ResearchEsoLang-Bench: LLM Coding Benchmarks Measure Memorization Not ReasoningarXiv·high signalNovel benchmark using esoteric languages proves massive gap between mainstream vs esoteric performance. Current benchmarks largely measure memorization.SourceSource pagearXiv↳ Follow the threadStack layer / Threat patternPiSAs Benchmarks Cross-User Privacy Leaks in Shared Agentic SystemsarXivStack layer / Update threadVisual Action Outcome Reasoning Alignment Improves VLM Physical ReasoningarXivStack layerCoding Before Testing Biases an LLM's Own Test Suite Toward Its Buggy CodearXivUpdate threadELSA3D Unifies 3D Generation and Language Reasoning in One BackbonearXivStack layer / Threat patternAirflowAttack Fools Infrared Remote-Sensing VLMs With Physical PerturbationsarXivSame source domain / Semantic neighborData Analysis in the Wild Benchmarks LLMs on Messy Real-World DataarXivContrastRMISC Is a Large-Scale Real-World Corpus for Time-Series Foundation ModelsarXivSame source domain / Semantic neighborEmpirical Study Quantifies Diminishing Returns in LLM Repair LoopsarXiv