Publication
Too Many Tools, Too Much Confusion? Navigating Agentic Tool Selection at Scale
Jun 1, 2026 · Algorithms · Citations: 2
IG
Ilya Galyukshev
@ilya-galyukshev
Featured
Publication
DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers
Jan 1, 2026 · Conference on Empirical Methods in Natural Language Processing (EMNLP) · Citations: 1
Publication
Knowing When Not to Answer: Cross-Domain and Multi-Turn Generalization of Latent Underspecification Signals
Oct 6, 2026 · arXiv (Cornell University)
Publication
Processing Inconsistency Predicts Language Competence: LLM Evaluation Without Answer Labels on Turkic Languages
Jun 3, 2026 · Underline Science Inc.