for cross-architecture interoperability.
-
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.