IBM · 7 records

dateidtitleauthorsvenue↑
2026-10-212610.29722Retrieval Augmented Generation CompositionalityIdo Levy et al.arXiv48
2026-09-302609.37236Asking for What Was Never Requested: Horizontal and Vertical Proactivity in AgentsIdo Levy et al.arXiv30
2026-06-192606.19704Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM AgentsDhaval C. Patel et al.arXiv42
2026-05-212605.20630Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute PipelinesAlimurtaza Mustafa Merchant et al.arXiv9
2026-05-202605.18827Code-Guided Reasoning for Small Language Models: Evaluating Executable MCQA ScaffoldsPrateek Biswas et al.arXiv6
2026-05-182605.08614DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic RulesDevin Yasith De Silva et al.arXiv6
2026-05-152605.14051SPIN: Structural LLM Planning via Iterative Navigation for Industrial TasksYusuke Ozaki et al.arXiv1